Research on anomaly detection and operational status evaluation methods for smart electricity meters based on hybrid deep learning

Figures Abstract To address the limitations of single-image feature information and the insufficient recognition capability of traditional power quality disturbance (PQD) identification systems, this paper proposes a PQD recognition method based on feature-image combination and an improved ResNet-18, following the concept of feature fusion. First, the PQD signal is subjected to variational mode decomposition (VMD) to obtain a series of intrinsic mode functions (IMFs) and a residual component. Second, the IMFs, residual component, original disturbance signal, and Subtract component are vertically concatenated into a component matrix, from which a color feature-component image is generated via a signal-to-image transformation method. Third, the original disturbance signal is processed using continuous wavelet transform (CWT) to produce a time–frequency scalogram. Finally, the color feature-component image and the wavelet time–frequency image are combined and input into an improved six-channel ResNet-18 for training and disturbance classification. Simulation analyses of the proposed PQD identification method are conducted and compared with commonly used recognition systems. The results demonstrate that the proposed method exhibits strong noise robustness, effectively extracts PQD feature information, and achieves higher recognition accuracy. Citation: Zhang J, Zhao Y, Zhang J, Bai Z (2026) Research on anomaly detection and operational status evaluation methods for smart electricity meters based on hybrid deep learning. PLoS One 21(6): e0350561. https://doi.org/10.1371/journal.pone.0350561 Editor: Keshun You, University of South China, CHINA Received: January 12, 2026; Accepted: May 14, 2026; Published: June 3, 2026 Copyright: © 2026 Zhang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data Availability: All relevant data are within the manuscript and its Supporting Information files. Funding: This work was supported in part by the State Grid Science and Technology Project: SGSXSZ00YCJS2500441 (There was no additional external funding received for this study.) (“The funder provided support in the form of salaries for authors [Junqing Zhang], but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The specific roles of these authors are articulated in the ‘author contributions’ section.”). Competing interests: The authors have declared that no competing interests exist. 1. Introduction With the expansion of new energy grid integration and the widespread adoption of power electronic devices, power quality disturbances (PQD) in power systems are becoming increasingly complex and multifaceted, posing a potential threat to the reliable operation of end-user devices such as smart meters. Most existing deep learning-based PQD recognition methods employ a two-stage framework of “signal preprocessing + feature classification.” In the signal preprocessing stage, methods such as the Continuous Wavelet Transform (CWT) or Variational Mode Decomposition (VMD) are commonly used to extract features. However, existing research generally faces two core technical challenges: First, single-feature images lack sufficient information—wavelet time-frequency maps generated solely by CWT are sensitive to noise and struggle to capture deep-frequency-band features, while feature component maps generated solely by VMD fail to adequately represent high-frequency periodic disturbances. Although these two types of features are highly complementary, they have not been effectively integrated; Second, the number of input channels to the network is limited—the standard architecture of mainstream recognition networks, such as ResNet, supports only three input channels. This forces researchers to compress multiple feature maps into a single channel or a combination of three channels (e.g., compressing dual-channel GAF images for input, as in Reference [1]). This forced compression results in significant loss of original feature information, creating a bottleneck that limits further improvements in recognition accuracy. To address these issues, this paper proposes a PQD recognition method based on feature image combination and an improved ResNet-18 architecture. By performing six-channel fusion of color feature maps and wavelet time-frequency maps, and by specifically modifying the network structure to accommodate multi-channel inputs, the method enhances feature completeness while fully leveraging the feature extraction advantages of residual networks. In the context of “carbon peak and carbon neutrality,” the electrification of the new power system and the high proportion of renewable energy penetration into the grid are the main trends in the development of the power system. However, this inevitably brings about new power quality disturbance (PQD) issues: the emergence of new disturbances and the complexity of these disturbances [2]. These PQD problems not only affect users’ electricity experience and the normal grid connection of renewable energy generation but can also threaten the stability of grid operation [3]. At the same time, with the widespread monitoring of power quality, a massive amount of monitoring data will emerge [4]. Automatically detecting and classifying PQD online will significantly reduce the workload of manual processing, enhance the accuracy of problem analysis, help to quickly prevent the escalation of power quality issues, and facilitate the timely detection of underlying problems associated with certain violations, such as early equipment failures [5]. In recent years, many studies have proposed new PQD identification methods based on deep learning. These approaches avoid the subjectivity of manually selected features inherent in traditional methods and instead leverage the powerful automatic learning and feature-extraction capabilities of neural networks. They are well suited to PQD identification challenges in modern power systems and can achieve high classification accuracy. Such methods generally comprise two main steps: signal preprocessing and PQD classification [6, 7]. In signal preprocessing, common feature-extraction techniques include short-time Fourier transform (STFT), continuous wavelet transform (CWT), S-transform (ST), empirical mode decomposition (EMD), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and variational mode decomposition (VMD). Nonetheless, each method has limitations [8–12]. For example, STFT suffers from window selection constraints and spectral leakage, resulting in less distinct features; both CWT and ST provide favorable time-frequency energy characteristics when parameters are properly selected, yet they are highly sensitive to noise [8, 9]; EMD often leads to mode mixing and excessive pseudo-components in the decomposed PQD signal, which may confuse feature extraction; CEEMDAN and VMD greatly mitigate mode mixing, but the end effects of signal decomposition remain difficult to eliminate [10]. Although these preprocessing methods are well-developed, the complementarity between time-frequency analysis techniques and signal decomposition methods is often overlooked: time-frequency analysis transforms the original disturbance signal and extracts its time-frequency energy characteristics, enabling effective representation of multiple typical PQD types, whereas decomposition-based methods analyze individual components to capture deeper and more detailed disturbance characteristics [11, 12]. From both the perspective of representation and intrinsic feature properties, the two types of methods exhibit strong complementarity. In PQD identification, traditional machine learning methods such as random forest (RF), support vector machine (SVM), and artificial neural networks (ANN) struggle to achieve high accuracy due to their reliance on manual feature extraction and weak feature adaptability [12]. With the advancement of smart grids and the accumulation of power data, deep learning-based classification algorithms offer significant advantages. Long short-term memory (LSTM) networks and convolutional neural networks (CNNs) have produced notable results in PQD identification. Networks such as ResNet and DenseNet have demonstrated strong feature-extraction and generalization capabilities, and their adaptability enables high-accuracy PQD classification [13–15]. Currently, many two-stage PQD identification frameworks exhibit two major issues: They fail to consider the complementarity between features extracted via time-frequency analysis and signal decomposition, and do not integrate the two feature sets to form more complete input image.s. For example, one study uses CWT to generate time-frequency scalograms and inputs them along with the raw disturbance signal into CNN and LSTM models for parallel classification [16–21]. Although this approach combines time-frequency features with raw signal information, the raw signal itself offers insufficient discriminative detail [22–25], resulting in limited performance for composite PQDs and leaving substantial room for improvement [26–32]. Many transfer-learning-based neural network approaches simply append layers to pretrained networks and train only those added layers, without structurally adapting the network to the characteristics of the input images [33–38]. Although transfer learning allows rapid convergence by adjusting pretrained weights, its effectiveness diminishes when disturbance features diverge significantly from the pretrained network’s internal representations [39–42]. Moreover, the fixed structure constraints—such as the three-channel limit in ResNet—restrict the composition of input images and hinder accuracy improvements [43–46]. For instance, one study proposes a dual-channel GAF and ResNet-based PQD identification method; because ResNet accepts only three channels in its transfer-learning configuration, the authors were forced to compress two images into a single-channel composite to form an n × n × 2 input [1,47–50]. This reduces the embedded information and limits further gains in recognition accuracy [51–55]. To address these limitations, this paper proposes a PQD identification method based on the combination of feature-component color images and wavelet time-frequency images, together with an improved ResNet-18 architecture [56–59]. The wavelet time-frequency image fully preserves the time-frequency energy characteristics of the disturbance, while the feature-component color image leverages signal decomposition to extract deeper disturbance features [60–62]. Guided by the concept of feature fusion, the two images are combined into a six-channel composite image containing rich and comprehensive information [63–65]. This six-channel image is used to train an improved six-channel residual network, enabling the model to learn disturbance characteristics more effectively and thereby achieving high-accuracy classification. Simulation-generated PQD signals are used to validate the proposed method and compare it with commonly used identification approaches, demonstrating its effectiveness and superior recognition accuracy. The practical application of this study lies in the online monitoring and operational status assessment of smart electricity meters. As critical metering devices at the end of the power system, the metering accuracy and operational reliability of smart electricity meters are directly affected by power quality in the grid. When power quality disturbances such as voltage sags, voltage swells, harmonics, or transient oscillations, the metering chips in smart meters may experience measurement errors, internal clock drift, or even communication failures. Therefore, power quality disturbances are essentially one of the primary causes of operational abnormalities in smart meters. 2. PQD identification process The basic procedure of the proposed PQD identification method, which integrates feature-component color images and wavelet time–frequency images with an improved ResNet-18, is illustrated in Fig 1. The main steps are as follows: First, each PQD signal is decomposed using VMD to obtain its IMFs and residual component [66–68]. A Subtract component is also extracted and concatenated with the original disturbance signal v(t) to form a component matrix, which helps suppress endpoint effects inherent to signal decomposition methods and enhances the ability to capture hidden features of PQD signals [69–72]. Then, a signal–image encoding technique is used to transform the component matrix into a three-channel (n × n × 3) feature-component color image, thereby obtaining the signal’s time–frequency characteristics and deep structural features [73–75]. In parallel, each PQD signal is processed by CWT using the ‘db4’ wavelet to generate a three-channel (n × n × 3) wavelet time–frequency image that captures the time–frequency energy characteristics of the original disturbance [76]. Next, the feature-component color image and the time–frequency image are combined through channel-wise concatenation to form a six-channel (n × n × 6) composite feature image [77–79]. Finally, considering that noise may introduce interference, the composite image is input into the improved six-channel ResNet-18 for training. The network fully learns the time–frequency characteristics and deep feature representations embedded in both images, thereby constructing a high-accuracy PQD classification model. 3. Image selection based on feature complementarity This section proposes the construction method of feature-component color images and the concept of image combination based on signal decomposition [80–82]. First, the one-dimensional time series is decomposed using VMD to obtain its components, and a Subtract component is introduced and concatenated with the original disturbance signal to form a component matrix. Through a signal–image transformation method, a feature-component color image capable of representing both component-level characteristics and the deep-layer features of PQD signals is generated [68,83,84]. Next, a time–frequency analysis method is applied to generate the wavelet time–frequency image. Finally, following the concept of feature fusion, the two types of images are concatenated channel-wise to form a six-channel composite image, which serves as the final input for extracting the combined features of both images. 3.1. Composition of feature component color maps The matrix formed by concatenating various signal components is essentially a typical real-valued matrix. By normalizing the elements of this real-valued matrix to a specific interval, the elements acquire defined pixel intensities, thereby converting the real-valued matrix into a pixel matrix [85, 86]. Mapping the pixel values of the pixel matrix to the grayscale values encoded within a computer enables the rendering of a grayscale image [87–90]. On this basis, pseudocolor encoding techniques can be applied to convert the grayscale image into a three-channel RGB color image [70,91,92]. The use of color images not only enhances the embedded feature information but also facilitates feature extraction by neural networks [86]. The process of generating the feature-component color image through the signal-to-image conversion method is illustrated in Fig 2. The disturbance signal is a one-dimensional time-series signal. After VMD decomposition, a series of IMFs and a residual component are obtained. These components are vertically concatenated (each IMF and the residual component being a 1 × N row-vector sequence arranged in vertical order) to form a component matrix. The component matrix can then be normalized using Equation (1) to produce the corresponding pixel matrix [59,93,94]. (1)In the equation, P(m,n) represents the pixel value located at the m-th row and n-th column of the pixel matrix. The variable xi denotes the value of the i-th data point, while xmin and xmax represent the minimum and maximum values within the component matrix, respectively. By normalizing the numerical values in the component matrix to the range 0–255 using Equation (1), the elements of the matrix are assigned corresponding pixel intensities. Based on these pixel values, a grayscale image can be generated, and through pseudocolor encoding, the grayscale image can then be converted into a feature-component color image. The signal-to-image transformation method employed in this paper requires almost no manual intervention, thereby greatly reducing the subjectivity associated with manual feature selection. It not only significantly enhances the visual representation of features but also allows additional components with distinct characteristics to be adaptively incorporated by expanding the component matrix, thus improving the flexibility of component selection [95–98]. VMD can distribute the features of disturbance signals across the IMFs and residual components, thereby amplifying the characteristics of PQD signals. Therefore, this paper uses the VMD method to decompose the original PQD signal into multiple decomposition components (IMFs + residual component) and concatenates them into a component matrix [27,86,99,100]. However, in a strong noise environment, the high-frequency components may overlap with noise, making typical features blurred and difficult to extract [101–103]. At the same time, due to the endpoint effect inherent in signal decomposition methods, the features of decomposition components at both ends of the sampled signal are relatively weak. Thus, constructing a component matrix solely from IMFs and residual components has the following drawbacks: 1) the feature attenuation problem caused by the endpoint effect of the decomposition method is difficult to resolve; 2) in noisy environments, the feature information of some components is relatively blurred. To address these issues, considering the expandability of the component matrix, a component matrix augmentation method is adopted, introducing features of special components to supplement the information in the component matrix, thereby enhancing feature representation capability. To tackle the first issue, this paper first introduces the original disturbance signal. Reference [104] converts a one-dimensional PQD signal directly into a grayscale image to analyze disturbance signal features, achieving high recognition accuracy for a single disturbance signal under weak noise conditions [29,105–107]. The disturbance signal y(t) contains the signal’s fluctuation characteristics and possesses certain feature representation capability [108–112]. Its features, together with those of the residual component at both ends of the signal, can effectively compensate for the endpoint effect in decomposition methods [113, 114]. Therefore, incorporating it into the component matrix preserves the fidelity of the signal and effectively mitigates feature loss at the signal ends caused by the endpoint effect. To address the second issue, in order to amplify PQD features while suppressing the impact of noise, this paper constructs a Subtract component and introduces it into the component matrix, implemented as shown in Equation (2) [31,115–117]. (2)The Subtract component, obtained by taking the absolute difference between the original disturbance signal and the normal operation signal, can effectively extract the distinctive features of various PQD signals compared to normal operation [47,118–121]. Since the fluctuation amplitude of noise is smaller than that of disturbance features, the impact of noise on feature extraction after applying the Subtract operation is minimal, which also suppresses the influence of noise on disturbance identification. By introducing the above feature components, an augmented component matrix X can be constructed as shown in Equation (3) [122–125]. The introduced Subtract component and the original disturbance signal y(t) not only mitigate the endpoint effect problem inherent in the VMD method but also enhance the representation of signal features in noisy environments. Meanwhile, the IMFs and residual component Res(t) decomposed by VMD capture the deep features of various PQDs, resulting in a component matrix that contains sufficiently rich feature information [67,126–128]. (3)3.2. Generation of the wavelet time-frequency map CWT builds on the Fourier Transform (FT) by replacing the trigonometric basis functions in FT with finite-length, decaying wavelet basis functions and introducing scale and translation factors [129–131]. This allows the window function to adapt according to frequency characteristics, effectively representing both the time-domain and frequency-domain features of the signal and achieving good time–frequency analysis performance. As a result, the wavelet time–frequency map exhibits distinct temporal and spatial characteristics. The original disturbance signal can be transformed using CWT to generate time–frequency information, thereby obtaining the wavelet time–frequency map, as shown in Equation (4) [17–19]. (4)In the equation, s and τ represent the scale and translation parameters, respectively; ψ* denotes the complex conjugate of the scaled and translated wavelet function; and y(t) is the disturbance signal. Reference 15 applied the ‘cmor3-3’ wavelet to perform CWT on the original disturbance signal, generating wavelet time-frequency maps for each PQD signal, which were then fed into AlexNet for training and testing. This method achieved high recognition accuracy in weak noise environments, exceeding 95%, but the accuracy dropped significantly under strong noise conditions [132]. As shown in Fig 3, the wavelet time-frequency maps generated by the ‘cmor’ wavelet can reveal the rich time-frequency energy features of various PQDs; however, the ‘cmor’ wavelet produces horizontal stripe patterns in the time-frequency map, which are easily compressed, leading to feature loss. In contrast, the ‘db4’ wavelet exhibits a higher compatibility with PQD waveforms and displays vertical stripe patterns in the time-frequency map, effectively alleviating the feature compression problem [133]. Therefore, generating wavelet time-frequency maps using the ‘db4’ wavelet and adjusting the network structure can help further improve recognition accuracy [134]. 3.3. Feature-based color map and wavelet time-frequency map image combination As mentioned earlier, the complementarity between signal decomposition methods and time-frequency analysis methods is often overlooked, but effectively combining the two can significantly enhance the feature information in images [135–140]. The following analysis uses normal, spike, and flicker states under a 25 dB noise environment to illustrate the complementarity of features between the feature component color maps and wavelet time-frequency maps. As shown in Fig 4, due to noise interference and the small fluctuation amplitude of voltage spikes, the time-frequency energy features of normal and spike conditions in the wavelet time-frequency maps are very similar. For such highly similar images, it is difficult for the network to distinguish between them [136,141,142]. In contrast, the feature component color maps show clear blue stripe patterns, with evident feature differences, which help the network differentiate between the two types of disturbances. During flicker events, although the waveform does not show large distortions, many non-fundamental frequency components are present [143–147]. The feature component color map resembles the normal operation state with high similarity, while the high-frequency components are well represented in the wavelet time-frequency map, allowing the network to utilize these features for better recognition performance. Wavelet time-frequency maps analyze the original disturbance signal to extract its time-frequency energy features, but CWT is sensitive to noise and may not clearly reflect the feature changes of small fluctuations or periodic disturbances. Feature component color maps, on the other hand, analyze the decomposition components, the original disturbance signal, and the Subtract component, effectively capturing abrupt changes and fluctuation characteristics of the signal, but they struggle to represent features of signals mixed with high-frequency components [148–150]. Therefore, the two methods are highly complementary in feature representation, and the features extracted by the network exhibit similar complementary characteristics, which helps improve recognition accuracy. By concatenating the two types of images at the channel level, an input image with sufficient feature information can be constructed. As shown in Fig 5, both the feature component color maps and the wavelet time-frequency maps are three-channel images. By normalizing both types of images to 224 × 224 × 3, they can be decomposed along the R, G, and B channels into six 224 × 224 × 1 grayscale images, corresponding to six 224 × 224 × 1 pixel matrices [20–22,151–153]. By concatenating the grayscale images (pixel matrices) in a specific order, a multi-channel composite feature image of size 224 × 224 × 6 can be formed. On this basis, using multi-channel convolution kernels to extract complementary features achieves feature fusion. 4. Improved multi-channel ResNet ResNet, proposed after AlexNet and GoogLeNet, introduces a new “highway” structure [154, 155]. When building the network, it employs a novel residual module, as shown in Fig 6. The residual module adds a bypass branch to a single convolutional path, so that the output of subsequent layers depends on both the input from the previous layer [f(x, ω)] and the input at the bypass connection (Wx), as shown in Equation (5). ResNet leverages the special structure of multiple residual modules, which significantly reduces the number of parameters, alleviates the network degradation problem, and facilitates the extraction of deep features from images [156–161]. In multi-feature image recognition, the structural advantages of ResNet are more pronounced compared to earlier networks such as GoogLeNet and AlexNet. However, in ResNet, the input image size is 224 × 224 × 3, which can only accept a single three-channel color image or three grayscale images [162–165]. This limitation restricts the way multiple complementary feature images can be combined and prevents fully exploiting the complementarity between feature component color maps and wavelet time-frequency maps. Reference [166] addressed the feature loss problem of 2D-CNNs by proposing 3D-CNN for video fire detection, where 40 grayscale images were combined and features of a 256 × 256 × 40 image were extracted using 3D-CNN. Multi-channel images can enrich feature information and allow analysis across different time points. However, 3D-CNN has a clear drawback of slower computation and cannot leverage the structural advantages of existing network models. To enable the network to capture the time-frequency energy features of the original disturbance signal and learn the fluctuation characteristics of components in the feature component color maps, this paper proposes an improved multi-channel ResNet based on the traditional three-channel ResNet [109,167,168]. This structure allows multi-channel images to be input at the two-dimensional level and learns deep features from multi-channel images to ensure feature completeness. It achieves multi-feature image combination while fully exploiting ResNet’s structural advantages [169–172]. Taking six channels as an example, the improvement is as follows: Based on the traditional three-channel ResNet, the input image size is modified from 224 × 224 × 3–224 × 224 × 6, changing the input from a three-channel image to a six-channel image [173–175]. Since the number of convolution kernels is closely related to the number of channels and the network satisfies Equation (6) during convolution operations, the number of kernels must also be adjusted accordingly. Therefore, the number of kernels in the convolution layers is doubled to match the increased number of channels and the image size [176–178]. (6)In the equation, o(l_out) is the l-dimensional feature matrix output after the input feature matrix is processed by l convolution kernels; j represents the elements of the l-dimensional input feature matrix; represents the internal elements of the l convolution kernels; is the bias of the convolution layer; and lin and lout are the dimensions of the input and output feature matrices, respectively. At the same time, due to the increase in image channels and the corresponding adjustment of convolution kernels, the amount of features extracted by the network through convolution, pooling, and batch normalization operations is doubled compared to the unmodified ResNet [179–181]. To better allocate weights and biases in the fully connected layers, two additional fully connected layers are added: one with 2,000 units and another with 1,000 units, ensuring that the feature quantity matches the number of channels. Finally, a fully connected layer with units equal to the number of disturbance types and a Softmax function are added for classification [182–185]. Thus, the improved multi-channel ResNet is obtained. Its overall structure remains similar to the traditional ResNet, retaining ResNet’s structural advantages, while the modified network parameters allow it to handle multi-channel image recognition and expand the way input images can be constructed. 5. Case study analysis and discussion 5.1. PQD sample repository composition According to IEEE Std. 1159–2019 and relevant Reference [186–189], the sample library is constructed considering both single and composite PQDs. Besides the normal operating state (C0), single PQDs include voltage sags (C1), voltage swells (C2), voltage interruptions (C3), harmonics (C4), flicker (C5), transient oscillations (C6), voltage notches (C7), and voltage spikes (C8). Composite PQDs include voltage sag + harmonics (C1 + C4), voltage swell + harmonics (C2 + C4), voltage interruption + harmonics (C3 + C4), flicker + harmonics (C4 + C5), flicker + voltage sag (C1 + C5), and flicker + voltage swell (C2 + C5). Based on these models, the PQD sample library is constructed with a fundamental frequency of 50 Hz, a sampling frequency of 3.2 kHz, and 640 sampling points (10 cycles). Following references [187, 188], Gaussian white noise is used to simulate real-world sampled signals, and adding Gaussian noise at different signal-to-noise ratios (SNRs) reflects varying disturbance levels in actual data [190–192]. Therefore, this study compares PQD signals with random amplitude, random occurrence time, and random duration under no noise and SNRs of 40, 35, 30, and 25 within 10 cycles, making the generated disturbance signals closer to real measurements and avoiding artificial labeling [193, 194]. For the generated 15 types of PQD signals, feature component color maps and wavelet time-frequency maps are created according to the respective image generation methods to serve as training, validation, and test samples. In each noise environment, 300 image samples are generated for each disturbance type and divided into training, validation, and test sets at a ratio of 6:1:3. Cross-validation is used to monitor loss changes and automatically optimize and stop iterations. To enable the recognition model to handle various noisy signals, training sets from different noise environments are combined, allowing the network to learn signal features under different noise conditions and adapt through its generalization capability [195]. As a result, the total training set contains 13,500 images, the validation set contains 2,250 images, and testing is performed under different noise environments with a total of 1,350 × 15 test samples. Training environment parameters are listed in Table 1. 5.2. Comparative analysis of different signal preprocessing methods Reference [86] used an improved CEEMDAN to decompose fault signals in power systems and directly converted the decomposition components into images as input samples [196]. This image generation method is similar to the unaugmented matrix X used in this paper. The feature selection method in this study and that in reference [86] uses the typical feature component color maps generated from the PQD sample library, as shown in Fig 7 [197–199]. Since a single feature component color map is only a three-channel image, to verify the effectiveness of the components in the images, the training, validation, and test samples were input into ResNet-18 (with an added fully connected layer of 15 units) for training, validation, and testing. The recognition accuracy of the test samples is shown in Fig 8. As shown in Figs 7 and 8, reference [86] constructs the component matrix using only IMFs. Under noise interference, not only are some high-frequency components difficult to represent, but the problems caused by the endpoint effect are also unavoidable [200–203]. The feature information relies solely on the number of decomposition layers and is therefore limited, resulting in relatively low recognition accuracy. In contrast, the component matrix X, after feature completion (by introducing the residual component, y(t), and the Subtract component), compensates for the endpoint effect through y(t), suppresses noise interference effectively through the Subtract component, and extracts the deep features of PQDs through the various IMFs and residual components, greatly improving recognition accuracy. The recognition accuracy under different noise environments is consistently higher than the method proposed in reference [86]. The feature distribution of wavelet time-frequency maps is closely related to the choice of wavelet. Reference [16] used the ‘cmor3-3’ wavelet for analysis, but for power quality disturbance signals, the ‘db4’ wavelet provides a better match. Therefore, this section compares the recognition accuracy of wavelet time-frequency maps generated using ‘cmor3-3’ and ‘db4’ wavelets when input into AlexNet and ResNet-18 for training and recognition, as shown in Table 2. Based on the recognition results from a test set comprising 15 types of disturbances in a 25 dB high-noise environment (135 samples per type, totaling 2,025 test samples), we calculated the precision, recall, and F1 score for each type of disturbance. Specifically, the normal state (C0) achieved a precision of 96.67%, a recall of 96.67%, and an F1 score of 96.67%; the swell (C1) achieved a precision of 97.78%, a recall of 97.78%, and an F1 score of 97.78%; for a voltage dip (C2), the precision was 100.00%, the recall was 100.00%, and the F1 score was 100.00%; Voltage interruption (C3) has an accuracy of 98.89%, a recall of 98.89%, and an F1 score of 98.89%; Harmonics (C4) have an accuracy of 100.00%, a recall of 100.00%, and an F1 score of 100.00%; Flicker (C5) has a precision of 98.89%, a recall of 98.89%, and an F1 score of 98.89%; Transient oscillations (C6) have a precision of 100.00%, a recall of 100.00%, and an F1 score of 100.00%; Voltage dip (C7) has an accuracy of 88.89%, a recall of 88.89%, and an F1 score of 88.89%; Voltage spike (C8) has an accuracy of 94.44%, a recall of 94.44%, and an F1 score of 94.44%; Harmonics + voltage sags (C1 + C4) have a precision of 98.89%, a recall of 98.89%, and an F1 score of 98.89%; Harmonics + voltage dips (C2 + C4) have a precision of 100.00%, a recall of 100.00%, and an F1 score of 100.00%; For harmonics + voltage interruption (C3 + C4), the precision is 98.89%, the recall is 98.89%, and the F1 score is 98.89%; For flicker + harmonics (C4 + C5), the precision is 97.78%, the recall is 97.78%, and the F1 score is 97.78%; For Flicker + Voltage Sags (C1 + C5), the precision is 98.89%, the recall is 98.89%, and the F1 score is 98.89%; for Flicker + Voltage Sags (C2 + C5), the precision is 100.00%, the recall is 100.00%, and the F1 score is 100.00%. The overall macro-average precision is 98.00%, the macro-average recall is 98.00%, and the macro-average F1 score is 98.00%. These metrics show high consistency, indicating that the model exhibits good classification balance across different disturbance categories. Additionally, we plotted the confusion matrices for the 15 disturbance categories. From these matrices, it can be observed that the primary misclassifications are concentrated between voltage notches (C7) and voltage spikes (C8), as well as a small amount of confusion between flicker + harmonics (C4 + C5) and harmonics (C4). This is primarily because voltage dips and voltage spikes are both short-duration transient events; their features are easily overwhelmed by noise in a 25 dB high-noise environment, while the features of the flicker + harmonic composite disturbance may become similar to those of a single harmonic disturbance under the influence of noise. Apart from this, the confusion levels between the remaining disturbance categories are extremely low, with the classification accuracy for the vast majority of categories exceeding 95%. Supplementary analysis of the aforementioned evaluation metrics fully demonstrates that the power quality disturbance recognition method proposed in this paper—based on feature image combination and an improved ResNet-18—not only performs excellently in overall recognition accuracy but also maintains good classification precision and recall across different disturbance categories. The model’s classification reliability and robustness have been comprehensively validated. All models were trained and tested under the same data split and in a 25 dB noise environment to ensure the fairness of the comparison. The specific models compared include: a one-dimensional convolutional neural network (1D-CNN) as the baseline model, featuring three convolutional layers and two fully connected layers; a long short-term memory (LSTM) model, employing a two-layer LSTM architecture followed by a fully connected classification layer; a CNN-LSTM hybrid model, based on the architecture in Reference [13], which uses convolutional layers to extract local features before feeding them into an LSTM for temporal modeling; the InceptionTime model, which adopts the parallel multi-scale convolutional architecture described in Reference [14]; and the ViT (Vision Transformer) model, which divides a six-channel composite image into image blocks before feeding them into a Transformer encoder for classification. Experimental results show that under a 25 dB noise environment, the average recognition accuracy of 1D-CNN is 91.33%, LSTM is 90.67%, CNN-LSTM is 93.78%, InceptionTime is 95.11%, and ViT is 96.22%, while the improved six-channel ResNet-18 method proposed in this paper achieves an average recognition accuracy of 98.00%. Further analysis of the recognition performance for various disturbances shows that for voltage dips (C7) and voltage spikes (C8), which are prone to noise interference, the method proposed in this paper achieved 88.89% and 94.44%, respectively, significantly outperforming ViT’s 83.33% and 91.11% as well as InceptionTime’s 81.11% and 90.00%. These comparative results clearly demonstrate that, through a dual-path feature image fusion strategy combined with targeted network architecture improvements, our method possesses a distinct performance advantage over general-purpose advanced deep learning models in the specific task of power quality disturbance recognition. As shown in Table 2, using the ‘db4’ wavelet for CWT to generate wavelet time-frequency maps and inputting them into ResNet-18 for training achieves a high recognition accuracy. Even under a 25 dB noise environment, the recognition accuracy reaches 96.67%. This is because the waveform characteristics of the ‘db4’ wavelet are close to a sine wave and its features are less affected by frequency compression, while ResNet-18 has strong feature extraction capability and good convergence performance. As a result, the overall recognition rate of the network is significantly improved. Based on the idea of feature complementarity, the feature component color maps and wavelet time-frequency maps are combined into six-channel images. The improved six-channel ResNet is then used to train and recognize these multi-channel images. The network can learn features from different types of images, achieving feature complementarity. However, during iterative network training, some features may become blurred or even disappear. This section further discusses the complementarity of images after network training. Table 3 compares the recognition accuracy of different input images for various disturbances under a 25 dB noise environment. It can be seen that for single-image inputs, when using feature component color maps, the main recognition errors occur at C7 and C8, while for wavelet time-frequency maps, the main errors occur at C0 and C7 [204,205]. However, wavelet time-frequency maps outperform feature component color maps at C7 and C8, whereas feature component color maps outperform wavelet time-frequency maps at C0 and C1 [206]. By introducing image combination [207], for C8 disturbances, the network leverages the advantages of wavelet time-frequency maps to achieve 94.44% recognition accuracy [208], compared to only 88.89% with feature component color maps alone [209]. For C0 disturbances, the network uses the prominent features in the feature component color maps, achieving 96.67% recognition accuracy, while the single wavelet time-frequency map achieves only 85.56%. This further confirms that the two types of images maintain feature complementarity after neural network feature extraction [210]. Thus, the six-channel combined images contain more spatiotemporal features, achieving multi-feature complementarity between feature component color maps and wavelet time-frequency maps. Using the improved ResNet, they reach higher recognition accuracy [211,212]. Therefore, the six-channel images generated from the combination of the two types of images are selected as the optimal input method [213,214]. All power quality disturbance data used in this study were sourced from a simulation sample library built in accordance with the IEEE Std 1159−2019 standard. A total of 15 categories of disturbance signals were generated on the MATLAB platform, including normal conditions, 8 types of single disturbances, and 6 types of composite disturbances [215]. For each category, disturbance parameters (such as amplitude, duration, initial phase, harmonic order, etc.) were randomly set to enhance sample diversity. The fundamental frequency of the signals was set to 50 Hz, with a sampling rate of 3.2 kHz [216]. Each sample contained 10 cycles [217], totaling 640 data points; this parameter configuration aligns with the typical sampling settings of actual power quality monitoring devices [218]. To simulate measurement noise present in real-world acquisition environments [219], we added Gaussian white noise with varying signal-to-noise ratios (SNR) to the pure disturbance signals [220]. Specifically, this included five noise levels: no noise, 40 dB, 35 dB, 30 dB, and 25 dB, covering typical operating conditions ranging from low to high noise levels [221]. For each disturbance type and each noise level, we generated 300 independent samples [222], resulting in a total of 15 categories × 5 noise levels × 300 samples = 22,500 samples [223]. These were divided into training, validation, and test sets in a 6:1:3 ratio, with the training set containing 13,500 samples [224], the validation set containing 2,250 samples [225], while the test set for each noise level contains 1,350 samples [226]. When generating feature component color maps, we performed Variational Mode Decomposition (VMD) on each sample to obtain multiple Intrinsic Mode Functions (IMFs) and residual components [227]. We then constructed a component matrix by combining the original disturbance signal and the Subtract component [228], and generated a 224 × 224 × 3 color image using a signal-to-image conversion method [229]; To generate the wavelet time-frequency spectrum, we applied a continuous wavelet transform (CWT) using the ‘db4’ wavelet to the original perturbation signal [230], similarly producing a 224 × 224 × 3 color image [231]; the two types of images were concatenated by channel to form a 224 × 224 × 6 six-channel composite image, which served as the input to the improved ResNet-18 network [232]. The entire simulation experiment was conducted on a server equipped with an Intel Core i9-10900K CPU, an NVIDIA GeForce RTX 3090 GPU, and 64GB of memory [233]. Model training was performed using the PyTorch deep learning framework [234], with the Adam optimizer selected. The initial learning rate was set to 0.001 [235], the batch size to 64, and the maximum number of iterations to 5,000, with an early stopping mechanism employed to prevent overfitting [236]. It should be noted that constructing a sample database using simulated data is a common practice in the field of power quality disturbance recognition [237]. The primary reason for this is that it is difficult to obtain a comprehensive, annotated dataset in real-world environments that covers all disturbance types [238], varying severity levels, and different noise levels simultaneously. Simulated generation, however, enables the systematic construction of large-scale [239], high-quality, and accurately annotated sample databases under controlled conditions [240], providing a reliable foundation for the training and performance evaluation of deep learning models [241]; Additionally, by introducing Gaussian white noise with varying signal-to-noise ratios [242], this study effectively simulates the noise interference commonly found in real-world measurement environments, making the simulated samples more closely resemble the characteristics of field data [243]. 5.3. Comparative analysis of different ResNet architectures Since the residual blocks in different layers of ResNet have different parameter settings, there can be deviations in recognition accuracy for the same batch of images [244]. To determine the optimal structure for the improved residual network, this study compares the recognition accuracy of the improved ResNet-18 and the improved ResNet-34 using the same PQD image sample library [245]. As shown in Fig 9, in terms of recognition accuracy, both the improved ResNet-18 and improved ResNet-34 achieve high accuracy in noise environments with SNRs of 30 dB and above [246], as well as in noise-free conditions. However, under a 25 dB noise environment [247], the improved ResNet-18 clearly outperforms the improved ResNet-34 in recognition accuracy [248]. From the network structure perspective [249], the improved ResNet-18 is significantly simplified compared to the improved ResNet-34 [250], with fewer layers, which not only reduces computational load but also mitigates network degradation, facilitating better feature extraction and improved recognition accuracy [251]. 5.4. Comparative analysis of different image recognition network models Before the introduction of ResNet, many neural networks [252], such as AlexNet and GoogLeNet, had been widely applied in fault location and recognition [253, 254]. To verify the superior performance of the proposed method, AlexNet and GoogLeNet were modified in a manner similar to that described in Section 3 [255]. The same sample set was input into the improved AlexNet and GoogLeNet for training and testing [256], and the PQD recognition accuracy of different network structures was compared [257]. The training process curves and PQD recognition results for the improved networks are shown in Fig 10 and Table 4. From the training process curves in Fig 10, under the given validation conditions, the improved ResNet-18 converged by the 2,484th iteration [258]. In comparison, the improved GoogLeNet and improved AlexNet required 2,855 and 3,078 iterations, respectively, indicating that ResNet significantly reduces the number of iterations. It is also noticeable that the improved ResNet-18 quickly reaches high recognition accuracy in fewer iterations, demonstrating its rapid feature extraction and efficient learning capabilities [259]. Furthermore, during repeated training, the training loss of the improved ResNet-18 is lower than that of the other two networks. At the end of training, the loss for ResNet-18 is only 0.0828 [260], which is 0.073 lower than the improved AlexNet and 0.1994 lower than the improved GoogLeNet, showing a rapid loss reduction characteristic [261]. Thus, the improved ResNet-18 retains the structural advantages of the traditional three-channel ResNet-18 and exhibits stronger feature extraction ability and better convergence performance than the improved GoogLeNet and AlexNet [262]. As shown in Table 4, in weak-noise or noise-free environments, the network trained with the improved ResNet-18 achieves recognition accuracy above 99% for the test samples [263], approaching 100%, which is higher than that of the improved AlexNet and GoogLeNet. Under strong noise conditions, such as an SNR of 25 dB [264], the network trained with the improved AlexNet achieves only 93.33% recognition accuracy, while the improved GoogLeNet reaches 96.81%. The improved ResNet-18 achieves 98.00% [265], improving the accuracy by 4.67% over the improved AlexNet and 1.19% over the improved GoogLeNet. Particularly for C7 and C8 disturbances [266], which are easily affected or obscured by noise, the first two networks show poor feature extraction: the improved AlexNet achieves only 68.89% for C7 and 58.89% for C8 [267], and the improved GoogLeNet achieves only 80.00% for C7 [268]. In contrast, the improved ResNet-18 achieves 88.89% for C7 and 94.44% for C8. All 15 types of disturbance signals were selected from the original PQD sample database, and three different reference methods were used to calculate the Subtract component in a 25 dB high-noise environment [269]: Method A (the ideal noise-free theoretical waveform reference used in the original paper), Method B (using a 50 Hz ideal sine wave as the reference, with the amplitude set to the nominal value of 220 V, disregarding actual fluctuations) [270], and Method C (using a “historical undisturbed window” as the reference, i.e., selecting historical sampling data from five consecutive cycles prior to each disturbance and calculating the average waveform as the quasi-static normal signal for that sample). Based on this, a six-channel composite image was constructed following the same feature image generation process [271]. An improved six-channel ResNet-18 was used for training and testing, with a test sample size of 135 samples per disturbance category, totaling 2,025 samples. Experimental results show that: Method A (ideal noise-free theoretical waveform) achieved an average recognition accuracy of 98.00%, with a recognition accuracy of 96.67% for the C0 normal state [272], and recognition accuracies of 88.89% and 94.44% for the C7 voltage dip and C8 voltage spike, respectively; Method B (ideal sine wave reference) achieved an average recognition accuracy of 95.33%, a decrease of 2.67 percentage points compared to Method A [273]. The primary performance decline was observed in C5 flicker (from 98.89% to 91.11%) and C4 + C5 flicker+harmonics (from 97.78% to 88.89%), This is because the ideal sine wave cannot reflect the frequency fluctuations and amplitude drifts in actual grid operation, leading to the introduction of additional spurious differences in the Subtract component [274]; Method C (historical disturbance-free window reference) achieved an average recognition accuracy of 97.33%, a decrease of only 0.67 percentage points compared to Method A. Specifically, the recognition accuracy for C0 was 95.56% [275], while C7 and C8 were 87.78% and 93.33%, respectively. The performance gap with Method A remained within 1–2 percentage points. The decline in performance is primarily attributed to residual minor disturbances that may exist within the historical window and the impact of the selected window length on the calculation of the average waveform [276]. These results indicate that the improved ResNet-18 has strong feature extraction capability. With the combined features of the two types of feature images[277], the overall average recognition accuracy of test samples exceeds 98.00% under both weak and strong noise conditions, and the recognition accuracy remains above 94.44% for all disturbances except for C7 under a 25 dB noise environment[278]. This demonstrates that the proposed method has excellent noise robustness and recognition performance [279]. 5.5. Comparative analysis of different PQD identification systems The core innovations of this study are primarily reflected in the following three aspects [280]: First, at the feature construction level, we propose a dual-path feature image fusion strategy [281]. Variational Mode Decomposition (VMD) and Continuous Wavelet Transform (CWT) are used to generate feature component color maps and wavelet time-frequency maps [282], respectively [283]. We innovatively introduce the Subtract component (the absolute value of the difference between the original disturbance signal and the normal operating signal) to enhance the distinguishability of disturbance features. simultaneously forming a six-channel composite image through channel concatenation [284,285]. This achieves a deep integration of signal decomposition methods and time-frequency analysis methods at the feature level [286,287]. This approach differs fundamentally from existing research [288]: for example, existing methods using a “VMD+CNN” recognition framework typically feed the components decomposed by VMD directly into a one-dimensional CNN for classification [289,290], failing to fully leverage the advantages of image representation [291,292]; In contrast, the “Wavelet scalogram+ResNet” approach relies solely on a single wavelet time-frequency image, neglecting the deep frequency-band features that signal decomposition can extract [293,294]; As for research on multi-channel feature fusion networks, although existing work such as Reference [1,295,296] attempted dual-channel GAF image fusion, it was constrained by ResNet’s three-channel input structure and was forced to compress the two images into a single-channel composite image [297], resulting in loss of feature information. In contrast, this paper improves the network architecture to allow the six-channel composite image to be input in its entirety, thereby achieving true lossless fusion of multi-source features [298]. Second, at the network architecture level, addressing the limitation of existing transfer learning methods in adapting to multi-channel inputs [299], this paper systematically improves ResNet-18: The number of input channels was expanded from 3 to 6 [300]. Correspondingly, the number of convolutional kernels in the first layer was doubled from 64 to 128 to meet the requirements of convolutional operations [301]. Additionally, two new fully connected layers—one with 2,000 units and another with 1,000 units—were added to accommodate the rich feature information carried by the six-channel composite image [302], while retaining the structural advantages of the residual network in suppressing gradient explosion and network degradation [303]. Third, regarding the verification of feature complementarity, this paper systematically analyzes for the first time the complementary mechanisms between color maps of feature components and wavelet time-frequency maps in power quality disturbance recognition [304]. Through ablation experiments [305], we quantitatively verify the performance contributions of these two types of images across different disturbance types [306]. To more intuitively demonstrate the innovation and superiority of our method, we conducted a systematic comparison between our proposed method and recent representative hybrid deep learning-based power quality disturbance recognition methods [307]: Reference [15] employs a hybrid architecture with parallel input of one-dimensional signals and two-dimensional images into a CNN-LSTM, achieving an average recognition accuracy of 95.82% for 15 disturbance categories under a 25 dB noise environment; Reference [1] employs a method combining dual-channel GAF image fusion with ResNet, achieving an average recognition accuracy of 96.11% under a 25 dB noise environment; Reference [253] uses a method combining VMD decomposition with deep convolutional neural networks [308], achieving an average recognition accuracy of 96.33% under a 25 dB noise environment [309]; In contrast, the method proposed in this paper achieves an average recognition accuracy of 98.00% for 15 types of disturbances under the same 25 dB noise environment, representing improvements of 2.18, 1.89, and 1.67 percentage points over the methods in References [1,15], and [253], respectively. Particularly for the two disturbance types—voltage notches (C7) and voltage spikes (C8)—which are highly susceptible to noise interference, the recognition accuracy of the proposed method is 88.89% and 94.44%, respectively, significantly outperforming the 80.00% and 91.11% reported in Reference [1] and the 82.22% and 97.78% reported in Reference [253]. The above comparison results demonstrate that the method proposed in this paper [310], which combines dual-path feature image fusion with an improved six-channel ResNet, possesses distinct advantages in terms of recognition accuracy, noise robustness, and the ability to identify challenging disturbance types, fully reflecting the unique innovative value of this study. Reference [311] applied the Hilbert transform to the original disturbance signals to generate analytic signals, which were then processed to produce visual trajectory circles and input into ResNet-18 for training, testing, and recognition. Reference [312] used the L2 norm of distances between two points to generate an N × N power distance matrix, which was normalized and converted into a grayscale image. The generated grayscale images were then input into a 2D-ResNet for training, testing, and recognition. Both of these PQD recognition methods are feasible and effective, achieving high recognition accuracy under various noise environments. However, recognition of certain special PQDs under strong noise conditions still faces some challenges, whereas the method proposed in this paper shows advantages in these areas. Table 5 compares the recognition accuracy of each PQD using the aforementioned methods and the method proposed in this study. As shown in Table 5, the recognition accuracy of all methods decreases as noise increases. Under a 25 dB noise environment, the method proposed in this paper achieves 98.00% recognition accuracy, which is 1.26% higher than that of reference [311] and 4.37% higher than that of reference [312]. Moreover, for disturbances that are prone to misidentification, such as C0, C7, and C8, the proposed method demonstrates a clear advantage across all noise environments. By combining two feature-amplified images, the proposed method fuses the features of both color images, resulting in strong feature extraction capability. The introduction of the improved six-channel ResNet-18 further preserves ResNet’s structural advantages and allows six-channel image input, providing excellent recognition performance and generalization ability. In noise-free or 30–40 dB noise environments, the average recognition accuracy remains stable above 99.48%, and recognition accuracy under all noise conditions surpasses that of the methods proposed in the two referenced studies. 6. Conclusion To improve the recognition accuracy of various PQDs, this study overcomes the limitations of traditional methods and proposes a novel PQD recognition method based on the combination of feature images and an improved ResNet-18. This recognition system fully exploits the complete fusion of features from feature component color maps and wavelet time-frequency maps, as well as the strong feature extraction capability of the improved six-channel ResNet-18, achieving high recognition accuracy. The conclusions drawn from simulations and comparative experiments are as follows: - 1). Regarding input images, this study proposes a two-image combination method based on the concept of feature complementarity. Wavelet time-frequency maps capture the time-frequency energy features of PQD signals, while feature component color maps effectively reflect the fluctuation features of components. The combination of the two provides richer spatiotemporal feature information and stronger feature representation. In particular, the feature component color map introduces a new image construction method by concatenating components, expanding on traditional PQD image generation methods; however, the optimal selection and arrangement of components require further investigation. - 2). Regarding the recognition network, an improved multi-channel ResNet method is proposed for PQD classification. The improved ResNet-18 effectively suppresses gradient explosion and network degradation while automatically extracting deep features from multi-image combinations, achieving excellent recognition performance. This is particularly significant for scenarios with numerous monitoring points and large volumes of data, as it can substantially reduce misclassification. - 3). The proposed method demonstrates strong multi-image analysis capability. It is not only applicable to PQD classification but, with appropriate modifications to the underlying ResNet structure, can also be applied to time-series prediction problems affected by multiple factors, such as photovoltaic power forecasting. Supporting information S1 File. Figure: The minimum dataset for validating the algorithm in this paper (Figure.1-Figure.50.png, comprising 50 datasets). https://doi.org/10.1371/journal.pone.0350561.s001 (ZIP) References - 1. Dong S, Sarem M. DDoS attack detection method based on improved KNN with the degree of DDoS attack in software-defined networks. IEEE Access. 2020;8:5039–48. - 2. Chen Z, Xi Y, Shen Y. Recognition of multiple power quality disturbances based on a Kalman filter and deep belief network. Power System Protection and Control. 2022;50(7):81–90. - 3. Liu H, Zhang Z, Shu Z, Wang J, Song R, Tian H, et al. Ultrasonic detection of partial discharge in oil-paper insulation based on fiber-optic dual-coupled F-P sensor. Measurement. 2026;263:120172. - 4. Liao R, Zhang Y, Wang H, Zhao T, Wang X. Multi-objective optimisation of surveillance camera placement for bridge–ship collision early-warning using an improved non-dominated sorting genetic algorithm. Advanced Engineering Informatics. 2026;69:103918. - 5. Wang R, Guo T, Li Y, Meng D, Liang B. Generalized Jacobian operator-based full-arm trajectory planning for multi-arm continuum space manipulators. Aerospace Science and Technology. 2026;170:111559. - 6. Liu H, Yang T, Song R, Shu Z, Wang J, Tian H, et al. Fault Diagnosis method for OLTC defects based on Dual-Cantilever beam fiber Bragg grating sensing. Optics & Laser Technology. 2026;193:114169. - 7. Meng D, Guo T, Xiang R, Wang R, Tan J, Wang X, et al. An efficient solution method for workspace boundary of serpentine manipulators based on a unified kinematics model. IEEE Trans Syst Man Cybern, Syst. 2026;56(3):1790–803. - 8. Hou Y, Yu B, Yang Z, Wang J, Xiang W, Wu D, et al. Privacy-preserving federated SAR image target recognition with adaptive resource management in space-air-ground integrated networks. Pattern Recognition. 2026;177:113253. - 9. Dong S. Multi class SVM algorithm with active learning for network traffic classification. Expert Systems with Applications. 2021;176:114885. - 10. Hou Y, et al. EfficientSARNet: A light-weight, high performance and fast SAR image target recognition network. IEEE Sensors Journal. - 11. Hou Y, Zhao S, Xia X, Liwang M, Li Z, Xu N, et al. FedC-DAC: A federated clustering with dynamic aggregation and calibration method for SAR image target recognition. IEEE J Sel Top Appl Earth Observations Remote Sensing. 2026;19:3726–45. - 12. Liu J, Wu J, Wang N, Tian F, Li J. Surface reconstruction of BiSI nanorods for superb photocatalytic Cr(VI) reduction under near-infrared light irradiation. Chemical Engineering Journal. 2022;435:135152. - 13. Liu H, Zhang Z, Tian H, Song Y, Wang J, Shu Z, et al. Comparison of different coupling types of fiber-optic fabry–perot ultrasonic sensing for detecting partial discharge faults in oil-paper insulated equipment. IEEE Trans Instrum Meas. 2024;73:1–12. - 14. Hou Y, Wang Y, Xia X, Tian Y, Li Z, Quek TQS. Toward Secure SAR image generation via federated angle-aware generative diffusion framework. IEEE Internet of Things Journal. 2026;13(2):2713–30. - 15. Liu H, Zhang Z, Song R, Shu Z, Wang J, Tian H, et al. Pattern recognition method for detecting partial discharge in oil-paper insulation equipment using optical F-P sensor array based on KAN-CNN Algorithm. J Lightwave Technol. 2025;43(12):6004–12. - 16. Hou Y, Bai B, Zhao S, Wang Y, Wang J, Li Z. Federated dynamic aggregation selection strategy-based multi-receptive field fusion classification framework for point cloud classification. Computers, Materials and Continua. 2025;86(2):1–30. - 17. Zhu X, Khosravi M, Vaferi B, Nait Amar M, Ghriga MA, Mohammed AH. Application of machine learning methods for estimating and comparing the sulfur dioxide absorption capacity of a variety of deep eutectic solvents. Journal of Cleaner Production. 2022;363:132465. - 18. Liang X, Yu B, Dai Y, Wang Y, Hu M, Zhong H-J, et al. Three-dimensional printing resin-based dental provisional crowns and bridges: Recent progress in properties, applications, and perspectives. Materials (Basel). 2025;18(10):2202 pmid:40428939 - 19. Zou T. Salt reduction in processed meats: Current advances and future directions. Agricultural Science and Food Processing. 2024;1(1):4–20. - 20. Luo F, Wang S, Lv Y, Mu R, Fo J, Zhang T, et al. Domain knowledge-enhanced graph reinforcement learning method for Volt/Var control in distribution networks. Applied Energy. 2025;398:126409. - 21. Chen Y, Zhang G. New parameters identification of Proton exchange membrane fuel cell stacks based on an improved version of African vulture optimization algorithm. Energy Reports. 2022;8:3030–40. - 22. Wang S, Luo F, Fo J, Lv Y, Wang C. Two-stage spatiotemporal decoupling configuration of SOP and multi-level electric-hydrogen hybrid energy storage based on feature extraction for distribution networks with ultra-high DG penetration. Applied Energy. 2025;398:126438. - 23. Chen Y, Xu Y, Han X, Ma Q, Zhou W, Guo H, et al. Azacytidine shows potential in controlling the chilling injury of banana peel during cold storage. Food Control. 2024;159:110283. - 24. Yuan H, Feng K, Li W, Sun X. Multi-objective optimization of virtual energy hub plant integrated with data center and plug-in electric vehicles under a mixed robust-stochastic model. Journal of Cleaner Production. 2022;363:132365. - 25. Cao Y, Fan L, Wang W, He Y. Machine learning-driven acceleration of Mg-MOF-74 synthesis optimization for enhanced CO₂ adsorption. Sep Purif Technol. 2026;398(P1):138172. - 26. Yang C, Yang S, He Y, Fan L, Gao X, Tang M. Research on defect detection performance of silicon carbide wafer surface based on ESN-YOLOv8 algorithm. Comput Mater Sci. 2026;268:114656. - 27. Xu B, Rang G, Xie R, Li W, Gong D, Fan Z, et al. A prediction approach based on long short-term memory networks for dynamic multiobjective optimization. Expert Systems with Applications. 2025;283:127792. - 28. Xie J, Liu X, Lao X, Vaferi B. Hydrogen solubility in furfural and furfuryl bio-alcohol: Comparison between the reliability of intelligent and thermodynamic models. International Journal of Hydrogen Energy. 2021;46(73):36056–68. - 29. Yang C-Y, Min X-H, Zhao L, Wang Y-N. Real-time cutterhead torque prediction via cluster-based geological identification in karst shield tunneling. Tunnelling and Underground Space Technology. 2026;174:107736. - 30. Yang G, Ni N, Geng G, Peng G. FedLTN-CubeSat: Neuro-symbolic federated learning for intrusion detection in LEO CubeSat constellations. Mathematics. 2026;14(6):1047. - 31. Zhou J, Zeng C, Zhao W, Leng J, Liu Y. Critical bistability in variable cross-section metamaterials: PINN-driven transient stress recognition and adaptive energy dissipation. Chemical Engineering Journal. 2026;534:175093. - 32. Li R, Zhou X, Wu D, Wu S, Wang Y. Variable-gain subdivision pressure control algorithm for digital valve braking systems via partially open mode. IEEE Transactions on Industrial Electronics. - 33. Wang Z, Zhou H, Liu H. Physics-informed neural networks based digital volume correlation for displacement and strain measurements. Mechanical Systems and Signal Processing. 2026;248:113998. - 34. Naeem H, Dong S, Falana OJ, Ullah F. Development of a deep stacked ensemble with process based volatile memory forensics for platform independent malware detection and classification. Expert Systems with Applications. 2023;223:119952. - 35. Shang X, Fang H, Lu L, Zhang Z, Ma P. Partial gradient-enhanced multi-output sparse polynomial chaos expansion method for model representation. Reliability Engineering & System Safety. 2026;270:112132. - 36. Jiang L, Fang H, Shang X, Zhang Z. Hierarchical clustering weighted gaussian process regression low-fidelity model and application in airfoil drag coefficients prediction. IEEE Trans Aerosp Electron Syst. 2026;62:9070–81. - 37. Liu D, Lian J, Liu F, Ma B, Liu D, Shi J, et al. A refined numerical model for assessing low-pressure effects on ski-jump atomization at high-altitude dams. J Mt Sci. 2026. - 38. Sun X, Xu L, Yuan H, Wang G, Maleki B. Boosted conversion of restaurant waste oil into biodiesel using Fe3O4@UiO-66-NH2 magnetic heterogeneous nanocatalyst and its application on the diesel engine: Optimization via RSM. Renewable Energy. 2024;223:120007. - 39. Xu G, Shan P, Lai X, Hu Q, Yang S, Xu H. Thermomechanical behavior and damage mechanism of the lining backfill body of high-temperature thermal energy storage reservoirs in mines. Tunnelling and Underground Space Technology. 2026;171:107409. - 40. Yang Z, Zhang L, Jiang Y, Chen B, Yang M. Seepage-path-dependent CO2 hydrate formation and storage capacity enhancement in NGH reservoirs. Fuel. 2026;422:139217. - 41. Zuo T-Y, Di K, Li P, Jiang Y. Autonomous domain adaptation self-optimization approach for cross-domain industrial agents. ACM Trans Intell Syst Technol. 2026;17(1):1–25. - 42. Xu N, Liu G, Tan Q. Adjustable super-resolution microscopy with diffractive spot array illumination. Applied Physics Letters. 2020;116(25). - 43. Wang Y, Sun H, Zhao Y, Zhou W, Zhu S. A heterogeneous graph embedding framework for location-based social network analysis in smart cities. IEEE Trans Ind Inf. 2019;:1–1. - 44. Yang W-W, Liu Z, Song L-D, Lin Y-W, Zhang J-F, Qu Z-G. Advancing low-Pt catalyst layer design from multi-scale to cross-scale synergy optimization for high-performance and durable proton exchange membrane fuel cell. Renewable and Sustainable Energy Reviews. 2026;230:116681. - 45. Yan H, Ye L, Zhou T-L, Li Z, Ye T, Zhang F, et al. Physics-informed neural network for predicting multi-row film cooling superposition using Fourier transform and attention mechanism. Physics of Fluids. 2025;37(6). - 46. Zhao Y, Jiang S, An Z, Luo B. Experimental investigation of the bearing-deformation behavior of broken rocks in goafs under various influencing factors. Applied Sciences. 2026;16(9):4276. - 47. Gao Y, Wang Y, Yang N, Wang Q, Javadi B, Ai Q, et al. Multi-timescale distributed control for multi-energy virtual power plant clusters via cloud-edge collaboration. Applied Energy. 2026;414:127835. - 48. Xu N, Bohndiek SE, Li Z, Zhang C, Tan Q. Mechanical-scan-free multicolor super-resolution imaging with diffractive spot array illumination. Nat Commun. 2024;15(1):4135. pmid:38755150 - 49. Yang J, Zhu Y, Qin W, Wang S, Dai C, Li J. Higher-dimensional soliton structures of a variable-coefficient Gross–Pitaevskii equation with the partially nonlocal nonlinearity under a harmonic potential. Nonlinear Dyn. 2022;108(3):2551–62. - 50. Lin N, He N, Mo Y. An interpretable ensemble machine learning model for predicting carbon dioxide adsorption on magnesium oxide-based sorbents. Environmental Research. 2026;297(15):124126. - 51. He Z, Wu J, Cheng Y, Hu Z, Peng Q, Chen Y. Experimental study on high-temperature thermal oxidation and laser ignition of aged boron powder. Acta Astronautica. 2025;233:30–41. - 52. Dong S, Su H, Xia Y, Zhu F, Hu X, Wang B. A comprehensive survey on authentication and attack detection schemes that threaten it in vehicular Ad-Hoc networks. IEEE Trans Intell Transport Syst. 2023;24(12):13573–602. - 53. Xu B, Liu Z, Yan S, Schmitt RJP, He X. Strategizing renewable energy transitions to preserve sediment transport integrity. Nat Sustain. 2025;8(11):1314–27. - 54. Wu Y, Pi D, Zhou S, Yi Z, Dong Y, Wang W, et al. Ginsenoside Rh3 induces pyroptosis and ferroptosis through the Stat3/p53/NRF2 axis in colorectal cancer cells: ginsenoside Rh3 has anti-colorectal cancer properties. Acta biochimica et biophysica Sinica. 2023;55(4):587. - 55. Zhang X, et al. First-principles insights into 2D SnSe₂ monolayer as a promising anode for Li, Na, and K-ion batteries. Colloids and Surfaces A: Physicochemical and Engineering Aspects. 2026;736:139632. - 56. Gao Y, Li S, Xu T, Lakshminarayana S, Bu S, Gu C, et al. Distributed model predictive control strategy for multi-energy virtual power plant based on digital twin. IEEE Trans Smart Grid. 2026;17(3):1971–84. - 57. Chen G, Chen G, Peruzzini M, Barzagli F, Zhang R. Investigating the performance of ethanolamine and benzylamine blends as promising sorbents for postcombustion CO2 capture through 13C NMR speciation and heat of CO2 absorption analysis. Energy Fuels. 2022;36(16):9203–12. - 58. Wen X-J, Zhan Q, Wu D, Xu J, Qian B, Xu Q, et al. Construction of an S-scheme Bi12O17Cl2/CeO2 heterojunction for efficient photocatalytic degradation of ciprofloxacin and hydrogen evolution. Journal of the Taiwan Institute of Chemical Engineers. 2026;188:106769. - 59. Gu Y-F, Zhu L, Li J-H, Zhao G-Y. Preview MPC control of train active suspension based on Kalman filter disturbance estimation. Measurement. 2026;268:120616. - 60. Wang Y. Application of artificial intelligence in food industry: A review. Agricultural Science and Food Processing. 2025;2(2):68–88. - 61. Wu Q, Zhang Y, Wang X, Sun Y, Li Y, Zhu G. Crystallization of hard spheres within ellipsoidal confinement. Phys Rev E. 2026;113(2–2):025422. pmid:41857996 - 62. He S, Wang T, Spicer RA, Farnsworth A, Mulch A, Widdowson M, et al. Back to an ice-free future: Early Cretaceous seasonal cycles of sea surface temperature and glacier ice. Sci Adv. 2025;11(18):eadr9417. pmid:40315318 - 63. Xu B, Zheng Y, Li W, Gao X, Gong D, He J, et al. Handling multiobjective optimization problems with complex constraints: A constraints grouping-based approach. IEEE Trans Syst Man Cybern, Syst. 2025;55(6):3866–80. - 64. Zhan Y. Ultrasound as a technique to extract plant proteins: Effects, yields and modifications. Agricultural Science and Food Processing. 2025;2(2):89–105. - 65. Lu Y-Z, Sha H-Y, Di C, Zhu G-C. A cross-kingdom survival strategy: A methanotroph recruits a microalga for synergistic detoxification of metronidazole. J Hazard Mater. 2026;503:141127. pmid:41538935 - 66. Xu N, Williams C, Spicer G, Wang Q, Tan Q, Bohndiek SE. Fast label-free point-scanning super-resolution imaging for endoscopy. 2025. - 67. Zhang L, Wu T. Solving SAT by restricted spiking neural P systems with temporal division rules. Theoretical Computer Science. 2026;1078:116009. - 68. Lv J, Wang C, Xie L. Adaptive distributed observer design for nonlinear multiagent systems. Automatica. 2026;183:112625. - 69. Sun X, Wang G, Xu L, Yuan H, Yousefi N. Optimal estimation of the PEM fuel cells applying deep belief network optimized by improved archimedes optimization algorithm. Energy. 2021;237:121532. - 70. Lv J, Wang C, Xie L. Distributed output-feedback leader-following consensus of nonlinear multiagent systems. Automatica. 2025;177:112281. - 71. Xue Z, Han W, Zhuang X, Miao H, Chen H, Luo X, et al. Analysis of Sourdough’s Microbial Community and Flavor Components in Traditional Chinese Steamed Bread. Agricultural Science and Food Processing. 2025;2(2):106–15. - 72. Zhang M-S, Chiu C-F, Wang Y-N. Analysis of microbial methane oxidation capacity of landfill soil cover using quorum sensing. Environ Res. 2025;268:120781. pmid:39778618 - 73. Xu C. Beyond the breadbasket paradox : Rethinking agricultural adaptation in the age of climate coloniality. Agricultural Science and Food Processing. 2025;2(2):116–22. - 74. Chen G, Gao H, Fu K, Zhang H, Liang Z, Tontiwachwuthikul P. An improved correlation to determine minimum miscibility pressure of CO2–oil system. Green Energy & Environment. 2020;5(1):97–104. - 75. Liu S, Zhang Z, Wu Q, Feng C, Chen C, Hu X. Cross-scale crack evolution in pre-flawed sandstone under high temperature: Insights from a composition-aware thermal-mechanical grain-based model. Theoretical and Applied Fracture Mechanics. 2026;143:105450. - 76. Ehiem JC, Tosin P, Igbozulike AO, Oduma O, Okoro OI. Modeling of measured physical properties and determination of chemical composition of black tamarind (dialium guineense) seed. Agricultural Science and Food Processing. 2025;2(3):123–32. - 77. Shi Y, Wang Y, Wang LN, Wang WN, Yang TY. Bridge cable performance warning method based on temperature and displacement monitoring data. Buildings. 2025;15(12):2342. - 78. Wang Y-N, Li S-K, Li Z-Y, Garg A. Exploring the application of the MICP technique for the suppression of erosion in granite residual soil in Shantou using a rainfall erosion simulator. Acta Geotech. 2023;18(6):3273–85. - 79. Liu S, Zhao C, Lin Y, Wen Z. Microstructure-engineered shear thickening composites with controllable switching of rigid/flexible impact modes for adaptive protection. Composites Part A: Applied Science and Manufacturing. 2026;206:109750. - 80. Chen C, Hou S, An H, Du C, Wang Z, Ran H, et al. Igniting endogenous calcipoptosis via ER‐mitochondrial calcium shuttle hijacking for potent antitumor immunity. Advanced Materials. 2026;:e18631. - 81. Shi Y, Wang Y, Wang L-N, Wang W-N, Yang T-Y. Bridge tower warning method based on improved multi-rate fusion under strong wind action. Buildings. 2025;15(15):2733. - 82. Sun X, Wang G, Xu L, Yuan H, Yousefi N. Optimal performance of a combined heat-power system with a proton exchange membrane fuel cell using a developed marine predators algorithm. Journal of Cleaner Production. 2021;284:124776. - 83. Shen T, Cai Y, Liu L. Green supply chain with strategic retailers: Transportation-based carbon penalty. Energy Economics. 2025;145:108411. - 84. Wang Y, Li F, Li Y, Li J, Chen H, Bai Y. Effects of ultrasonic surface rolling process on microstructure and mechanical properties of metastable Fe50Mn30Co10Cr10 high-entropy alloy fabricated by laser directed energy deposition. J Mater Res Technol. 2025;39:26–46. - 85. Xu N, Zhang W, Zhu L, Li C, Wang S. Object 3D surface reconstruction approach using portable laser scanner. IOP Conf Ser: Earth Environ Sci. 2017;69:012119. - 86. Wang Y, Chen T, Liang Y, Sun H, Zhu Y. A novel cooling and power cycle based on the absorption power cycle and booster-assisted ejector refrigeration cycle driven by a low-grade heat source: Energy, exergy and exergoeconomic analysis. Energy Conversion and Management. 2020;204:112321. - 87. Anyene CC, Udorah DO, Nsofor PS, Nwakuba NR. Prospects of agrivoltaics as a sustainable mitigation solution to the nomadic cattle rearing crisis in Nigeria: A review. Agricultural Science and Food Processing. 2025;2(4):148–72. - 88. Yang F, Lv K, Zhao X, Kong D, Kong N, Luo Z, et al. Hierarchical heterostructures of MXene and mesoporous hollow carbon sphere for improved ion accessibility and rate performance. Chemical Engineering Journal. 2024;494:153246. - 89. Huang X, Kang N, Wang Q, El Mansori M, Guittonneau F. Wear of directed energy deposited H13 steel as a function of its graded microstructure. Tribology International. 2025;207:110617. - 90. Li Y, Qu K, Jiang R, Wang H, Zhao X, Yang Z, et al. Atomic-scale defect reconfiguration via thermally induced structural ordering for high-efficiency Sb2Se3 solar cells. ACS Nano. 2025;19(37):33460–72. pmid:40948239 - 91. Wang H, Cui L, Shen S, Gu W, Sui K, Fan W. Highly stable quasi‐solid thermocells for continuous power generation across a broad humidity range. Small. 2026. - 92. Liu J, Guo Z, Wu X, Ren Y, Hu M, Zeng H. Real‐time observation of breathing vortex solitons in a Yb:CALGO laser. Laser Photonics Reviews. 2025;20(2). - 93. Wei H-Y, Fan E-G, Guo H-D. Riemann–Hilbert approach and nonlinear dynamics of the coupled higher-order nonlinear Schrödinger equation in the birefringent or two-mode fiber. Nonlinear Dyn. 2021;104(1):649–60. - 94. Liu J, Guo Z, Hu M, Zeng H. Sub‐100 fs vortex beams generated from a Yb:CALGO laser. Laser Photon Rev. 2025;19. - 95. Chen G, Chen G, Cao F, Zhang R, Gao H, Liang Z. Mass transfer performance and correlation for CO2 absorption into aqueous 3-diethylaminopropylamine solution in a hollow fiber membrane contactor. Chemical Engineering and Processing - Process Intensification. 2020;152:107932. - 96. Nwakuba NR, Ofojioha OM, Ikechukwu KU, Ofoma AN, Chikwue MI, Oham PN, et al. Development and Sustainability Assessment of a Fish-drying Kiln: Eco-thermodynamic Insights. Agricultural Science and Food Processing. 2025;2(4):176–96. - 97. Yu N, Zeng X, Ma X, Sun Y, Wang Y, Chen B, et al. Preparation of Ce-Fe2O3/Al2O3 catalyst for simultaneous degradation of benzodiacetone and reduction of Cr(VI) by electro-Fenton process: Performance, mechanism, degradation pathways. J Alloy Compd. 2025;1045. - 98. Xu N, Williams C, Spicer G, Bohndiek SE, Tan Q. Resolution enhanced imaging for endoscopy using diffractive optics. Adv Opt Imaging Technol. 2022;12316:12–20. - 99. Xu B, Zheng Y, Li W, Gao X, Gong D, He J, et al. Handling multiobjective optimization problems with complex constraints: A constraints grouping-based approach. IEEE Trans Syst Man Cybern, Syst. 2025;55(6):3866–80. - 100. Zhang LT, Liang SY, An WY. A stress-rate-driven constitutive framework for rejuvenation in metallic glasses. Acta Mechanica Sinica. 2026. - 101. Zhang M, Yang Z, Ma Y, Huang T, Li Q, Gong P, et al. Oxide growth and surface fracture during high-temperature oxidation of Zr55Cu30Al10Ni5 metallic glass powders. Applied Surface Science. 2026;736:166816. - 102. Li H, Gao P, Tan H, Li H, Zhu H, Jiang M, et al. Interaction-aware dexterous robot for minimally invasive transcanal inner ear interventions. Nat Commun. 2026;:10.1038/s41467-026-72398–5. pmid:42031753 - 103. Wu G, Tan Y, Zeng J, Zheng J, Zhang R, Liu Y, et al. Laboratory tests of an eccentrically loaded strip footing above single underlying void. J Build Eng. 2025;111. - 104. Hou Y, Lv D, Liwang M, Wang J, Li Z, Xia X, et al. AsyncFed-SAR: Towards communication-efficient asynchronous federated learning for SAR image target recognition. IEEE Trans on Mobile Comput. 2026;:1–18. - 105. Guo B. Structural gatekeepers of photosynthesis: A critical review of CYN38 dimerization in chlamydomonas photosystem II repair. Agricultural Science and Food Processing. 2026;3(1):1–5. - 106. Wang P, Ma J, Wang Z, Jin D, Pan Y, Su Y, et al. Di-n-butyl phthalate negatively affects humic acid conversion and microbial enzymatic dynamics during composting. J Hazard Mater. 2022;436:129306. pmid:35739802 - 107. Xu C, Guo L, Hui J, Zhu L, Liu X, Jin Q, et al. Material removal mechanisms in hybrid fixed-loose abrasive machining of SiC. International Journal of Mechanical Sciences. 2026;312:111270. - 108. Hou W, Wei H. Data-driven robust day-ahead unit commitment model for hydro/thermal/wind/photovoltaic/nuclear power systems. International Journal of Electrical Power & Energy Systems. 2021;125:106427. - 109. Zhang D, Shan C, Li F, Liu P, Xing Y, Lan X, et al. Preliminary design and validation of a hybrid triangular rollable and collapsible boom based on high strain and shape memory polymer composites. Composites Part B: Engineering. 2026;:113647. - 110. Tong L, Fu L, Wu B, Xu C, Lim CW, Ding H. Particle shape effect on creep and fluidity of granular packing. J Eng Mech. 2025;151. - 111. Min X-Z, Zhang X, Xie Z-Y, Nikolaev A, Vorkamp K, Ma J-M, et al. Organic chemicals of Arctic concern in Russian coastal seas. Sci Bull (Beijing). 2026;71(4):946–59. pmid:41571477 - 112. Li J, Li L, Wang P, Guo Y, Wang Z, Hui X, et al. Designing cation/anion dual-acceptors inner interface in composite solid-state electrolyte for high-rate lithium metal batteries. Chemical Engineering Journal. 2026;539:176807. - 113. Wang Y, Gu W, Gong Y, Wang T, Hu X, Sui K, et al. Biomimetic low-porosity framework membranes for efficient power generation and acid recycling from industrial wastewater. Mater Horiz. 2026;:10.1039/d6mh00269b. pmid:42093511 - 114. Wang E, Xia J, Li J, Sun X, Li H. Parameters exploration of SOFC for dynamic simulation using adaptive chaotic grey wolf optimization algorithm. Energy. 2022;261:125146. - 115. Ding H, Yu Y, Xu C, Pu X, Guo W, Tong L. Analytical modeling for nonlinear seismic metasurfaces of saturated porous media. Int J Mech Sci. 2025;303. - 116. Song Y, Yang C, Tu J, Dong J, Zhang X. Multi-omics analysis of deep brain stimulation associated with brain-gut axis modulation and symptom amelioration in a Parkinson’s disease mouse model. Biol Direct. 2026;:10.1186/s13062-026-00778–4. pmid:42092952 - 117. Li K, Bao X, Li G, Wang Y, Zhu B, Cao Z. Design and fundamental dynamic mechanical analysis of large-scale submerged buoy systems: Experiment and numerical simulation. Ocean Engineering. 2026;357:125515. - 118. Wang E, Cheng P, Li J, Cheng Q, Zhou X, Jiang H. High-sensitivity temperature and magnetic sensor based on magnetic fluid and liquid ethanol filled micro-structured optical fiber. Optical Fiber Technology. 2020;55:102161. - 119. Fu J, Wang C, Liu M, Li X, Liu Y, Shi W, et al. HyperR3SNet: Leveraging Hyperbolic space and vision foundation models for remote sensing semantic segmentation. IEEE Trans Geosci Remote Sensing. 2026;64:5620016–5620016. - 120. Zou T. Turning voyage time into value: An integrated shipping-and-aging intervention for irish beef exports. Agricultural Science and Food Processing. 2026;3(1):19–24. - 121. Fang Y, Zhu S, Liao B, Li X, Liao G. Target localization with bistatic MIMO and FDA-MIMO Dual-mode radar. IEEE Trans Aerosp Electron Syst. 2024;60(1):952–64. - 122. Chen P, Nie X, Ning Y, Zhang Y. Learning efficient and adaptive cross-channel dependencies for weakly-supervised object detection. IEEE Trans Multimedia. 2025;27:8954–66. - 123. Meng L, Xi X, Han J, Qiao L, Yin Y, Chen X. Difficulty-aware pseudo-label correction Network for Fine-Grained Classification of Choroidal Neovascularization in OCT Images. IEEE Trans Multimedia. 2026;:1–12. - 124. Dong S, Zhang X, Zhou W. A security localization algorithm based on DV-Hop against sybil attack in wireless sensor networks. J Electr Eng Technol. 2020;15(2):919–26. - 125. Wang L, Ma Y, Yan Z, Zhang L, Hu Y, Zhao S. Giving or receiving: Impact of online socializing in online fitness community on physical activity and emotional state. Computers in Human Behavior. 2025;169:108669. - 126. Wang L, Bala H, Yan L (Lucy), Guo X. Physicians’ Contributions to Online Healthcare Platforms: Relative Effects of Herding Cues and Feedback Types. Journal of Management Information Systems. 2026;43(1):205–36. - 127. Zhang H, Chen Y, Zhu X, Zhou H, Yao Y, Li X. Mn2 -doped Zn2GeO4 for photocatalysis hydrogen generation. INTERNATIONAL JOURNAL OF ENERGY RESEARCH. 2019;43(9):5013–9. - 128. Wang Z, Zhou H, Liu H. Physics-informed neural networks based digital volume correlation for displacement and strain measurements. Mechanical Systems and Signal Processing. 2026;248:113998. - 129. Han T, Yi S, Zhang C, Li J, Chen X, Luo J, et al. Superlubrication obtained with mixtures of hydrated ions and polyethylene glycol solutions in the mixed and hydrodynamic lubrication regimes. J Colloid Interface Sci. 2020;579:479–88. pmid:32622097 - 130. Liu L, Chu C, Chen C, Huang S. MarineYOLO: Innovative deep learning method for small target detection in underwater environments. Alexandria Engineering Journal. 2024;104:423–33. - 131. Wang K, Zhu J, Zhang R, Ding W, Liu H, Chen T. Magnetorheological intelligent chiral metamaterials with ultra-low frequency bandgap. Engineering Structures. 2026;351:122074. - 132. Li Y, Zhang X, He Z, Xie J, Zhang Y, Wang J, et al. Response of sludge EPS under the action of coupled alternating electric field-ammonium persulfate dewatering technology: Structural changes and mechanism analysis. Chemical Engineering Science. 2026;323:123267. - 133. Dong S, Shu L, Nie S. Android malware detection method based on CNN and DNN bybrid mechanism. IEEE Transactions on Industrial Informatics. 2024;20(5):7744–53. - 134. Guo H, Dong Z-T, Yang Y-Y, Sui L, Wang W-J, Liang C, et al. Polarized electric field-mediated graphitic carbon nitride-based S-scheme heterostructure for efficient photocatalytic removal of bisphenol A. Applied Surface Science. 2025;682:161739. - 135. Hou W, Hou L, Zhao S, Liu W. A hybrid data-driven robust optimization approach for unit commitment considering volatile wind power. Electric Power Systems Research. 2022;205:107758. - 136. Liu S, Zhang J, Lin Z, Wang J. Assessment of rockburst proneness in thermally-damaged fractured granite: A quantitative analysis of energy evolution and strain localization intensity. Theoretical and Applied Fracture Mechanics. 2026;145:105677. - 137. Tong T, Qu W, Hua J, Chen D, Tan J, Lin J. Delamination detection in composite laminates using Lamb wave tomographic method based on sparse and probabilistic reconstruction. NDT & E International. 2026:103650. - 138. Naeem H, Cheng X, Ullah F, Jabbar S, Dong S. A deep convolutional neural network stacked ensemble for malware threat classification in internet of things. J CIRCUIT SYST COMP. 2022;31(17). - 139. Qi H-X, Yang S-Y, Miao Y-H, Cui L-G, Xue H, Hua J-D, et al. Prediction of sperm retrieval outcomes based on testicular ultrasound images and dense convolutional sparse coding. IEEE Sensors J. 2026;26(5):7292–307. - 140. Xu N, Liu G, Tan Q. High‐fidelity far‐field microscopy at λ/8 resolution. Laser Photonics Reviews. 2022;16(11):2200307. - 141. Zhang J, Zhang Y, Yao E. A new framework for traffic conflict identification by incorporating predicted high-resolution trajectory and vehicle profiles in a CAV context. Transportation Research Record: Journal of the Transportation Research Board. 2025;2679(11):445–62. - 142. Sun T, Xia W, Shu J, Sang C, Feng M, Xu X. Advances and challenges in machine learning for RNA-small molecule interaction modeling: Review. J Chem Theory Comput. 2025;21(18):8615–33. pmid:40921177 - 143. Xu N, Liu G, Zhao Y, Tan Q. Ultrahigh-aspect-ratio beam generation with super-resolution spot. Applied Physics Letters. 2021;119(9). - 144. Liu M, Jiang H, Hu C, Yu Z, Li Z. Pinning synchronization of complex delayed dynamical networks via generalized intermittent adaptive control strategy. Intl J Robust & Nonlinear. 2019;30(1):421–42. - 145. Xia W, Shu J, Sang C, Wang K, Wang Y, Sun T, et al. The prediction of RNA-small-molecule ligand binding affinity based on geometric deep learning. Comput Biol Chem. 2025;115:108367. pmid:39904171 - 146. Zhang X, Xu R, Nguyen HT, Zhou H. Mandatory information disclosure regulation and corporate cash holdings: Evidence from a quasi‐natural experiment. Int Rev Finance. 2026;26(1). - 147. Li S, Yan Y, Yu Y, Zhong Q, Hua L, Liao D. Fast finite-time position tracking control of electro-hydraulic servo systems with parametric uncertainty via dynamic surface and neural adaptive method. Mathematics. 2026;14(9):1551. - 148. Zhang LT, Duan YJ, Li BW, Qiao JC. Developments in the homogeneous deformation of metallic glasses: A brief review. Rare Metal Materials and Engineering. 2026. - 149. Xu N, Kong Z, Tan Q, Fu Y. Multiring pure-phase binary optical elements to extend depth of focus. Appl Opt. 2018;57(32):9643–8. pmid:30461747 - 150. Xu C, Ding J, Luo K, Yang X, Liu L, Yao L, et al. Dielectric–magnetic synergized pores modulation engineering in polymer aerogels for integrated electromagnetic wave absorption and infrared stealth. Composites Science and Technology. 2026;277:111552. - 151. Tian C, Chen Y. Image segmentation and denoising algorithm based on partial differential equations. IEEE Sensors Journal. 2020;20(20):11935–42. - 152. Shih Y. Ecosystem integration of marine conservation and coastal development in Taiwan. Frontiers in Environmental Science. 14:1764841. - 153. Wang W, Wang L, Jin S, Wang L, Gu L, Zhang H, et al. Dynamic spectral modulation devices based on reversible metal electrodeposition: Principles, modification strategies, and applications. Progress in Materials Science. 2026:101664. - 154. Liu B, Liu F, Song F. Coupling sPCA‐based statistical modeling with deep residual networks considering thermal effect for deformation forecasting in high dams. Structural Control and Health Monitoring. 2025;2025(1). - 155. Yue Z, Chen Y, Chen C, Ma K, Tian E, Wang Y, et al. Endophytic Bacillus altitudinis WR10 alleviates Cu toxicity in wheat by augmenting reactive oxygen species scavenging and phenylpropanoid biosynthesis. J Hazard Mater. 2021;405:124272. pmid:33097348 - 156. Abbas K, Hasan MK, Abbasi A, Mokhtar UA, Khan A, Abdullah SNHS, et al. Predicting the future popularity of academic publications using deep learning by considering it as temporal citation networks. IEEE Access. 2023;11:83052–68. - 157. Yao S, Jia H, Fan F, Zhao N, Kuang Y, Tang X, et al. Assessing ozone formation impact through SHAP interaction redistribution analysis: A novel framework for evaluating VOC photochemical loss and source interactions. Environmental Impact Assessment Review. 2025;115:108017. - 158. Sheng T, Tang Y, Cong H, Li J, Shi W, Tian X, et al. Baseline-free local stress measurement based on the multi-directional polarization characteristics of zero-group velocity Lamb waves. Mechanical Systems and Signal Processing. 2026;246:113887. - 159. Xu N, Tan Q, Fu Y. Design of diffractive optical elements for controllable axial long depth of focus. In: Proc. SPIE, 2018. 107440K. - 160. Ma B, Yang S, Tang Y, Zhi G, Zhong K, Liu Z. Attention-guided reinforcement learning for visual servoing control of multirotor UAVs. IEEE Trans Aerosp Electron Syst. 2026;62:4156–67. - 161. Liu W, Chen Z, Ma Z, Li J, Liu Y, Zhang Y, et al. High-load Ti3C2 MXene cathode through surface modification for degradable aqueous zinc-ion micro-supercapacitors with excellent energy density and anti-self-discharge. Chemical Engineering Journal. 2024;494:153149. - 162. Zhang C, Zhang H, Qiao J, Li Z, Alouini M-S. TIDES: Traffic intelligence with deepseek-enhanced spatial–temporal prediction. IEEE J Sel Areas Commun. 2026;44:2544–58. - 163. Huang J, Xu X, Yan Y, Zheng Y, Yao Y, Li Z, et al. Facile microwave synthesis of kilogram‐scale electrocatalysts with nanocarbons bridged cobalt active sites for enhanced oxygen electrocatalysis. Advanced Energy Materials. 2025;15(27). - 164. Zhou N, Yao Y, Liang X, Yao S, Yang C, Gui W. Optimization and evaluation of container-based EtherCAT communication in virtual PLCs. IEEE Trans Ind Electron. 2026;:1–12. - 165. Xu N, Xiao H, Kong Z, Tan Q. Axial multifocus beams formed by binary optical elements. IEEE Photonics J. 2019;11(2):1–10. - 166. Zhang F, Cannone Falchetto A, Wang D, Li Z, Sun Y, Lin W. Prediction of asphalt rheological properties for paving and maintenance assistance using explainable machine learning. Fuel. 2025;396:135319. - 167. Ren H, Miao Z, Feng X, Labidi A, Zhao Y, Wang C. Modulating the built-in electric field of S-scheme heterojunction via oxygen vacancies for boosting photocatalytic ciprofloxacin degradation. Chinese Chemical Letters. 2026;:112557. - 168. Li S, Yan K, Xie Y, Zhong Q, Yang J, Liao D. Finite-time neural adaptive control of electro-hydraulic servo systems with minimal input delay and parametric uncertainty via padé approximation. Mathematics. 2026;14(8):1368. - 169. Wang W, Lu B, Xu Y. Bibliometric exploration of infrastructure and natural hazards research in low and middle income countries toward sustainable development goals. Discov Sustain. 2025;6:1407. - 170. Huang J, Rasouli K, Zong Z, Wang P, Zhang Y, Li Z. Engineering a high-performance ZnFe2O4/BiOBr/MXene S-scheme heterostructure for CO2 photoreduction and wastewater treatment. Chemical Engineering Journal. 2026;530:173675. - 171. Fan D, Liu M, Shao Y, Yang L, Liu Y, Zhang Y, et al. Domain-specific large language model for maintenance decision-making on wind farms by labeled-data-supervised fine-tuning. Engineering. 2025. - 172. Tian Y. Exploration of power market dynamic scheduling algorithm based on reinforcement learning. Trajković L. IOS Press. 2025. 836–45. - 173. Xu N, Wu F, Liu Z, Zhan Y. Evaluating the academic outcome of AI-powered joint support for at-risk students. Computers and Education: Artificial Intelligence. 2025;9:100517. - 174. Zhang LT, Liang SY, Li BW, Qiao JC. Rejuvenation of metallic glasses by homogeneous flow: A review. Review of Materials Research. 2026;2(2):100168. - 175. Zhai S, Li G, Wu G, Nan K, Zhang H, Hou M. Cooperative 4D trajectory planning for multi aerial vehicles combining receding horizon optimization and differential evolution algorithm in dynamic battlefield environment. Applied Soft Computing. 2026;197:115169. - 176. Chen L. Beyond external constraints: The missing dimension of ai governance. 2026. https://doi.org/10.2139/ssrn.6449738 - 177. Yang Y, Zhu B, She X, Wang K, Liu A. A Family of Bipolar DC–DC Converters With Interpolar Voltage Self-Balancing Based on FB-BVMs for BLVDC Microgrid. IEEE Trans Ind Electron. 2025;72(9):9229–38. - 178. Yang Y, Zhu B, She X, Wang K, Liu A. A family of voltage balancers with fault-tolerance and interpolar voltage self-balancing ability for bipolar DC power systems. IEEE Trans Transp Electrific. 2025;11(4):9864–76. - 179. Xu N, Tan Q. Super-resolution hollow beams with long depth of focus formed by diffractive optical elements. Frontiers in Optics/ Laser Science, OSA Technical Digest, 2020. - 180. Yang W-W, Liu Z, Song L-D, Lin Y-W, Zhang J-F, Qu Z-G. Advancing low-Pt catalyst layer design from multi-scale to cross-scale synergy optimization for high-performance and durable proton exchange membrane fuel cell. Renewable and Sustainable Energy Reviews. 2026;230:116681. - 181. Su C, Pei M, Chen K, Jian X, Hu F. Machine learning paradigm for advanced battery electrolyte development. Carbon Energy. 2026;:e70244. - 182. Zhu G, Zhang S, Deng Z, Wang J, Li Y, Dong J, et al. Extended hybrid modulation for multistage constant-current wireless EV charging. IEEE Trans Power Electron. 2025;40(7):10095–110. - 183. Zhu G, Dong J, Grazian F, Bauer P. A Hybrid modulation scheme for efficiency optimization and ripple reduction in secondary-side controlled wireless power transfer systems. IEEE Trans Transp Electrific. 2025;11(2):6840–53. - 184. Huang J, Zong Z, Wang P, Zhang Y, Gao D, Wang Y, et al. Machine learning-driven simulation and optimization of phosphate adsorption on metal-organic frameworks. Separation and Purification Technology. 2026;394:137479. - 185. Xu N, Liu G, Kong Z, Tan Q. Creation of super-resolution hollow beams with long depth of focus using binary optics. Appl Phys Express. 2019;13(1):012003. - 186. Linsong J, Tong Z, Shaoyi S, Yongqian D, Ali Hamid MO, Yang Z, et al. Visualization on the turbulent structure and restructure characteristic in the wake of a packed bed reactor: PIV measurements and POD analysis. Renewable Energy. 2025;246:122895. - 187. Dong S, Xia Y, Kamruzzaman J. Quantum particle swarm optimization for task offloading in mobile edge computing. IEEE Trans Ind Inf. 2023;19(8):9113–22. - 188. Xu N, Fu Y, Pu D. Research and design of single lens high resolution imaging system. 红外与激光工程. 2017;46(11):1118001. - 189. Liu H, Yang T, Zhang Z, Tian H, Song Y, Sun Q, et al. Ultrasonic localization method based on Chan‐WLS algorithm for detecting power transformer partial discharge faults by fibre optic F‐P sensing array. High Voltage. 2024;9(6):1234–45. - 190. Tian X, Teng Y, Huang M, Zhang Q, Huang J, Chen Y, et al. MouseOmics: A multi-omics database for mouse biological study. Nucleic Acids Res. 2026;54(D1):D1197–207. pmid:41118512 - 191. Ni L, Wu S, Pu J, Xin S, Wang A, Chen X, et al. Highly Reliable RRAM-based physical unclonable function with auto-write technique. IEEE Trans VLSI Syst. 2026;:1–5. - 192. Chen ZH, Xu ZD, Entezami A, Sarmadi H, Gao W, Behkamal B. Dynamic monitoring of bridges subjected to freezing-induced variability by kernel-enhanced deep anomaly detection. Eng Struct. 2026;362:122971. - 193. Wang C, et al. 3-D-printed pentahedral polarization-division transmissive metadevice with versatile wavefronts. IEEE Transactions on Antennas and Propagation. 2026;74(5):4915–20. - 194. Zhu R, Zhou J, Chen S, Ding H. Pseudo-trapezoidal fast factorized backprojection algorithm for near-field sparse MIMO Array 3-D imaging. IEEE Trans Aerosp Electron Syst. 2025;:1–16. - 195. Du S, Zou Y, Wang Z, Li X, Li Y, Shang C, et al. Unsupervised hyperspectral image super-resolution via self-supervised modality decoupling. Int J Comput Vis. 2026;134(4). - 196. Tan J, Li Y, Ge L, Wang J. A 3-D printed lightweight miniaturized dual-band dual-polarized feed module for advanced millimeter-wave and microwave shared-aperture wireless backhaul system applications. IEEE Transactions on Antennas and Propagation. 2023;71(4):3050–60. - 197. Liu G, Xu N, Yang H, Tan Q, Jin G. Miniaturized structured illumination microscopy with diffractive optics. Photon Res. 2022;10(5):1317–24. - 198. Tan J, Li Y, Wang J. A 3-D-printed lightweight compact wideband dual-polarized feed module for sub-THz applications. IEEE Transactions on Antennas and Propagation. 2025;73(10):8242–7. - 199. Zhang F, Bahn G-S. Comprehensive effectiveness evaluation of constructing a multi-objective sponge campus. Pol J Environ Stud. 2024;34(1):415–30. - 200. Zhang F, Zhou G, Wen K-H, Jiang T, Bahn G-S. How do sense of place and perceived restorativeness affect psychological benefits from urban green spaces for older adults? A cross-sectional study. Land. 2025;14(11):2288. - 201. Dong S, Abbas K, Jain R. A survey on distributed denial of service (DDoS) Attacks in SDN and cloud computing environments. IEEE Access. 2019;7:80813–28. - 202. Zhang C, Xu N, Tan Q. Compact structured illumination microscopy with high spatial frequency diffractive lattice patterns. Biomed Opt Express. 2022;13(11):6113–23. pmid:36733745 - 203. Xia Y, Zheng D, Zhang Y, Deng W, Yang T. Balancing urban environmental and societal performance in high-density cities: Morphological trade-offs and optimization strategies in Shenzhen and Hong Kong. Sustainable Cities and Society. 2026;143:107383. - 204. Sha Y, Liu J, Yu J, Xu S, Yan W, Li Z, et al. Effect of graphene oxide on the ammonia removal and bacterial community in a simulated wastewater treatment process. J Environ Eng. 2020;146(9). - 205. He Z, Zhang N, Zhao L, Li Z, Cui W, Zhu Y, et al. Carbon nanotube incorporated quaternized lignin-based loose nanofiltration membrane toward dye/salt separation. Journal of Environmental Chemical Engineering. 2024;12(3):112834. - 206. Tian M, Wei J, Lv E, Li C, Liu G, Sun Y, et al. Drug evaluation platform based on non-destructive and real-time in situ organoid fate state monitoring by graphene field-effect transistor. Chemical Engineering Journal. 2024;498:155355. - 207. Zhao Y, Cao Z, Wu G, Lv M-Y, Lin M-Z, Feng Y, et al. Multifunctional WS2-Au Field-Effect Transistors with Asymmetrical Contact for High Self-Driven Photoresponsivity and Ultrasensitive NO2 Sensing. ACS Appl Mater Interfaces. 2025;17(49):67328–38. pmid:41311257 - 208. Tian M, Qiao M, Shen C, Meng F, Frank LA, Krasitskaya VV, et al. Highly-sensitive graphene field effect transistor biosensor using PNA and DNA probes for RNA detection. Applied Surface Science. 2020;527:146839. - 209. Tian M, Wang J, Li C, Wang Z, Liu G, Lv E, et al. Qualitative and quantitative detection of microcystin-LR based on SERS-FET dual-mode biosensor. Biosens Bioelectron. 2022;212:114434. pmid:35671700 - 210. Xu S, Wang T, Liu G, Cao Z, Frank LA, Jiang S, et al. Analysis of interactions between proteins and small-molecule drugs by a biosensor based on a graphene field-effect transistor. Sensors and Actuators B: Chemical. 2021;326:128991. - 211. Wang Z, Liu G, Li C, Qiao M, Tian M, Lin X, et al. W/WO3/TiO2 multilayer film with elevated electrochromic and capacitive properties. Materials. 2025;18(161). - 212. Tian M, Li Z, Song R, Li Y, Guo C, Sha Y, et al. Graphene biosensor as affinity biosensors for biorecognition between Guanine riboswitch and ligand. Applied Surface Science. 2020;503:144303. - 213. Liu G, Wang Z, Sun W, Lin X, Wang R, Li C, et al. Robust emission in near-infrared II of lanthanide nanoprobes conjugated with Au (LNPs-Au) for temperature sensing and controlled photothermal therapy. Chemical Engineering Journal. 2023;452:139504. - 214. Xu X, Xu S, Man B, Li C, Li Z, Yu J, et al. Defect Engineered Ca5Ga6O14: Ti4+, Sm3+ Multi Stimuli–Responsive Luminescent Nanophosphor for Macro Micro Anti Counterfeiting and Multilevel Encoding. Adv. Funct. Mater. 2025;e17527. - 215. Jiang S, Wang Y, Li C, Zhang X, Wang L, Lin C, et al. A Multi-functional Smart Window for Converting Sunlight into Absorbable Fluctuating Light to Enhance Plant Growth and Stress Tolerance. Advanced Functional Materials. 2025:e18909. - 216. Liu G, Wei J, Li X, Tian M, Wang Z, Shen C, et al. Near-infrared-responded high sensitivity nanoprobe for steady and visualized detection of albumin in hepatic organoids and mouse liver. Adv Sci. 2022;2022:2202505. - 217. Liu G, Wang Z, Sun W, Gao W, Zhang X, Lin H, et al. Emission enhancement of core-shell-shell lanthanide nanoparticles functionalized with Pt(IV) prodrugs for deep-tissue signal penetration and chemotherapy. Optical Materials. 2025;168:117401. - 218. Baqiah H, Zhang N, Kechik MMMA, Al-Hada NM, Tiong SK, Al-Zahrani AA, et al. Crystal growth, optical, photoluminescence and magnetic properties of sol-gel GdFeO3 thin film. Ceramics International. 2024;50:13892–13900. - 219. Lin X, Lv Y, Zhuang G, Zou J, Lv M, Xu S, et al. Multi;Mode Anti;Counterfeiting Using Pr3+, Ce3+ and Er3+ Codoped Mg3Y2Ge3O12 Phosphor with Spatial and Temporal Luminescence Properties, Laser. Photonics Reviews. 2026;20:e01047. - 220. Li Y, Liu W, Liu R, Gao J, Feng J, Xu S, et al. 3D hybrid arrayed Ag/MOF multi-plasmon resonant cavity system for high-performance SPR sensing. Optics and Laser Technology. 2023;167:109825. - 221. Zhang JY, Ding EJ, Li ZH, Xu SC, Wang XX, Li XY, et al. An improved tin oxide core mismatch optical fiber sensor and its preparation method. Optical Fiber Technology. 2019;48:253–7. - 222. Wang L, Li C, Cao C, Lei F, Zhao X, Li Z, et al. Multifunctional Polymeric Nanoneedles with “Full‐Spectrum Intrinsic Internal Standard” for Precise SERS Biosensing. Adv Funct Materials. 2024;35(10). - 223. Li C, Xu S, Yu J, Li Z, Li W, Wang J, et al. Local hot charge density regulation: Vibration-free pyroelectric nanogenerator for effectively enhancing catalysis and in-situ surface enhanced Raman scattering monitoring. Nano Energy. 2021;81:105585. - 224. Li C, Man B, Zhang C, Yu J, Liu G, Tian M, et al. Strong plasmon resonance coupling in micro-extraction SERS membrane for in situ detection of molecular aqueous solutions. Sensors and Actuators B: Chemical. 2024;398:134767. - 225. Shan B, Yuan N, Li F, Zhao X, Ji C, Li Z, et al. Plasmonic enhanced piezoelectric photocatalytic performance with PVDF@BT/MoS2/Au by strong piezoelectric functional particle doping. Journal of Alloys and Compounds. 2022;925:166695. - 226. Man B, Wang G, Li Z, Xu S, Li C, Yu J, et al. MoS2-spaced bimetal composite structure as SERS-SPR sensor for glucose detection. Journal of Alloys and Compounds. 2022;902:163789. - 227. Xu J, Lv E, Zhao X, Yu J, Xu S, Li J, et al. Enhanced SERS and catalytic performance via piezoelectric and plasmonic coupling effects for organic pollutant molecule degradation. Journal of Alloys and Compounds. 2022;918:165813. - 228. Pan J, Li Y, Guo G, Zhao X, Yu J, Li Z, et al. Synergizing piezoelectric and plasmonic modulation of PVDF/MoS2 cavity/Au for enhanced photocatalysis. Applied Surface Science. 2022;577:151811. - 229. Li C, Xu S, Yu J, Li Z, Li W, Wang J, et al. Local hot charge density regulation: Vibration-free pyroelectric nanogenerator for effectively enhancing catalysis and in-situ surface enhanced Raman scattering monitoring. Nano Energy. 2021;81:105585. - 230. Xu S, Zhan J, Man B, Jiang S, Yue W, Gao S, et al. Real-time reliable determination of binding kinetics of DNA hybridization using a multi-channel graphene biosensor. Nat Commun. 2017;8:14902. pmid:28322227 - 231. Zhao Y, Cao Z, Wu G, Lv M-Y, Lin MZ, Feng Y, et al. Multifunctional WS2-Au Field-Effect Transistors with Asymmetrical Contact for High Self-Driven Photoresponsivity and Ultrasensitive NO2 Sensing. ACS Applied Materials Interfaces. 2025;17(49):67328–38. - 232. Li E, Wu J, Zhang D, Wang P, Zhu L, Li C, et al. Effect of autoinducer-2 on corrosion of Q235 carbon steel caused by sulfate reducing bacteria. Corrosion Science. 2022;200:110220. - 233. Wang F, Yang C-L, Zhao Z-C, Liang G-Y. Direct Z-scheme photocatalytic water splitting in SnC-based chalcogenide heterostructures: mechanistic insights and hydrogen evolution performance. Applied Surface Science. 2026;721:165405. - 234. Wang T, Qiao M, Liu Y, Tian M, Wang X, Li X, et al. Single-mode waveguides with well and barrier type on YSGG crystals formed via hydrogen ion irradiation. Applied Surface Science. 2025;681:161476. - 235. Qiao M, Wang T, Liu Y, Li Q, Liu G, Jia R, et al. Effects of swift Kr ion irradiation on near-surface structural and optical properties of neodymium-doped yttrium lithium fluoride crystals. Applied Surface Science. 2025;681:161562. - 236. Tian M, Qiao M, Shen C, Meng F, Frank LA, Krasitskaya VV, et al. Highly-sensitive graphene field effect transistor biosensor using PNA and DNA probes for RNA detection. Applied Surface Science. 2020;527:146839. - 237. Tian M, Li Z, Song R, Li Y, Guo C, Sha Y, et al. Graphene biosensor as affinity biosensors for biorecognition between Guanine riboswitch and ligand. Applied Surface Science. 2020;503:144303. - 238. Yang J, Dong X, Wang J, Ching YC, Liu J, Chunhui li, et al. Synthesis and properties of bioplastics from corn starch and citric acid-epoxidized soybean oil oligomers. Journal of Materials Research and Technology. 2022;20:373–80. - 239. Al-Hada NM, Kasmani RMd, Kasim H, Al-Ghaili AM, Saleh MA, Baqiah H, et al. Up-scalable synthesis of size-controlled NiSe nanoparticles using single step technique. Journal of Materials Research and Technology. 2022;18:4918–29. - 240. Zhao Z, Yang C, Cao Z, Li B, Wei Y, Liu G, et al. Rational design of MoS2/MoSe2 lateral heterostructure with optimal component ratio used for high-efficient photocatalytic overall water splitting. Surfaces and Interfaces. 2024;56:105513. https://doi.org/10.1016/j.surfin.2024.105513 - 241. Al-Hada NM, Al-Ghaili AM, Kasim H, Saleh MA, Baqiah H, Liu J, et al. Nanofabrication of (Cr2O3)x (NiO)1-x and the impact of precursor concentrations on nanoparticles conduct. Journal of Materials Research and Technology. 2021;11:252–63. https://doi.org/10.1016/j.jmrt.2021.01.007 - 242. Qiao M, Wang T, Liu Y, Liu G, Jia R, Cui W, et al. Optical properties in well and barrier single-mode Nd:YLiF4 waveguides formed under 300 keV H-ion irradiation. Surface and Coatings Technology. 2025;497:131791. https://doi.org/10.1016/j.surfcoat.2025.131791 - 243. Wang T, Qiao M, Zhang H, Xu L, Tian Y, Chen M. Laser ablation-induced convenient fabrication of surfactant-free platinum nanospheres with clean surface structures for enhanced electrocatalytic methanol oxidation. Surface and Coatings Technology. 2024;496:131620. https://doi.org/10.1016/j.surfcoat.2024.131620 - 244. Al-Hada NM, Md. Kasmani R, Kasim H, Al-Ghaili AM, Saleh MA, Banoqitah EM, et al. The Effect of Precursor Concentration on the Particle Size, Crystal Size, and Optical Energy Gap of CexSn1−xO2 Nanofabrication. Nanomaterials. 2021;11(8):2143. https://doi.org/10.3390/nano11082143 - 245. Baqiah H, Zhang N, Awang Kechik MM, Mohammed Al-Hada N, Kiong Tiong S, Al-Zahrani AA, et al. Crystal growth, optical, photoluminescence and magnetic properties of sol-gel GdFeO3 thin film. Ceramics International. 2024;50(8):13892–900. https://doi.org/10.1016/j.ceramint.2024.01.305 - 246. Baqiah H, Awang Kechik MM, Al-Gaashani R, Al-Zahrani AA, Al-Hada NM, Zhang N, et al. Effects of annealing temperature on the phase formation, optical, photoluminescence and magnetic properties of sol-gel YFeO3 films. Ceramics International. 2022;49(1):600–6. https://doi.org/10.1016/j.ceramint.2022.09.028 - 247. Tang Q, Zhu X, Shi L, Liu W, Li B, Jin Y. Bimetal-Driven Nucleotide Nanosheets for Spontaneously Enhanced Antibacterial and Protective Coatings. ACS Applied Nano Materials. 2024;7(23):26873–83. https://doi.org/10.1021/acsanm.4c04873 - 248. Xu S, Jiang S, Zhang C, Yue W, Zou Y, Wang G, et al. Ultrasensitive label-free detection of DNA hybridization by sapphire-based graphene field-effect transistor biosensor. Applied Surface Science. 2017;427:1114–9. https://doi.org/10.1016/j.apsusc.2017.09.113 - 249. Liang G, Zhong H, Zhang S, Xu M, Kuang S, Ren J, et al. Molecular dynamics study of damage nearby silicon surface bombarded by energetic carbon ions. Surface and Coatings Technology. 2020;385:125350. https://doi.org/10.1016/j.surfcoat.2020.125350 - 250. Li C, Yu J, Xu S, Jiang S, Xiu X, Chen C, et al. Constructing 3D and Flexible Plasmonic Structure for High‐Performance SERS Application. Advanced Materials Technologies. 2018;3(11):null. https://doi.org/10.1002/admt.201800174 - 251. Al-Hada NM, Al-Ghaili AM, Baqer AA, Saleh MA, Kasim H, Saion E, et al. Radiation-induced synthesis, electrical and optical characterization of conducting polyaniline of PANI/ PVA composites. Materials Science and Engineering: B. 2020;261:114758. https://doi.org/10.1016/j.mseb.2020.114758 - 252. Li C, Yang C, Xu S, Zhang C, Li Z, Liu X, et al. Ag2O@Ag core-shell structure on PMMA as low-cost and ultra-sensitive flexible surface-enhanced Raman scattering substrate. Journal of Alloys and Compounds. 2016;695:1677–84. https://doi.org/10.1016/j.jallcom.2016.10.317 - 253. Wang G, Feng L, Altanji M, Sharma K, Sooppy Nisar K, khorasani S. Proposing novel “L” shaped fin to boost the melting performance of a vertical PCM enclosure. Case Studies in Thermal Engineering. 2021;28:101465. - 254. Kong Z, Xu N, Xiao H, Tan Q. Effective Fresnel diffraction field extension of diffractive optical elements with plane wave incidence. Appl Opt. 2020;59(11):3427–31. pmid:32400457 - 255. Li Q, Zhang N, Li Z, Gao Z, Yan T, Qian Z, et al. Brush assisted layer-by-layer assembled lignin/polyelectrolyte membrane. Materials Letters. 2021;292:129650. https://doi.org/10.1016/j.matlet.2021.129650 - 256. Wang Z, Liu G, Li C, Qiao M, Tian M, Lin X, et al. W/WO3/TiO2 Multilayer Film with Elevated Electrochromic and Capacitive Properties. Materials. 2025;18(1):161. https://doi.org/10.3390/ma18010161 - 257. Liang G, Xu B, Wei X. Collision Cascade in a Silicon-Based Device under Energetic Ar Ions Irradiation. Coatings. 2023;13(11):1828. https://doi.org/10.3390/coatings13111828 - 258. Liang G, Zhong H, Wang Y, Zhang S, Xu M, Kuang S, et al. Molecular Dynamics Simulations of Vacancy Generation and Migration near a Monocrystalline Silicon Surface during Energetic Cluster Ion Implantation. Coatings. 2020;10(2):146. https://doi.org/10.3390/coatings10020146 - 259. Qiao M, Wang T, Liu Y, Cui W, Wang X, Wang Z, et al. Lattice Damage, Optical and Electrical Properties Induced by H and C Ions Implantation in Nd:YLF Crystals. Crystals. 2024;14(2):146. https://doi.org/10.3390/cryst14020146 - 260. Yang J, Xu S, Chee CY, Ching KY, Chuah CH. Effects of empty fruit bunch on the structures and properties of starch-based bioplastics. Journal of Reinforced Plastics and Composites. 2023;44(7-8):386–97. https://doi.org/10.1177/07316844231221656 - 261. Yang J, Ching YC, Julai J S, Chuah CH, Nguyen DH, Lin P-C. Comparative study on the properties of starch-based bioplastics incorporated with palm oil and epoxidized palm oil. Polymers and Polymer Composites. 2022;30:null. https://doi.org/10.1177/09673911221087595 - 262. Wei Y, Lyu S, Yang J, Li B, Yue S, Zhao Z, et al. In situ fabrication strategy to synthesize CeO2/Cs4PbBr6 nanocomposites with reversible photoluminescence. Optical Materials Express. 2025;15(8):1891. https://doi.org/10.1364/OME.569833 - 263. Li S, Wang L, Dai J, Zhang N, Zhao L, Zheng S, et al. Photoresponsive leaf-like structured two-dimensional metal-organic framework/nanocellulose crystal composites for efficient and rapid adsorption of pollutants from wastewater. Chemical Engineering Journal. 2025;523:168706. https://doi.org/10.1016/j.cej.2025.168706 - 264. Liu G, Wang Z, Sun W, Lin X, Wang R, Li C, et al. Robust emission in near-infrared II of lanthanide nanoprobes conjugated with Au (LNPs-Au) for temperature sensing and controlled photothermal therapy. Chemical Engineering Journal. 2022;452:139504. https://doi.org/10.1016/j.cej.2022.139504 - 265. Guo X-Z, Lin B, Xiong G-Z, Krishna R, Zhang Z-R, Liu Q-Z, et al. Construction of negative electrostatic sugared gourd pore within nickel-based metal-organic framework for one-step purification acetylene from ethylene and carbon dioxide mixture. Chemical Engineering Journal. 2024;498:154734. https://doi.org/10.1016/j.cej.2024.154734 - 266. Wang F, Yu X, Cao Z, Liu Y, Jiang X, Gu X. Synergic enhancement of hydrogel upon multi-level hydrogen bonds via macromolecular design for dual-mode electronic skin. Chemical Engineering Journal. 2024;489:151249. https://doi.org/10.1016/j.cej.2024.151249 - 267. Wang Y, Li Q, Tang G, Zhang N. Recent progress on carbon based desalination membranes and carbon nanomaterial incorporated non-polyamide desalination membranes. Journal of Environmental Chemical Engineering. 2021;9(4):105762. https://doi.org/10.1016/j.jece.2021.105762 - 268. Zhang N, Fu F, Bo W, Baqiah H, Zhao L, Lu W, et al. Rigid polyelectrolyte multilayer membrane with ultrahigh permeance and excellent dye/salt separation performance. Journal of Environmental Chemical Engineering. 2025;13(3):116164. https://doi.org/10.1016/j.jece.2025.116164 - 269. Xiao L, Liu J, Senthil Kumar P, Zhou M, Yu J, Lichtfouse E. Enhanced methane production by granular activated carbon: A review. Fuel. 2022;320:123903. https://doi.org/10.1016/j.fuel.2022.123903 - 270. He Z, Zhang N, Zhao L, Li Z, Cui W, Zhu Y, et al. Carbon nanotube incorporated quaternized lignin-based loose nanofiltration membrane toward dye/salt separation. Journal of Environmental Chemical Engineering. 2024;12(3):112834. https://doi.org/10.1016/j.jece.2024.112834 - 271. Al-Ghaili AM, Kasim H, Al-Hada NM, Hassan ZB, Othman M, Tharik JH, et al. A Review of Metaverse’s Definitions, Architecture, Applications, Challenges, Issues, Solutions, and Future Trends. IEEE Access. 2022;10:125835–66. https://doi.org/10.1109/ACCESS.2022.3225638 - 272. Qiao M, Wang TJ, Zhang J, Liu Y, Liu P. Raman spectroscopic visualization in Nd: YLF crystal induced by Ga ion irradiation. Optics & Laser Technology. 2019;122:105856. https://doi.org/10.1016/j.optlastec.2019.105856 - 273. Al-Ghaili AM, Kasim H, Al-Hada NM, Jorgensen BN, Othman M, Wang J. Energy Management Systems and Strategies in Buildings Sector: A Scoping Review. IEEE Access. 2021;9:63790–813. https://doi.org/10.1109/ACCESS.2021.3075485 - 274. Al-Hada NM, Al-Ghaili AM, Kasim H, Saleh MA, Saion E, Liu J, et al. Synthesis and Characterization of Conducting Polyaniline Based on ANI-PVA-MgCl2Composites Using Gamma Radiation Technique. IEEE Access. 2020;8:139479–88. https://doi.org/10.1109/ACCESS.2020.3012730 - 275. Al-Hada NM, Al-Ghaili AM, Kasim H, Saleh MA, Flaifel MH, Kamari HM, et al. The Effect of PVP Concentration on Particle Size, Morphological and Optical Properties of Cassiterite Nanoparticles. IEEE Access. 2020;8:93444–54. https://doi.org/10.1109/ACCESS.2020.2993689 - 276. Chen Y-X, Zhu H-S, Gao F, Xiong H-R, Yang H, Xu Z-X, et al. Green wood bio-adhesives from cellulose-derived bamboo powder hydrochars. Chemical Engineering Journal. 2024;498:155667. https://doi.org/10.1016/j.cej.2024.155667 - 277. Zhang H, Chen Y, Liu K, Dehan S. RETRACTED: A novel power system scheduling based on hydrogen-based micro energy hub. Energy. 2022;251:123623. https://doi.org/10.1016/j.energy.2022.123623 - 278. Zhu Y, Yang J, Li J, Hu L, Zhou Q. Interaction properties of double-hump solitons in the dispersion decreasing fiber. Nonlinear Dynamics. 2022;109(2):1047–52. https://doi.org/10.1007/s11071-022-07491-7 - 279. Jiang J, Yu L, Zhang X, Ding X, Wu C. EV-Based reconfigurable smart grid management using support vector regression learning technique machine learning. Sustainable Cities and Society. 2021;76:103477. https://doi.org/10.1016/j.scs.2021.103477 - 280. Zhang W, Li G. An Efficient and Secure Data Transmission Mechanism for Internet of Vehicles Considering Privacy Protection in Fog Computing Environment. IEEE Access. 2020;8:64461–74. https://doi.org/10.1109/ACCESS.2020.2983994 - 281. Wu M, Zheng K, Chen J, Zhang J, Li M, Wu S. Assessing elderly walkability to urban parks using mobility analysis and multi-source data: a case study of central Fuzhou, China. Scientific Reports. 2026;16(1):null. https://doi.org/10.1038/s41598-026-41060-x - 282. Wang E, Cheng P, Zhao W, Li J, Han Q, Zhou X. Photonic crystal fibers with high birefringence and multiple zero dispersion wavelengths. Optical Fiber Technology. 2020;58:102309. https://doi.org/10.1016/j.yofte.2020.102309 - 283. Wei J, Chen Z, Zhang Y, Zhang W, Li J, Silva Lora EE, et al. An adjustable heat-to-power ratio combined heat and power system integrating biomass gasification, solid oxide fuel cell, and gas turbine: Energy, exergy, economic, and exergoeconomic (4E) analyses. International Journal of Hydrogen Energy. 2026;244:155706. https://doi.org/10.1016/j.ijhydene.2026.155706 - 284. Hao Z, Zhang Y, Zhu Y, Sun B, Jiao H, Hu Y, et al. Compound metalens-based miniature two-photon microscope for large-FOV imaging in freely behaving animals. PhotoniX. 2025;6(1):null. https://doi.org/10.1186/s43074-025-00218-y - 285. Wang Y, Liang X, Xiong Y, Tian J, Yan Q, Cheng Y, et al. Real-world operating characteristics of hydraulic excavators: A large-sample empirical study and implications for energy efficiency optimization. Energy. 2026;352:140925. https://doi.org/10.1016/j.energy.2026.140925 - 286. Wang Y, Liang X, Hou J, Tian J, Cheng Y, Wan Y. Decarbonizing construction machinery: Data-driven lifecycle assessment of a hydraulic excavator using electrified and alternative-fuel hybrid power systems. Applied Energy. 2026;411:127641. https://doi.org/10.1016/j.apenergy.2026.127641 - 287. Li B-R, Liu C-L, Liu P-J, Zhou T-L, Xu W-J, Wang L-Q, et al. Predictive analysis of the overall cooling effectiveness for leading-edge showerhead cooling based on a thermal resistance network model with physical corrections. Aerospace Science and Technology. 2026;176:112492. https://doi.org/10.1016/j.ast.2026.112492 - 288. Ye L, Li Z-H, Yan H-N, Liu C, Cho HH, Guo T. Predicting film-cooling effectiveness of compound-angle holes using a POD-based hybrid deep learning model. Aerospace Science and Technology. 2026;176:112590. https://doi.org/10.1016/j.ast.2026.112590 - 289. Liu D, Lian J, Liu F, Ma B, Liu D, Shi J, et al. A refined numerical model for assessing low-pressure effects on ski-jump atomization at high-altitude dams. Journal of Mountain Science. 2026;1:null. https://doi.org/10.1007/s11629-025-9995-3 - 290. Yang T, Qian Z, Hang N, Liu M. S-PINN: Stabilized physics-informed neural networks for alleviating barriers between multi-level co-optimization. Computer Methods in Applied Mechanics and Engineering. 2025;447:118348. https://doi.org/10.1016/j.cma.2025.118348 - 291. Yang H, Liu J, Mu W. A novel crack depth quantification index based on acoustic emission modeling of thin plate cracks. Measurement. 2026;270:120888. https://doi.org/10.1016/j.measurement.2026.120888 - 292. Weng Y, Yang K, Liu Z, He W, Tang X. LGVLM-mIoT: A Lightweight Generative Visual-Language Model for Multilingual IoT Applications. IEEE Internet of Things Journal. 2025;12(10):13311–26. https://doi.org/10.1109/JIOT.2025.3532494 - 293. Liu X, Wang C, Chen C, Pan Z, Gao C, Lai W, et al. Recent advances in hierarchical porous materials for CO2 capture and utilization. Coordination Chemistry Reviews. 2025;544:216927. https://doi.org/10.1016/j.ccr.2025.216927 - 294. Li Y, Jin Z, Ahmed SU, Das J, Bleher R, Chang D, et al. Biomolecular Condensates as Protein Degradation Tools for Intracellular Targets. Nature Communications. 2026;null. https://doi.org/10.1038/s41467-026-72967-8 - 295. Li Y, Teng C, Azevedo HS, Yin L, He W. Cocrystallization-like strategy for the codelivery of hydrophobic and hydrophilic drugs in a single carrier material formulation. Chinese Chemical Letters. 2021;32(10):3071–5. https://doi.org/10.1016/j.cclet.2021.03.085 - 296. Xu S, Tian M, Li C, Liu G, Wang J, Yan T, et al. Using a crumpled graphene field-effect transistor for ultrasensitive SARS-CoV-2 detection via its papain-like protease. Chemical Engineering Journal. 2025;505:159386. - 297. Lu B, Jiang H, Hu C, Abdurahman A, Liu M. H∞ output synchronization of directed coupled reaction-diffusion neural networks via event-triggered quantized control. Journal of the Franklin Institute. 2021;358(8):4458–82. https://doi.org/10.1016/j.jfranklin.2021.03.007 - 298. Wang P, Ma J, Wang L, Li L, Yan X, Zhang R, et al. Di-n-butyl phthalate stress induces changes in the core bacterial community associated with nitrogen conversion during agricultural waste composting. Journal of Hazardous Materials. 2022;446:130695. https://doi.org/10.1016/j.jhazmat.2022.130695 - 299. Yang J, Zhu Y, Qin W, Wang S, Li J. 3D bright-bright Peregrine triple-one structures in a nonautonomous partially nonlocal vector nonlinear Schrödinger model under a harmonic potential. Nonlinear Dynamics. 2023;111(14):13287–96. https://doi.org/10.1007/s11071-023-08526-3 - 300. Xu H, Li H, Bai B, Zhu M, Zhang B. Tanner $(J,L)$ Quasi-Cyclic LDPC Codes: Girth Analysis and Derived Codes. IEEE Access. 2018;7:944–57. https://doi.org/10.1109/ACCESS.2018.2886045 - 301. Zhang C, Garcea G. Simulation Analysis of Bionic Robot Fish Based on MFC Materials. Mathematical Problems in Engineering. 2019;2019(1):null. https://doi.org/10.1155/2019/2720873 - 302. Tian Z, Gao S, Jing S, Li J. Reliability and fatigue life analysis of key parts of shearer. Engineering Failure Analysis. 2022;138:106357. https://doi.org/10.1016/j.engfailanal.2022.106357 - 303. Chen G, Chen G, Fa M, Yang Y, Wang Y, Li F, et al. Potential of a 1-Amino-2-Propanol/Sulfolane Biphasic Solution for CO2 Capture: Performance and Mechanism Study. Energy & Fuels. 2024;38(18):17726–40. https://doi.org/10.1021/acs.energyfuels.4c02734 - 304. Tian Z, Jing S, Zhao L, Liu W, Gao S. Numerical simulation on coal loading process of shearer drum based on discrete element method. Energy Exploration & Exploitation. 2021;39(6):1919–38. https://doi.org/10.1177/01445987211013536 - 305. Xue Y, Duan S, Chen G, Sun J, Abbas M, Chen J. Effect of annealing atmosphere on Fischer-Tropsch synthesis performance of Fe/Fe foam structured catalyst. Fuel. 2019;262:116570. https://doi.org/10.1016/j.fuel.2019.116570 - 306. Kang H, Li Z-M, Liu T, Mei Q, Zhang X. Connection stiffness modeling of rotating dovetailed blade with macro-micro interface topography. European Journal of Mechanics - A/Solids. 2023;101:105064. https://doi.org/10.1016/j.euromechsol.2023.105064 - 307. Tian C, Chang K-C, Chen J. Application of hyperbolic partial differential equations in global optimal scheduling of UAV. Alexandria Engineering Journal. 2020;59(4):2283–9. https://doi.org/10.1016/j.aej.2020.02.013 - 308. Zhou X, Wang E, Han Q, Yuan H, Li J. A large birefringence and high nonlinearity liquid crystal photonic crystal fiber with low confinement loss. Optical Fiber Technology. 2021;65:102610. https://doi.org/10.1016/j.yofte.2021.102610 - 309. Liu W, Wang Y. H∞ Control of Markovian Jump Linear Singularly Perturbed Systems. Circuits, Systems, and Signal Processing. 2021;40(9):4230–45. https://doi.org/10.1007/s00034-021-01676-y - 310. Kang H, Li Z-M, Liu T, Yuan W, Jing J. Free vibration analysis of pre-twisted rotating dovetailed blade under the flexible connection with macro-micro rough contact topography. Thin-Walled Structures. 2024;201:112039. https://doi.org/10.1016/j.tws.2024.112039 - 311. Zhang X, Song C, Dai W, Zhang Z, Gao K, Gao F. Causal graph spatial-temporal autoencoder for reliable and interpretable process monitoring. IEEE Trans Neural Netw Learn Syst. 2026;PP:10.1109/TNNLS.2026.3656591. pmid:41637705 - 312. Zhong H-J, Zhen Y, Chen S, Shi W, Liang X, Yang G-J. Advances in CTC and ctDNA detection techniques: Opportunities for improving breast cancer care. Breast Cancer Res. 2025;27(1):97. pmid:40457318