Xiaoli Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaoli Zhang has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
Fangzhen Wang
Key Laboratory of Road Construction Technology and Equipment, Ministry of Education, Chang’an University, Xi’an, China
7 shared publications- Ruqiang Yan
School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, China
7 shared publications Wang Liang
Key Laboratory of Road Construction Technology and Equipment, Ministry of Education, Chang’an University, Xi’an, China
7 shared publications- Weihua Li
South China University of Technology
7 shared publications Xin Luo
Key Laboratory of Road Construction Technology and Equipment, Ministry of Education, Chang’an University, Xi’an, China
7 shared publicationsShuangxuan Liang
Chang’an University
4 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (20) , 30870-30879
A Two-Stage Adaptive Signal Decomposition and Noise Deconvolution Framework for Compound Fault Diagnosis of Rolling Bearings
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (20) , 30870-30879
A Two-Stage Adaptive Signal Decomposition and Noise Deconvolution Framework for Compound Fault Diagnosis of Rolling Bearings
- 20 August 2026
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 20 (11) , 581
Tachometer-less fault diagnosis of rolling bearings via optimized IFCFR estimation and Vold-Kalman filter enhanced demodulation
- 20 August 2026
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 20 (11) , 581
Tachometer-less fault diagnosis of rolling bearings via optimized IFCFR estimation and Vold-Kalman filter enhanced demodulation
- 17 June 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (25) , 256107
TL-SBRN: a Siamese BiGRU gated residual shrinkage transfer network for robust cross-domain rolling bearing fault diagnosis
Under noisy cross-domain conditions, limited temporal modeling and sensitivity to interference can reduce the reliability of learned feature representations and degrade diagnostic performance in bearing fault diagnosis, especially when only a small amount of labelled target-domain data is available. To address this issue, a Siamese bidirectional GRU (BiGRU) Gated Residual Shrinkage Transfer framework (TL-SBRN) is developed for robust cross-domain bearing fault diagnosis. TL-SBRN integrates temporal modeling and feature denoising within a Siamese learning structure, allowing these components to complement each other and improve feature robustness under noisy interference. Specifically, a shared BiGRU backbone is employed to capture forward and backward temporal dependencies from vibration sequences, while residual shrinkage blocks are embedded within the Siamese branches to suppress redundant noise-sensitive components before feature comparison. Source-domain pretraining followed by target-domain fine-tuning is further adopted to improve adaptability under limited labelled target-domain conditions. Experiments on laboratory-collected bearing data and electric locomotive bearing data demonstrate that TL-SBRN achieves robust and stable diagnostic performance under noisy cross-domain conditions. Supplementary few-shot evaluations further examine its applicability in severely data-constrained scenarios.
- 17 June 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (25) , 256107
TL-SBRN: a Siamese BiGRU gated residual shrinkage transfer network for robust cross-domain rolling bearing fault diagnosis
Under noisy cross-domain conditions, limited temporal modeling and sensitivity to interference can reduce the reliability of learned feature representations and degrade diagnostic performance in bearing fault diagnosis, especially when only a small amount of labelled target-domain data is available. To address this issue, a Siamese bidirectional GRU (BiGRU) Gated Residual Shrinkage Transfer framework (TL-SBRN) is developed for robust cross-domain bearing fault diagnosis. TL-SBRN integrates temporal modeling and feature denoising within a Siamese learning structure, allowing these components to complement each other and improve feature robustness under noisy interference. Specifically, a shared BiGRU backbone is employed to capture forward and backward temporal dependencies from vibration sequences, while residual shrinkage blocks are embedded within the Siamese branches to suppress redundant noise-sensitive components before feature comparison. Source-domain pretraining followed by target-domain fine-tuning is further adopted to improve adaptability under limited labelled target-domain conditions. Experiments on laboratory-collected bearing data and electric locomotive bearing data demonstrate that TL-SBRN achieves robust and stable diagnostic performance under noisy cross-domain conditions. Supplementary few-shot evaluations further examine its applicability in severely data-constrained scenarios.
- 19 February 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
- Vol. 240 (9) , 3003-3021
A feature extraction interpretability research of one-dimensional convolutional neural networks in mechanical fault diagnosis
To address the “black-box” nature of one-dimensional convolutional neural networks (1D-CNNs) in mechanical fault diagnosis from a signal-processing perspective, a correspondence between the network and classical spectral analysis has been established. First, visualization of the convolutional layer weights before and after training revealed the evolution of their frequency responses, demonstrating that each convolutional kernel can be interpreted as exhibiting finite-impulse-response (FIR)-like temporal filtering behavior under fixed weights. Next, the nonlinear operation of the max-pooling layer was analyzed and found to satisfy the discriminative requirements of a binary classification task, allowing the activation function to be omitted after convolution. The influence of network depth on frequency resolution was then investigated, showing that layer-by-layer stacking of convolution and pooling effectively focuses on signal components near theoretical fault-feature frequencies-a mechanism highly analogous to the Fourier transform. Finally, by adjusting the number of layers such that the spectral decomposition range covers one to three times the fault-feature frequency, both feature-extraction precision and classification performance were significantly improved. Validation on the benchmark of rolling-bearing dataset and demonstrated that the proposed method not only maintains high accuracy but also markedly enhances model interpretability, offering a new approach for studying the “black-box” mechanism of 1D-CNNs and designing explainable intelligent diagnostic models.
- 19 February 2026
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
- Vol. 240 (9) , 3003-3021
A feature extraction interpretability research of one-dimensional convolutional neural networks in mechanical fault diagnosis
To address the “black-box” nature of one-dimensional convolutional neural networks (1D-CNNs) in mechanical fault diagnosis from a signal-processing perspective, a correspondence between the network and classical spectral analysis has been established. First, visualization of the convolutional layer weights before and after training revealed the evolution of their frequency responses, demonstrating that each convolutional kernel can be interpreted as exhibiting finite-impulse-response (FIR)-like temporal filtering behavior under fixed weights. Next, the nonlinear operation of the max-pooling layer was analyzed and found to satisfy the discriminative requirements of a binary classification task, allowing the activation function to be omitted after convolution. The influence of network depth on frequency resolution was then investigated, showing that layer-by-layer stacking of convolution and pooling effectively focuses on signal components near theoretical fault-feature frequencies-a mechanism highly analogous to the Fourier transform. Finally, by adjusting the number of layers such that the spectral decomposition range covers one to three times the fault-feature frequency, both feature-extraction precision and classification performance were significantly improved. Validation on the benchmark of rolling-bearing dataset and demonstrated that the proposed method not only maintains high accuracy but also markedly enhances model interpretability, offering a new approach for studying the “black-box” mechanism of 1D-CNNs and designing explainable intelligent diagnostic models.
- 9 February 2026
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 40 (2) , 857-869
PMPEIgram: An index-fused autogram approach for bearing diagnosis in high-noise and weak fault scenarios
- 9 February 2026
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 40 (2) , 857-869
PMPEIgram: An index-fused autogram approach for bearing diagnosis in high-noise and weak fault scenarios
- 23 January 2026
- Published by SAGE Publications in Journal of Vibration and Control
Bearing fault diagnosis based on parallel multi-channel deep CNN and optimization with local sparse structure
To solve the problem that signal processing-based bearing fault diagnosis methods require rich professional knowledge and experience and cannot cope with the large amount of data, an end-to-end one-dimensional parallel multi-channel deep convolutional neural network (PMDCNN) has been proposed. The experimental results show that the network model can effectively mine the different signal characteristics of different channels, which can realize the bearing fault diagnosis with high accuracy. The performance of the model is improved by increasing the depth of the network, using batch normalization (BN), Dropout technique, and choosing the right optimizer and learning rate. To reduce the number of model parameters, a local sparse structure is employed. Firstly, the larger convolutional kernels are replaced by smaller sized ones, thus greatly reducing the redundant parameters of that convolutional layer. Secondly, the fully connected layer is substituted by a global average pooling layer to further reduce the number of parameters. The final result is that the number of parameters is only 1/66th of the previous model with similar accuracy, and the training time is reduced, which shows the optimization method of local sparse structure achieves good results. The average fault diagnosis accuracy of 99.90 ± 0.03% in Case Western Reserve University (CWRU), 99.80 ± 0.05% in comprehensive experimental platform, and 99.65 ± 0.10% in University of Ottawa Rolling-element Dataset-Vibration and Acoustic Faults under Constant Load and Speed conditions (UORED-VAFCLS) also indicates that the optimized network model is good at extracting fault features from the original fault data, reflecting the superiority of the proposed method.
- 23 January 2026
- Published by SAGE Publications in Journal of Vibration and Control
Bearing fault diagnosis based on parallel multi-channel deep CNN and optimization with local sparse structure
To solve the problem that signal processing-based bearing fault diagnosis methods require rich professional knowledge and experience and cannot cope with the large amount of data, an end-to-end one-dimensional parallel multi-channel deep convolutional neural network (PMDCNN) has been proposed. The experimental results show that the network model can effectively mine the different signal characteristics of different channels, which can realize the bearing fault diagnosis with high accuracy. The performance of the model is improved by increasing the depth of the network, using batch normalization (BN), Dropout technique, and choosing the right optimizer and learning rate. To reduce the number of model parameters, a local sparse structure is employed. Firstly, the larger convolutional kernels are replaced by smaller sized ones, thus greatly reducing the redundant parameters of that convolutional layer. Secondly, the fully connected layer is substituted by a global average pooling layer to further reduce the number of parameters. The final result is that the number of parameters is only 1/66th of the previous model with similar accuracy, and the training time is reduced, which shows the optimization method of local sparse structure achieves good results. The average fault diagnosis accuracy of 99.90 ± 0.03% in Case Western Reserve University (CWRU), 99.80 ± 0.05% in comprehensive experimental platform, and 99.65 ± 0.10% in University of Ottawa Rolling-element Dataset-Vibration and Acoustic Faults under Constant Load and Speed conditions (UORED-VAFCLS) also indicates that the optimized network model is good at extracting fault features from the original fault data, reflecting the superiority of the proposed method.
- 26 November 2025
- Published by SAGE Publications in Journal of Vibration and Control
A dual-channel multi-scale residual network with dilated convolution optimization for rolling bearing fault diagnosis
Convolutional neural network (CNN) as a core component of deep learning is utilized to effectively extract potential features from input data through multiple layers of nonlinear units and have thus been widely applied in bearing fault diagnosis. However, the number of model parameters is significantly increased as the depth of the network increases, which potentially leads to overfitting during training and results in negative impacts on the model’s performance. Furthermore, introducing spatial invariance in convolution and pooling operations may reduce the model’s sensitivity to small changes in input data, impairing its ability to capture detailed information. To address these issues, a dual-channel multi-scale residual network with dilated convolution optimization for rolling bearing fault diagnosis is proposed by fusing the Inception network, Residual Neural Network (ResNet), and Squeeze-and-Excitation Network (SENet) attention mechanism to improve CNN. The method integrates the optimized multi-scale feature extraction module in the Inception network and ResNet, which enhances the feature extraction capability of the model, improves computational efficiency, and reduces performance degradation. Additionally, an SENet channel attention mechanism is incorporated to emphasize important features while suppressing irrelevant information, overcoming the network’s limitations in capturing detailed information. Furthermore, a two-branch network structure with parallel inputs of original and noisy STFT time-frequency images is designed and combined with dilated convolution optimization. The structure is designed not only to effectively extract time–frequency features and mitigate noise interference but also to enhance the model’s generalization ability, reduce parameter complexity, and enhance diagnostic accuracy. The effectiveness of each module is validated through ablation experiments on a public dataset. It is demonstrated that the proposed method outperforms four other neural network models in terms of accuracy, establishing its suitability for bearing fault diagnosis tasks.
- 26 November 2025
- Published by SAGE Publications in Journal of Vibration and Control
A dual-channel multi-scale residual network with dilated convolution optimization for rolling bearing fault diagnosis
Convolutional neural network (CNN) as a core component of deep learning is utilized to effectively extract potential features from input data through multiple layers of nonlinear units and have thus been widely applied in bearing fault diagnosis. However, the number of model parameters is significantly increased as the depth of the network increases, which potentially leads to overfitting during training and results in negative impacts on the model’s performance. Furthermore, introducing spatial invariance in convolution and pooling operations may reduce the model’s sensitivity to small changes in input data, impairing its ability to capture detailed information. To address these issues, a dual-channel multi-scale residual network with dilated convolution optimization for rolling bearing fault diagnosis is proposed by fusing the Inception network, Residual Neural Network (ResNet), and Squeeze-and-Excitation Network (SENet) attention mechanism to improve CNN. The method integrates the optimized multi-scale feature extraction module in the Inception network and ResNet, which enhances the feature extraction capability of the model, improves computational efficiency, and reduces performance degradation. Additionally, an SENet channel attention mechanism is incorporated to emphasize important features while suppressing irrelevant information, overcoming the network’s limitations in capturing detailed information. Furthermore, a two-branch network structure with parallel inputs of original and noisy STFT time-frequency images is designed and combined with dilated convolution optimization. The structure is designed not only to effectively extract time–frequency features and mitigate noise interference but also to enhance the model’s generalization ability, reduce parameter complexity, and enhance diagnostic accuracy. The effectiveness of each module is validated through ablation experiments on a public dataset. It is demonstrated that the proposed method outperforms four other neural network models in terms of accuracy, establishing its suitability for bearing fault diagnosis tasks.