Zhenya Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhenya Wang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Tao Liu
Kunming University of Science and Technology
5 shared publications - Chang Liu
Faculty of Mechanical & Electrical Engineering, Kunming University of Science & Technology, Kunming, 650500, People’s Republic of China
4 shared publications - Xing Wu
Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China
4 shared publications Xing Wu
Key Laboratory of Advanced Equipment Intelligent Manufacturing Technology of Yunnan Province, Kunming University of Science & Technology, Kunming, 650500, People’s Republic of China
3 shared publications- Feifei He
Key Laboratory of Advanced Equipment Intelligent Manufacturing Technology of Yunnan Province, Kunming University of Science & Technology, Kunming, 650500, People’s Republic of China
2 shared publications Tao Liu
2 shared publications
Latest Publications
- 29 December 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (4) , 0455e8
Adaptive compressive feature extraction method for bearing signals via dual-branch wavelet convolution joint sparse sensing
To address the issues of difficult sparsity evaluation in traditional compressive sensing and strong randomness in signal compressive sampling, an adaptive deep compressive feature extraction method based on dual-branch wavelet convolution joint sparse sensing is proposed and successfully applied to bearing vibration signals. Firstly, a feature extraction module with a dual-branch heterogeneous wavelet convolution architecture is designed to fully leverage the advantages of different-sized convolution kernels in feature extraction, capturing bearing vibration data features at multiple scales. Secondly, a deep compressive feature reduction module is developed based on the energy-preserving property of compressive sensing. An energy-and-information-entropy co-driven compression strategy is formulated to deeply optimize the reduction process, effectively improving the quality of compressive features. Then, a novel loss function with joint spatial-spectral optimization is constructed to enhance the model’s ability to learn sparse features, and an Adaptive Dynamic Weight Nonlinear Transition (ADWNT) mechanism is proposed to adaptively adjust the loss function weights. Finally, the proposed method is validated using data from a thrust bearing limit state performance test bench and a rotating machinery fault simulation test bench. Experimental results demonstrate that under strong noise conditions, the proposed method not only achieves a Pearson Correlation Coefficient (PCC) exceeding 90% and an approximate 18 dB improvement in the signal-to-noise ratio (SNR) of fault characteristic frequencies—significantly outperforming traditional methods and basic deep learning methods to enable efficient extraction of bearing fault features—but also overcomes the limitations of traditional compressive sensing in feature extraction under strong background noise, while maintaining a favorable balance between model complexity and performance.
- 29 December 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (4) , 0455e8
Adaptive compressive feature extraction method for bearing signals via dual-branch wavelet convolution joint sparse sensing
To address the issues of difficult sparsity evaluation in traditional compressive sensing and strong randomness in signal compressive sampling, an adaptive deep compressive feature extraction method based on dual-branch wavelet convolution joint sparse sensing is proposed and successfully applied to bearing vibration signals. Firstly, a feature extraction module with a dual-branch heterogeneous wavelet convolution architecture is designed to fully leverage the advantages of different-sized convolution kernels in feature extraction, capturing bearing vibration data features at multiple scales. Secondly, a deep compressive feature reduction module is developed based on the energy-preserving property of compressive sensing. An energy-and-information-entropy co-driven compression strategy is formulated to deeply optimize the reduction process, effectively improving the quality of compressive features. Then, a novel loss function with joint spatial-spectral optimization is constructed to enhance the model’s ability to learn sparse features, and an Adaptive Dynamic Weight Nonlinear Transition (ADWNT) mechanism is proposed to adaptively adjust the loss function weights. Finally, the proposed method is validated using data from a thrust bearing limit state performance test bench and a rotating machinery fault simulation test bench. Experimental results demonstrate that under strong noise conditions, the proposed method not only achieves a Pearson Correlation Coefficient (PCC) exceeding 90% and an approximate 18 dB improvement in the signal-to-noise ratio (SNR) of fault characteristic frequencies—significantly outperforming traditional methods and basic deep learning methods to enable efficient extraction of bearing fault features—but also overcomes the limitations of traditional compressive sensing in feature extraction under strong background noise, while maintaining a favorable balance between model complexity and performance.
- 22 November 2025
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 269
Mutual information embedded SSD and its application to bearing fault diagnosis in machining centers
- 22 November 2025
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 269
Mutual information embedded SSD and its application to bearing fault diagnosis in machining centers
- 12 November 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (4) , 045574
A rolling bearing fault diagnosis method based on multi-feature fusion of BiLSTM-DSC- transformer under strong noise background
In the backdrop of the rapid development of intelligent manufacturing technologies, bearings, as core components of mechanical equipment, play a crucial role in monitoring operational status and diagnosing faults to ensure production safety and efficiency. However, bearings often operate under severe environmental noise and frequently changing working conditions, which significantly constrain the noise resistance and generalization performance of intelligent fault diagnosis methods. Therefore, this paper proposes a multi-feature fusion method for rolling bearing fault diagnosis based on BiLSTM-DSC-Transformer (BDT). Firstly, a new nonlinear activation function, R-Swish, is designed and applied to a lightweight deep separable convolution (DSC) feature extraction module in both time and frequency domains, ensuring the model’s feature extraction capability and operational efficiency. Secondly, an adjustable BiLSTM-Transformer model is constructed, fully leveraging the advantages of Transformer in capturing long-range dependencies and the bidirectional data processing mechanism of BiLSTM to reveal the intrinsic relationships among multiple features. Finally, a feature fusion module is established to integrate multi-feature information, combined with a linear classification layer, to achieve high-accuracy fault diagnosis of bearings under complex working conditions. Experimental results from two case studies demonstrate that the proposed method exhibits excellent robustness and generalization ability under strong noise and varying load conditions, providing a new and effective technical solution for the field of bearing fault diagnosis.
- 12 November 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (4) , 045574
A rolling bearing fault diagnosis method based on multi-feature fusion of BiLSTM-DSC- transformer under strong noise background
In the backdrop of the rapid development of intelligent manufacturing technologies, bearings, as core components of mechanical equipment, play a crucial role in monitoring operational status and diagnosing faults to ensure production safety and efficiency. However, bearings often operate under severe environmental noise and frequently changing working conditions, which significantly constrain the noise resistance and generalization performance of intelligent fault diagnosis methods. Therefore, this paper proposes a multi-feature fusion method for rolling bearing fault diagnosis based on BiLSTM-DSC-Transformer (BDT). Firstly, a new nonlinear activation function, R-Swish, is designed and applied to a lightweight deep separable convolution (DSC) feature extraction module in both time and frequency domains, ensuring the model’s feature extraction capability and operational efficiency. Secondly, an adjustable BiLSTM-Transformer model is constructed, fully leveraging the advantages of Transformer in capturing long-range dependencies and the bidirectional data processing mechanism of BiLSTM to reveal the intrinsic relationships among multiple features. Finally, a feature fusion module is established to integrate multi-feature information, combined with a linear classification layer, to achieve high-accuracy fault diagnosis of bearings under complex working conditions. Experimental results from two case studies demonstrate that the proposed method exhibits excellent robustness and generalization ability under strong noise and varying load conditions, providing a new and effective technical solution for the field of bearing fault diagnosis.
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-16
A Fault Diagnosis Method for Variable Condition Equipment Based on Knowledge Transfer and Improved Residual Neural Networks
The foundation of contemporary industry, mechanical equipment is essential to many critical fields, including industrial production, transportation, energy generation, and utilization. Residual Neural Networks (ResNet) have made considerable progress in the identification of mechanical equipment faults in the past few years. However, due to its relatively high model complexity and large number of parameters, ResNet is challenging to implement in industrial settings and deploy on embedded platforms with limited resources. As a result, this research suggests a knowledge-transfer-based approach for diagnosing equipment faults in variable condition that uses enhanced residual neural networks. This method adopts a knowledge distillation architecture, where the teacher network uses an improved ResNet50 network to enhance feature information mining capability; the student network uses a simplified Depthwise Separable Convolutional Neural Network (DSCNN) to achieve lightweight deployment by reducing network size. First, the Short-Time Fourier Transform (STFT) is used to convert the gathered variable condition data into two-dimensional time-frequency pictures, which are then fed into the neural network model. Then, the ResNet50 model is utilized as the teacher network model and its design is gotten to the next level. Next, a simplified Depthwise Separable Convolutional Neural Network (DSCNN) and knowledge distillation method are used to train a more lightweight and efficient student network, transferring the complex knowledge from the teacher network to the lightweight Depthwise Separable Convolutional Network. Lastly, utilizing the rolling bearing experimental dataset under varied conditions, the suggested method is experimentally validated. The findings demonstrate that with a 96.14% accuracy rate, the computational and parameter complexity reduced by approximately 238 times, and the runtime shortened nearly 3 times. Additionally, experimental validation is conducted on a homemade RV gearbox fault simulation test bench. The experimental results demonstrate that the method can achieve robust and efficient fault diagnosis results in different conditions and practical application scenarios.
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-16
A Fault Diagnosis Method for Variable Condition Equipment Based on Knowledge Transfer and Improved Residual Neural Networks
The foundation of contemporary industry, mechanical equipment is essential to many critical fields, including industrial production, transportation, energy generation, and utilization. Residual Neural Networks (ResNet) have made considerable progress in the identification of mechanical equipment faults in the past few years. However, due to its relatively high model complexity and large number of parameters, ResNet is challenging to implement in industrial settings and deploy on embedded platforms with limited resources. As a result, this research suggests a knowledge-transfer-based approach for diagnosing equipment faults in variable condition that uses enhanced residual neural networks. This method adopts a knowledge distillation architecture, where the teacher network uses an improved ResNet50 network to enhance feature information mining capability; the student network uses a simplified Depthwise Separable Convolutional Neural Network (DSCNN) to achieve lightweight deployment by reducing network size. First, the Short-Time Fourier Transform (STFT) is used to convert the gathered variable condition data into two-dimensional time-frequency pictures, which are then fed into the neural network model. Then, the ResNet50 model is utilized as the teacher network model and its design is gotten to the next level. Next, a simplified Depthwise Separable Convolutional Neural Network (DSCNN) and knowledge distillation method are used to train a more lightweight and efficient student network, transferring the complex knowledge from the teacher network to the lightweight Depthwise Separable Convolutional Network. Lastly, utilizing the rolling bearing experimental dataset under varied conditions, the suggested method is experimentally validated. The findings demonstrate that with a 96.14% accuracy rate, the computational and parameter complexity reduced by approximately 238 times, and the runtime shortened nearly 3 times. Additionally, experimental validation is conducted on a homemade RV gearbox fault simulation test bench. The experimental results demonstrate that the method can achieve robust and efficient fault diagnosis results in different conditions and practical application scenarios.
- 15 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (13) , 20989-20998
A Fault Diagnosis Method Based on NTFES-FCCT for Variable Working Condition Bearing Signals
The vibration signals of rolling bearings under the influence of strong background noise and large fluctuation of rotational speed often show the characteristics of strong nonstationarity and spectral dispersion. These characteristics will bring about problems such as the failure of traditional filtering methods, large errors, and low efficiency of order analysis methods. A fault diagnosis method of normalized time-frequency entropy spectrum (NTFES) combined with a fault characteristic coefficient template (FCCT) for variable operating conditions is proposed in this work. First, the time-frequency distribution matrix is obtained by the short-time Fourier transform (STFT) of the vibration signal, and the entropy of the spectrum on each time window is calculated in turn and normalized to get the NTFES. Second, the instantaneous frequency change curve (IFCC) is extracted from the NTFES using the multiple time-frequency curve extraction (MTFCE). Then, the rotational frequency change curve (RFCC) is obtained by fitting the calculation to the simultaneously acquired rotational speed pulse signal. The instantaneous fault characterization change line (IFCCL) is obtained by calculating the ratio of IFCC to RFCC. Finally, the standard fault characterization coefficients are calculated according to the relevant parameters of rolling bearings, and the error analysis of IFCCL and standard fault characteristic change line (SFCCL) in different modes is carried out to realize the identification of bearing fault types under variable speed conditions. The simulation analysis and two real cases verify the effectiveness of the proposed method.
- 15 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (13) , 20989-20998
A Fault Diagnosis Method Based on NTFES-FCCT for Variable Working Condition Bearing Signals
The vibration signals of rolling bearings under the influence of strong background noise and large fluctuation of rotational speed often show the characteristics of strong nonstationarity and spectral dispersion. These characteristics will bring about problems such as the failure of traditional filtering methods, large errors, and low efficiency of order analysis methods. A fault diagnosis method of normalized time-frequency entropy spectrum (NTFES) combined with a fault characteristic coefficient template (FCCT) for variable operating conditions is proposed in this work. First, the time-frequency distribution matrix is obtained by the short-time Fourier transform (STFT) of the vibration signal, and the entropy of the spectrum on each time window is calculated in turn and normalized to get the NTFES. Second, the instantaneous frequency change curve (IFCC) is extracted from the NTFES using the multiple time-frequency curve extraction (MTFCE). Then, the rotational frequency change curve (RFCC) is obtained by fitting the calculation to the simultaneously acquired rotational speed pulse signal. The instantaneous fault characterization change line (IFCCL) is obtained by calculating the ratio of IFCC to RFCC. Finally, the standard fault characterization coefficients are calculated according to the relevant parameters of rolling bearings, and the error analysis of IFCCL and standard fault characteristic change line (SFCCL) in different modes is carried out to realize the identification of bearing fault types under variable speed conditions. The simulation analysis and two real cases verify the effectiveness of the proposed method.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (24) , 30584-30592
Application of Mutual Information Maximization Convolutional Neural Network in Bearing Feature Extraction
Deep learning models can automatically capture the state in a device from complex data. However, it is typically used for end-to-end fault diagnosis and the visualization results of the convolutional layer are abstract. A convolutional neural network model with maximization of mutual information (MMI) between inputs and outputs is proposed. It is the basic idea to enhance the feature extraction capability of the model through improved loss de-constraints, and improve the interpretability of the model at the visualization level. First, the bearing vibration data is converted to an envelope spectrum signal, which is used as input to the model. This process can be viewed as the model conducting feature extraction on the patterns of distinct characteristic spectral lines. Then, the multilayer convolution used for feature extraction is treated as a system; and the output of the system is designed to be the same size as the input of the model so that the model is easy to understand; second, an attention mechanism (AM) is added to enhance the obvious features. Finally, a loss function is designed to drive the convolutional system based on the MI rule between the signal before and after noise reduction to extract more frequency components of the fault features. The simulated signals and real cases show that the proposed method has achieved certain effect in the fault feature extraction of bearings, and also has this certain interpretability in the level of feature visualization.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (24) , 30584-30592
Application of Mutual Information Maximization Convolutional Neural Network in Bearing Feature Extraction
Deep learning models can automatically capture the state in a device from complex data. However, it is typically used for end-to-end fault diagnosis and the visualization results of the convolutional layer are abstract. A convolutional neural network model with maximization of mutual information (MMI) between inputs and outputs is proposed. It is the basic idea to enhance the feature extraction capability of the model through improved loss de-constraints, and improve the interpretability of the model at the visualization level. First, the bearing vibration data is converted to an envelope spectrum signal, which is used as input to the model. This process can be viewed as the model conducting feature extraction on the patterns of distinct characteristic spectral lines. Then, the multilayer convolution used for feature extraction is treated as a system; and the output of the system is designed to be the same size as the input of the model so that the model is easy to understand; second, an attention mechanism (AM) is added to enhance the obvious features. Finally, a loss function is designed to drive the convolutional system based on the MI rule between the signal before and after noise reduction to extract more frequency components of the fault features. The simulated signals and real cases show that the proposed method has achieved certain effect in the fault feature extraction of bearings, and also has this certain interpretability in the level of feature visualization.
- Open Access
- 4 August 2023
- Published by Oxford University Press (OUP) in Journal of Computational Design and Engineering
- Vol. 10 (5) , 1930-1940
A diagnosis method for imbalanced bearing data based on improved SMOTE model combined with CNN-AM
A boundary enhancement and Gaussian mixture model (G) optimized synthetic minority oversampling technique (SMOTE) algorithm (BE-G-SMOTE) is proposed to improve diagnostic accuracy under imbalanced bearing fault data conditions. It is designed to solve the problem that the diversity of samples generated by the original SMOTE model is limited, as well as the deep learning model is limited by the size of training samples and processing speed. Firstly, a few bearing fault data are clustered by G to achieve cluster division. Secondly, according to the cluster density distribution function designed in this paper, the weights of different clusters and sample weights to achieve intra-class balance are determined and data quality is improved. Then, to take full advantage of the limited fault data, based on the sensitivity of the support vector machine (SVM) to imbalanced data, the enhanced boundary is established between generated data and the SVM classifier under different penalty factor (PF) values. According to the accuracy, the optimal PF is determined, and fault datasets satisfying diversity are obtained. To improve the classification accuracy, a convolutional neural network with an attention mechanism is built. Finally, analysis using two practical cases shows the effectiveness of the proposed method.
- 4 August 2023
- Published by Oxford University Press (OUP) in Journal of Computational Design and Engineering
- Vol. 10 (5) , 1930-1940
Open AccessA diagnosis method for imbalanced bearing data based on improved SMOTE model combined with CNN-AM
A boundary enhancement and Gaussian mixture model (G) optimized synthetic minority oversampling technique (SMOTE) algorithm (BE-G-SMOTE) is proposed to improve diagnostic accuracy under imbalanced bearing fault data conditions. It is designed to solve the problem that the diversity of samples generated by the original SMOTE model is limited, as well as the deep learning model is limited by the size of training samples and processing speed. Firstly, a few bearing fault data are clustered by G to achieve cluster division. Secondly, according to the cluster density distribution function designed in this paper, the weights of different clusters and sample weights to achieve intra-class balance are determined and data quality is improved. Then, to take full advantage of the limited fault data, based on the sensitivity of the support vector machine (SVM) to imbalanced data, the enhanced boundary is established between generated data and the SVM classifier under different penalty factor (PF) values. According to the accuracy, the optimal PF is determined, and fault datasets satisfying diversity are obtained. To improve the classification accuracy, a convolutional neural network with an attention mechanism is built. Finally, analysis using two practical cases shows the effectiveness of the proposed method.
- 6 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (2) , 1931-1940
Application of an Oversampling Method Based on GMM and Boundary Optimization in Imbalance-Bearing Fault Diagnosis
Synthetic minority oversampling (SMOTE) has been widely used in dealing with the imbalance classification in the mechanical fault diagnosis field. However, the classical SMOTE model generates poor quality data, which leads to a low diagnostic accuracy of the classification model. This article proposes an oversampling generation model based on the Gaussian mixture model (GMM) and boundary joint optimization (BDOP-GMM-SMOTE). First, GMM is utilized to cluster minority class bearing fault data, and weights of different classes should be distributed according to the cluster density distribution function. Then, the minority classes should be resampled to balance intraclass. Third, the data boundary is established by calculating intraclass and interclass distances between the minority class and other failure-class samples. And penalty coefficient is introduced to optimize data generation boundary by minimizing intraclass and maximizing interclass principle. Afterward, a generated fault dataset satisfied intraclass and interclass balance is obtained. Finally, the generation effectiveness and robustness of the proposed method are verified by bearing experiment data, especially in diagnostic accuracy and processing speed.
- 6 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (2) , 1931-1940
Application of an Oversampling Method Based on GMM and Boundary Optimization in Imbalance-Bearing Fault Diagnosis
Synthetic minority oversampling (SMOTE) has been widely used in dealing with the imbalance classification in the mechanical fault diagnosis field. However, the classical SMOTE model generates poor quality data, which leads to a low diagnostic accuracy of the classification model. This article proposes an oversampling generation model based on the Gaussian mixture model (GMM) and boundary joint optimization (BDOP-GMM-SMOTE). First, GMM is utilized to cluster minority class bearing fault data, and weights of different classes should be distributed according to the cluster density distribution function. Then, the minority classes should be resampled to balance intraclass. Third, the data boundary is established by calculating intraclass and interclass distances between the minority class and other failure-class samples. And penalty coefficient is introduced to optimize data generation boundary by minimizing intraclass and maximizing interclass principle. Afterward, a generated fault dataset satisfied intraclass and interclass balance is obtained. Finally, the generation effectiveness and robustness of the proposed method are verified by bearing experiment data, especially in diagnostic accuracy and processing speed.