Jun Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jun Wang has a total of 106 co-authors. Here are the top co-authors by number of shared publications:
- Weiguo Huang
Soochow University
32 shared publications - Zhongkui Zhu
Soochow University
20 shared publications - Changqing Shen
Soochow University
14 shared publications - Chuancang Ding
Soochow University
14 shared publications Zhongkui Zhu
14 shared publicationsQingbo He
12 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (19) , 29278-29287
Semi-Supervised Intelligent Diagnosis Based on Dual Momentum Contrast
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (19) , 29278-29287
Semi-Supervised Intelligent Diagnosis Based on Dual Momentum Contrast
- 12 August 2026
- Published by Elsevier in ISA Transactions
- Vol. 177, 236-252
Adaptive mask flow adversarial network for single-source domain generalization fault diagnosis of train bearings
- 12 August 2026
- Published by Elsevier in ISA Transactions
- Vol. 177, 236-252
Adaptive mask flow adversarial network for single-source domain generalization fault diagnosis of train bearings
- 7 August 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
Contrastive adversarial glow model for machinery anomaly detection and degradation assessment
- 7 August 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
Contrastive adversarial glow model for machinery anomaly detection and degradation assessment
- Open Access
Few-Shot Cross-Domain Fault Diagnosis via Wavelet Convolution Embedding and BDC-Based Metric Meta-Learning
Few-shot cross-domain bearing fault diagnosis is challenging because labeled fault samples are limited and signals collected by vibration sensors under different operating conditions often show significant distribution shifts. To improve bearing fault identification under limited-sample and cross-condition scenarios, this paper proposes a wavelet convolution (WC) and Brownian distance covariance (BDC)-based metric meta-learning framework, termed WCBDC. In this framework, the WC is inserted into the feature extraction process to capture multiscale time–frequency information from vibration signals. The BDC is then applied to model nonlinear inter-channel statistical dependencies and improve the discriminability of fault embeddings. The obtained feature embeddings are further organized within a prototypical-network-based classifier, in which category prototypes are estimated from support samples and query instances are assigned by prototype-distance comparison. The proposed method is evaluated on the Paderborn University (PU) and Beijing Jiaotong University (BJTU) bearing datasets under both 5-way 5-shot and 5-way 1-shot scenarios. On the PU dataset, WCBDC reaches average accuracies of 92.19% and 84.13%, while the corresponding results on the BJTU dataset are 77.24% and 62.57%. These results exceed those of representative meta-learning baselines, demonstrating that WCBDC provides improved diagnostic performance for sensor-based bearing fault recognition when labeled samples are scarce and operating conditions vary.
Open AccessFew-Shot Cross-Domain Fault Diagnosis via Wavelet Convolution Embedding and BDC-Based Metric Meta-Learning
Few-shot cross-domain bearing fault diagnosis is challenging because labeled fault samples are limited and signals collected by vibration sensors under different operating conditions often show significant distribution shifts. To improve bearing fault identification under limited-sample and cross-condition scenarios, this paper proposes a wavelet convolution (WC) and Brownian distance covariance (BDC)-based metric meta-learning framework, termed WCBDC. In this framework, the WC is inserted into the feature extraction process to capture multiscale time–frequency information from vibration signals. The BDC is then applied to model nonlinear inter-channel statistical dependencies and improve the discriminability of fault embeddings. The obtained feature embeddings are further organized within a prototypical-network-based classifier, in which category prototypes are estimated from support samples and query instances are assigned by prototype-distance comparison. The proposed method is evaluated on the Paderborn University (PU) and Beijing Jiaotong University (BJTU) bearing datasets under both 5-way 5-shot and 5-way 1-shot scenarios. On the PU dataset, WCBDC reaches average accuracies of 92.19% and 84.13%, while the corresponding results on the BJTU dataset are 77.24% and 62.57%. These results exceed those of representative meta-learning baselines, demonstrating that WCBDC provides improved diagnostic performance for sensor-based bearing fault recognition when labeled samples are scarce and operating conditions vary.
- 7 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75 (00189529) , 1925-1938
Targeted Augmentation Domain-Mixed Network for Single-Source Domain Generalization Fault Diagnosis
Machinery typically operates under constantly changing working conditions in real-time production. Directly applying a diagnostic model, which has been trained solely on monitoring data from a single working condition, to a new unseen working condition poses a notably challenging task called single-source domain generalization (SSDG) fault diagnosis. Current research mainly aims to augment source-domain training samples but struggles to maintain health state information invariance for diverse augmented samples. Therefore, a targeted augmentation domain-mixed network (TADNet) is proposed in this paper for SSDG fault diagnosis of rotating machinery. The TADNet constructs a targeted augmentation chain, which generates samples in an augmented domain with different distributions from the source-domain samples through a chained generation structure, and ensures the semantic consistency of state features. Additionally, a domain random mixing strategy is established to synthesize a new mixed domain with diverse distributions, through probabilistically and randomly mixing the feature statistics of the samples from the source and augmented domains, for further augmentation of samples. The TADNet effectively balances the distribution diversity and semantic consistency of augmented samples in the course of model training. The superior diagnosis generalization ability of the proposed method to unseen working conditions is demonstrated on two rotating machinery datasets.
- 7 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75 (00189529) , 1925-1938
Targeted Augmentation Domain-Mixed Network for Single-Source Domain Generalization Fault Diagnosis
Machinery typically operates under constantly changing working conditions in real-time production. Directly applying a diagnostic model, which has been trained solely on monitoring data from a single working condition, to a new unseen working condition poses a notably challenging task called single-source domain generalization (SSDG) fault diagnosis. Current research mainly aims to augment source-domain training samples but struggles to maintain health state information invariance for diverse augmented samples. Therefore, a targeted augmentation domain-mixed network (TADNet) is proposed in this paper for SSDG fault diagnosis of rotating machinery. The TADNet constructs a targeted augmentation chain, which generates samples in an augmented domain with different distributions from the source-domain samples through a chained generation structure, and ensures the semantic consistency of state features. Additionally, a domain random mixing strategy is established to synthesize a new mixed domain with diverse distributions, through probabilistically and randomly mixing the feature statistics of the samples from the source and augmented domains, for further augmentation of samples. The TADNet effectively balances the distribution diversity and semantic consistency of augmented samples in the course of model training. The superior diagnosis generalization ability of the proposed method to unseen working conditions is demonstrated on two rotating machinery datasets.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-12
Interpretable Time–Frequency Spectra Augmentation and Enhancement for Bearing Imbalanced Fault Diagnosis
The health condition of rolling bearings is crucial for the safety of rotating machines in industry. However, the bearing abnormal samples are rare in engineering practice, thus the historical bearing dataset is usually imbalanced between the normal and abnormal samples, which degrades the performance of traditional intelligent diagnosis model. This paper proposes an interpretable time-frequency spectra augmentation and enhancement (TFSAE) method for bearing imbalanced fault diagnosis. The TFSAE explores a varying-parameter wavelet transform technique to expand the amounts of time-frequency spectra of bearing abnormal samples, and designs a time-frequency attention mechanism to enhance the time-frequency features. The data augmentation technique is physically interpretable, and the enhanced features have physical meanings. Specifically, each sample of the abnormal data is firstly converted to several time-frequency spectra by continuous wavelet transform with varying wavelet bandwidths. Then, the time-frequency spectra of the abnormal samples are combined with those of normal samples using a fixed-parameter wavelet transform to construct balanced bearing dataset, which is used to train a fault diagnosis model to achieve unbiased fault diagnosis. Finally, the time-frequency attention mechanism is designed in the fault diagnosis model to enhance the time-frequency features relevant to fault characteristics while alleviating noise contamination. Experimental results on two bearing datasets demonstrate that the proposed method achieves significant improvements over the state-of-the-art methods in bearing imbalanced fault diagnosis.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-12
Interpretable Time–Frequency Spectra Augmentation and Enhancement for Bearing Imbalanced Fault Diagnosis
The health condition of rolling bearings is crucial for the safety of rotating machines in industry. However, the bearing abnormal samples are rare in engineering practice, thus the historical bearing dataset is usually imbalanced between the normal and abnormal samples, which degrades the performance of traditional intelligent diagnosis model. This paper proposes an interpretable time-frequency spectra augmentation and enhancement (TFSAE) method for bearing imbalanced fault diagnosis. The TFSAE explores a varying-parameter wavelet transform technique to expand the amounts of time-frequency spectra of bearing abnormal samples, and designs a time-frequency attention mechanism to enhance the time-frequency features. The data augmentation technique is physically interpretable, and the enhanced features have physical meanings. Specifically, each sample of the abnormal data is firstly converted to several time-frequency spectra by continuous wavelet transform with varying wavelet bandwidths. Then, the time-frequency spectra of the abnormal samples are combined with those of normal samples using a fixed-parameter wavelet transform to construct balanced bearing dataset, which is used to train a fault diagnosis model to achieve unbiased fault diagnosis. Finally, the time-frequency attention mechanism is designed in the fault diagnosis model to enhance the time-frequency features relevant to fault characteristics while alleviating noise contamination. Experimental results on two bearing datasets demonstrate that the proposed method achieves significant improvements over the state-of-the-art methods in bearing imbalanced fault diagnosis.
- 22 November 2025
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 269
EnergyMatch: A long-tailed semi-supervised learning framework for cross-domain fault diagnosis
- 22 November 2025
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 269
EnergyMatch: A long-tailed semi-supervised learning framework for cross-domain fault diagnosis
- 29 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Physics-Informed Uncertainty-Aware Dynamic Balancing Learning Framework for Unsupervised Universal Domain Generalization Diagnosis Scenario
Conventional domain generalization assumes fully labeled source domains and consistent label spaces across domains. However, in industrial diagnostics, incomplete labeling is common, giving rise to the unsupervised universal domain generalization (UUDG) challenge. The paper proposes a physics-informed uncertainty-aware dynamic balancing learning framework for UUDG bearing fault diagnosis scenarios. The physical knowledge-guided pseudo-label generation strategy can reduce the impact of noise on the fault feature frequency offset and obtain physical pseudo-labels for the source domain and target domain sample sets. The physical knowledge-assisted uncertainty-aware pseudo-label dynamic updating strategy can provide dynamic pseudo-labels with gradually increasing confidence for model training, further reduce noise interference and improve the generalization performance of the model. To maximize the generalization performance of the model while ensuring the accuracy of the model, the weight dynamic balancing strategy for data-physical loss term based on stability testing and loss variance quantification is proposed to break through the accuracy-generalization dilemma, thereby obtaining a robust diagnosis model for UUDG scenario. Comparative experiments, ablation experiments, noise resistance tests, computational efficiency analysis experiments and model interpretability experiments are carried out to comprehensively analyze the diagnostic performance of the proposed method. Compared with the existing domain generalization diagnosis methods, the proposed method achieves more convincing results.
- 29 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Physics-Informed Uncertainty-Aware Dynamic Balancing Learning Framework for Unsupervised Universal Domain Generalization Diagnosis Scenario
Conventional domain generalization assumes fully labeled source domains and consistent label spaces across domains. However, in industrial diagnostics, incomplete labeling is common, giving rise to the unsupervised universal domain generalization (UUDG) challenge. The paper proposes a physics-informed uncertainty-aware dynamic balancing learning framework for UUDG bearing fault diagnosis scenarios. The physical knowledge-guided pseudo-label generation strategy can reduce the impact of noise on the fault feature frequency offset and obtain physical pseudo-labels for the source domain and target domain sample sets. The physical knowledge-assisted uncertainty-aware pseudo-label dynamic updating strategy can provide dynamic pseudo-labels with gradually increasing confidence for model training, further reduce noise interference and improve the generalization performance of the model. To maximize the generalization performance of the model while ensuring the accuracy of the model, the weight dynamic balancing strategy for data-physical loss term based on stability testing and loss variance quantification is proposed to break through the accuracy-generalization dilemma, thereby obtaining a robust diagnosis model for UUDG scenario. Comparative experiments, ablation experiments, noise resistance tests, computational efficiency analysis experiments and model interpretability experiments are carried out to comprehensively analyze the diagnostic performance of the proposed method. Compared with the existing domain generalization diagnosis methods, the proposed method achieves more convincing results.