Chen Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Chen Chen has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Changhua Hu
Laboratory of Intelligent Control, PLA Rocket Force University of Engineering, Xi’an, China
2 shared publications - Chuan He
Rocket Force University of Engineering, Xian, China
2 shared publications - Hong Pei
PLA Rocket Force University of Engineering
2 shared publications - Xiaosheng Si
Rocket Force University of Engineering, Xi’an 710025, China
2 shared publications Changhua Hu
1 shared publication- Changhua Hu
Xi’an Research Institute of High-Technology
1 shared publication
Latest Publications
- Open Access
- 1 September 2026
- Published by Elsevier in SSRN Electronic Journal
Class-Incremental Unsupervised Domain Adaptation for Rotating Machinery Fault Diagnosis via Reliable Shared-Class Identification and Selective Adversarial Alignment
Rotating machinery continuously generates unlabeled monitoring data during long-term operation, and the data distribution dynamically evolves with changing operating conditions. Conventional static offline diagnostic methods lack continuous adaptation capability, making it difficult to simultaneously handle newly emerging fault categories and cross-condition distribution shifts. This paper investigates class-incremental unsupervised domain adaptation for fault diagnosis (CIUDA-FD). In this setting, a diagnostic model is required to incrementally learn emerging fault categories from an unlabeled target-domain data stream while retaining previously acquired diagnostic knowledge. To address this challenge, this paper proposes a reliable shared-class identification and selective adversarial alignment (ReSCI-SAA) framework. Specifically, a tri-criteria shared-class identification (TriSCI) module with confidence fusion is first designed to identify reliable shared classes by jointly considering cumulative prediction probability, intra-domain clustering compactness, and inter-domain similarity. Based on the identified shared classes, a pseudo-label-guided selective adversarial alignment strategy is developed to align reliable class distributions across domains and reduce negative transfer from unreliable target samples. Furthermore, a prototype-accumulated knowledge distillation mechanism is introduced to mitigate catastrophic forgetting during class-incremental adaptation. Experimental results on the public CWRU bearing dataset and a self-built motor fault dataset demonstrate that the proposed method achieves superior average diagnostic performance over the best-performing existing method across multiple transfer tasks.
- 1 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessClass-Incremental Unsupervised Domain Adaptation for Rotating Machinery Fault Diagnosis via Reliable Shared-Class Identification and Selective Adversarial Alignment
Rotating machinery continuously generates unlabeled monitoring data during long-term operation, and the data distribution dynamically evolves with changing operating conditions. Conventional static offline diagnostic methods lack continuous adaptation capability, making it difficult to simultaneously handle newly emerging fault categories and cross-condition distribution shifts. This paper investigates class-incremental unsupervised domain adaptation for fault diagnosis (CIUDA-FD). In this setting, a diagnostic model is required to incrementally learn emerging fault categories from an unlabeled target-domain data stream while retaining previously acquired diagnostic knowledge. To address this challenge, this paper proposes a reliable shared-class identification and selective adversarial alignment (ReSCI-SAA) framework. Specifically, a tri-criteria shared-class identification (TriSCI) module with confidence fusion is first designed to identify reliable shared classes by jointly considering cumulative prediction probability, intra-domain clustering compactness, and inter-domain similarity. Based on the identified shared classes, a pseudo-label-guided selective adversarial alignment strategy is developed to align reliable class distributions across domains and reduce negative transfer from unreliable target samples. Furthermore, a prototype-accumulated knowledge distillation mechanism is introduced to mitigate catastrophic forgetting during class-incremental adaptation. Experimental results on the public CWRU bearing dataset and a self-built motor fault dataset demonstrate that the proposed method achieves superior average diagnostic performance over the best-performing existing method across multiple transfer tasks.
- 12 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-17
KLASSIC: Knowledge Pool-Assisted Forgetting-Resistant Representation Calibration for Few-Shot Class-Incremental Fault Diagnosis
Machinery in continuous operation may develop new faults over time, which not only jeopardizes the safe operation of equipment but also comes with scant available fault data, hampering the establishment of reliable diagnostic models. These challenges, termed Few-Shot Class-Incremental Fault Diagnosis (FS-CIFD), require the model to balance between retaining past diagnostic abilities and adapting to new faults despite scarce data. Existing incremental fault diagnosis methods suffer from catastrophic forgetting, primarily due to the model’s representation bias toward newly occurring faults. Moreover, the scarcity of new fault data induces overfitting, further aggravating catastrophic forgetting. To tackle FS-CIFD, we propose a novel Knowledge Pool-Assisted Forgetting-Resistant Representation Calibration (KLASSIC) method. Unlike existing methods, KLASSIC integrates signal statistical knowledge to enhance fault features in scarce data, enabling the model to learn generalized representations. First, a knowledge pool is established to offer a shared knowledge space and output task-relevant knowledge, reactivating the model’s memory of previously learned faults. Second, we design a Knowledge-Prompted Guided Adaptive Calibration (KPGAC) module to correct the representation bias towards new fault types and mitigate catastrophic forgetting. Third, to alleviate the overfitting, pseudo-incremental tasks are constructed, facilitating the development of a generalizable feature space for forthcoming tasks. Extensive experiments with different case studies demonstrate that KLASSIC outperforms existing methods in handling FS-CIFD challenges.
- 12 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-17
KLASSIC: Knowledge Pool-Assisted Forgetting-Resistant Representation Calibration for Few-Shot Class-Incremental Fault Diagnosis
Machinery in continuous operation may develop new faults over time, which not only jeopardizes the safe operation of equipment but also comes with scant available fault data, hampering the establishment of reliable diagnostic models. These challenges, termed Few-Shot Class-Incremental Fault Diagnosis (FS-CIFD), require the model to balance between retaining past diagnostic abilities and adapting to new faults despite scarce data. Existing incremental fault diagnosis methods suffer from catastrophic forgetting, primarily due to the model’s representation bias toward newly occurring faults. Moreover, the scarcity of new fault data induces overfitting, further aggravating catastrophic forgetting. To tackle FS-CIFD, we propose a novel Knowledge Pool-Assisted Forgetting-Resistant Representation Calibration (KLASSIC) method. Unlike existing methods, KLASSIC integrates signal statistical knowledge to enhance fault features in scarce data, enabling the model to learn generalized representations. First, a knowledge pool is established to offer a shared knowledge space and output task-relevant knowledge, reactivating the model’s memory of previously learned faults. Second, we design a Knowledge-Prompted Guided Adaptive Calibration (KPGAC) module to correct the representation bias towards new fault types and mitigate catastrophic forgetting. Third, to alleviate the overfitting, pseudo-incremental tasks are constructed, facilitating the development of a generalizable feature space for forthcoming tasks. Extensive experiments with different case studies demonstrate that KLASSIC outperforms existing methods in handling FS-CIFD challenges.
- Open Access
- 4 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 159262-159283
MSARN: A Deep Neural Network Based on an Adaptive Recalibration Mechanism for Multiscale and Arbitrary-Oriented SAR Ship Detection
Ship detection plays an important role in synthetic aperture radar (SAR) image interpretation. However, there are still some difficulties in SAR ship detection. First, ships often have a large aspect ratio and arbitrary directionality in SAR images. Traditional detection algorithms can cause the detection area to be redundant, which makes it difficult to accurately locate the target in complex scenes. Second, ships in ports are often densely arranged, and the effective identification of densely arranged ships is complicated. Finally, ships in SAR images exist at a variety of scales due to the multiresolution imaging modes used and ship shape variations, which pose a considerable challenge for ship detection. To solve the above problems, we propose a multiscale adaptive recalibration network (MSARN) to detect multiscale and arbitrarily oriented ships in complex scenarios. The recalibration of the extracted multiscale features through global information increases the sensitivity of the network to the target angle, thereby increasing the accuracy of positioning. In particular, we designed a pyramid anchor and a loss function to match the rotated target. In addition, we modified the rotation non-maximum suppression (RNMS) method to solve the problem of the large overlap ratio of the detection box. The proposed model combines the positioning advantage of rotation detection with the speed advantage of a single-stage framework. Experiments show that based on the SAR rotation ship detection (SRSD) data set, the proposed algorithm has a faster detection speed and higher accuracy than some state-of-the-art methods.
- 4 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 159262-159283
Open AccessMSARN: A Deep Neural Network Based on an Adaptive Recalibration Mechanism for Multiscale and Arbitrary-Oriented SAR Ship Detection
Ship detection plays an important role in synthetic aperture radar (SAR) image interpretation. However, there are still some difficulties in SAR ship detection. First, ships often have a large aspect ratio and arbitrary directionality in SAR images. Traditional detection algorithms can cause the detection area to be redundant, which makes it difficult to accurately locate the target in complex scenes. Second, ships in ports are often densely arranged, and the effective identification of densely arranged ships is complicated. Finally, ships in SAR images exist at a variety of scales due to the multiresolution imaging modes used and ship shape variations, which pose a considerable challenge for ship detection. To solve the above problems, we propose a multiscale adaptive recalibration network (MSARN) to detect multiscale and arbitrarily oriented ships in complex scenarios. The recalibration of the extracted multiscale features through global information increases the sensitivity of the network to the target angle, thereby increasing the accuracy of positioning. In particular, we designed a pyramid anchor and a loss function to match the rotated target. In addition, we modified the rotation non-maximum suppression (RNMS) method to solve the problem of the large overlap ratio of the detection box. The proposed model combines the positioning advantage of rotation detection with the speed advantage of a single-stage framework. Experiments show that based on the SAR rotation ship detection (SRSD) data set, the proposed algorithm has a faster detection speed and higher accuracy than some state-of-the-art methods.
- Open Access
- 24 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 104848-104863
A Deep Neural Network Based on an Attention Mechanism for SAR Ship Detection in Multiscale and Complex Scenarios
- 24 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 104848-104863
Open AccessA Deep Neural Network Based on an Attention Mechanism for SAR Ship Detection in Multiscale and Complex Scenarios