Changyun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Changyun Li has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Lanjun Wan
Hunan University of Technology
16 shared publications - Gen Zhang
School of computer science, Hunan University of Technology, Zhuzhou, China
4 shared publications Yuanyuan Li
4 shared publicationsZhibing Wang
School of computer science, Hunan University of Technology, Zhuzhou, China
3 shared publications- Hongyang Li
School of Computer, Hunan University of Technology, Zhuzhou 412007, China
2 shared publications Jiaen Ning
2 shared publications
Latest Publications
- 15 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
A Novel Class Prototype-Guided Open-Set Domain Adaptation Method for Mechanical Fault Diagnosis
Open-set domain adaptation (OSDA) can address the realistic fault diagnosis (FD) scenario where the target domain contains previously unseen fault classes. However, most of the previous studies usually adopt coarse-grained separation approaches and ignore the important role of the closed-set model itself, which affects the FD performance. To address this limitation, a novel class prototype-guided OSDA (CPOSDA) method for mechanical FD (MFD) is proposed. First, a multisource adversarial pretraining approach is designed, which provides a high-quality closed-set model for constructing reliable cross-domain class prototypes. Second, a class prototype-guided progressive separation strategy is developed, which leverages the class prototypes for coarse-grained separation of target domain samples, followed by fine-grained training to refine the decision boundary between known and unknown classes. Third, a domain adaptation (DA) strategy with unknown-class rejection is designed to filter out samples from unknown classes during the distribution alignment process between the source and target domains, thereby reducing the risk of negative transfer. Finally, extensive experiments prove that the proposed method achieves excellent cross-domain FD performance in the open-set scenario and outperforms the comparison methods. The source code is available at https://github.com/NullIsFine/CPOSDA
- 15 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
A Novel Class Prototype-Guided Open-Set Domain Adaptation Method for Mechanical Fault Diagnosis
Open-set domain adaptation (OSDA) can address the realistic fault diagnosis (FD) scenario where the target domain contains previously unseen fault classes. However, most of the previous studies usually adopt coarse-grained separation approaches and ignore the important role of the closed-set model itself, which affects the FD performance. To address this limitation, a novel class prototype-guided OSDA (CPOSDA) method for mechanical FD (MFD) is proposed. First, a multisource adversarial pretraining approach is designed, which provides a high-quality closed-set model for constructing reliable cross-domain class prototypes. Second, a class prototype-guided progressive separation strategy is developed, which leverages the class prototypes for coarse-grained separation of target domain samples, followed by fine-grained training to refine the decision boundary between known and unknown classes. Third, a domain adaptation (DA) strategy with unknown-class rejection is designed to filter out samples from unknown classes during the distribution alignment process between the source and target domains, thereby reducing the risk of negative transfer. Finally, extensive experiments prove that the proposed method achieves excellent cross-domain FD performance in the open-set scenario and outperforms the comparison methods. The source code is available at https://github.com/NullIsFine/CPOSDA
- 12 June 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 299
A novel meta-transfer learning approach via convolutional multi-head self-attention network for few-shot fault diagnosis
- 12 June 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 299
A novel meta-transfer learning approach via convolutional multi-head self-attention network for few-shot fault diagnosis
- Top Cited Papers
- 16 May 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 296
Flexible job shop scheduling via deep reinforcement learning with meta-path-based heterogeneous graph neural network
- 16 May 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 296
Top Cited PapersFlexible job shop scheduling via deep reinforcement learning with meta-path-based heterogeneous graph neural network
- 18 April 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (20) , 11877-11899
An effective deep actor-critic reinforcement learning method for solving the flexible job shop scheduling problem
- 18 April 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (20) , 11877-11899
An effective deep actor-critic reinforcement learning method for solving the flexible job shop scheduling problem
- 9 December 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 284
Intelligent fault diagnosis via ring-based decentralized federated transfer learning
- 9 December 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 284
Intelligent fault diagnosis via ring-based decentralized federated transfer learning
- 30 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (13) , 14601-14617
An Efficient I-PixelHop Framework Based on Spark-GPU for Intelligent Fault Diagnosis
I-PixelHop is a lightweight learning framework based on successive subspace learning. Compared with the deep learning methods, the rolling bearing fault diagnosis (RBFD) model based on I-PixelHop has lower computational complexity and smaller model size, and it can obtain a good diagnosis accuracy in the complex working conditions. However, the training and diagnosis time of the RBFD model based on I-PixelHop are still long in the face of large-scale rolling bearing (RB) fault datasets. Therefore, an efficient I-PixelHop framework based on Spark-GPU for intelligent fault diagnosis is proposed. Firstly, a Spark-GPU-based distributed parallel I-PixelHop framework is developed, which can efficiently perform distributed parallel training and diagnosis. Secondly, an asynchronous parallel execution strategy based on superscalar pipeline is proposed, which can reduce the waiting time of each functional unit of the distributed parallel I-PixelHop framework. Finally, an ensemble classifier based on Bagging is designed and parallelized, which can improve the diagnosis accuracy of the RBFD model based on distributed parallel I-PixelHop framework. Extensive experiments demonstrate that the proposed framework can not only maintain high diagnosis accuracy but also significantly improve the training performance and diagnosis performance of the RBFD model based on I-PixelHop under industrial big data.
- 30 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (13) , 14601-14617
An Efficient I-PixelHop Framework Based on Spark-GPU for Intelligent Fault Diagnosis
I-PixelHop is a lightweight learning framework based on successive subspace learning. Compared with the deep learning methods, the rolling bearing fault diagnosis (RBFD) model based on I-PixelHop has lower computational complexity and smaller model size, and it can obtain a good diagnosis accuracy in the complex working conditions. However, the training and diagnosis time of the RBFD model based on I-PixelHop are still long in the face of large-scale rolling bearing (RB) fault datasets. Therefore, an efficient I-PixelHop framework based on Spark-GPU for intelligent fault diagnosis is proposed. Firstly, a Spark-GPU-based distributed parallel I-PixelHop framework is developed, which can efficiently perform distributed parallel training and diagnosis. Secondly, an asynchronous parallel execution strategy based on superscalar pipeline is proposed, which can reduce the waiting time of each functional unit of the distributed parallel I-PixelHop framework. Finally, an ensemble classifier based on Bagging is designed and parallelized, which can improve the diagnosis accuracy of the RBFD model based on distributed parallel I-PixelHop framework. Extensive experiments demonstrate that the proposed framework can not only maintain high diagnosis accuracy but also significantly improve the training performance and diagnosis performance of the RBFD model based on I-PixelHop under industrial big data.
- Open Access
- 14 October 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-15
A Spatio-Temporal Attention Mechanism Based Approach for Remaining Useful Life Prediction of Turbofan Engine
The time-series data generated by turbofan engines has a great degree of complexity and dynamics. At present, recurrent neural networks are commonly used to model and forecast the remaining useful life (RUL). The relationship of the sample data is not taken into account, and there are issues such as gradient explosion. In view of this, a spatio-temporal attention model is proposed, which comprehensively relates to the temporal association of data features and the hidden state of data features in space. At the same time, position coding is performed on the temporal relationship, avoiding the use of recurrent neural networks. Experimental results show that by combining the two dimensions, the predictive performance of the model is significantly improved. Compared with different methods on the four data sets of the commercial modular aerospace propulsion system simulation (C-MAPSS), the stability and prediction accuracy of the spatio-temporal attention model are better than that of alternative methods.
- 14 October 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-15
Open AccessA Spatio-Temporal Attention Mechanism Based Approach for Remaining Useful Life Prediction of Turbofan Engine
The time-series data generated by turbofan engines has a great degree of complexity and dynamics. At present, recurrent neural networks are commonly used to model and forecast the remaining useful life (RUL). The relationship of the sample data is not taken into account, and there are issues such as gradient explosion. In view of this, a spatio-temporal attention model is proposed, which comprehensively relates to the temporal association of data features and the hidden state of data features in space. At the same time, position coding is performed on the temporal relationship, avoiding the use of recurrent neural networks. Experimental results show that by combining the two dimensions, the predictive performance of the model is significantly improved. Compared with different methods on the four data sets of the commercial modular aerospace propulsion system simulation (C-MAPSS), the stability and prediction accuracy of the spatio-temporal attention model are better than that of alternative methods.