Jiang Wang
Research Subjects
Research Interests
Jiang Wang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Liang Ji
College of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China
1 shared publication - Xingwu Yang
Engineering Research Center of Offshore Wind Technology Ministry of Education, Shanghai University of Electric Power, Shanghai, China
1 shared publication - Yang Fu
Engineering Research Center of Offshore Wind Technology Ministry of Education, Shanghai University of Electric Power, Shanghai, China
1 shared publication Yani Wang
College of Electrical Engineering, Shanghai University of Electric Power, Shanghai, China
1 shared publication- Yuan Lu
College of Electrical Engineering, Shanghai University of Electric Power, Shanghai, China
1 shared publication - Zhicheng Meng
Engineering Research Center of Offshore Wind Technology Ministry of Education, Shanghai University of Electric Power, Shanghai, China
1 shared publication
Latest Publications
- 22 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Emerging and Selected Topics in Power Electronics
- Vol. 12 (6) , 5625-5637
Multiple IGBT Open-Circuit Fault Diagnosis Strategy for MMC Using Feature Reconstruction-Based Recurrent Neural Network
The modular multilevel converter (MMC) open-circuit fault diagnosis under full power condition has become a challenging problem. Especially when MMC operates under low power condition, there are significant fluctuations in capacitor voltage and the existing fault diagnosis strategies face difficulties in selecting appropriate thresholds. The paper proposes a multiple open-circuit fault diagnosis strategy for MMC using Feature Reconstruction-Recurrent Neural Network (FR-RNN). In this method, the dominant characteristics of the theoretical and actual capacitor current of the submodules (SMs) are presented as the preferred feature set. The auxiliary mathematical feature based on capacitor current was screened using Maximal Information Coefficient (MIC), then the selected auxiliary mathematical feature and preferred feature set were inputted into the RNN for FR to realize fault diagnosis based on optimal feature set. The proposed strategy can directly achieve accurate fault localization and fault type judgment of SM faults without additional detection steps and diagnostic delay. Additionally, the determined optimal feature set greatly simplifies the network computation, thus avoiding deviation caused by multi-dimensional and redundant features on the diagnosis outputs. Simulation and experimental studies confirm the effectiveness of the strategy.
- 22 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Emerging and Selected Topics in Power Electronics
- Vol. 12 (6) , 5625-5637
Multiple IGBT Open-Circuit Fault Diagnosis Strategy for MMC Using Feature Reconstruction-Based Recurrent Neural Network
The modular multilevel converter (MMC) open-circuit fault diagnosis under full power condition has become a challenging problem. Especially when MMC operates under low power condition, there are significant fluctuations in capacitor voltage and the existing fault diagnosis strategies face difficulties in selecting appropriate thresholds. The paper proposes a multiple open-circuit fault diagnosis strategy for MMC using Feature Reconstruction-Recurrent Neural Network (FR-RNN). In this method, the dominant characteristics of the theoretical and actual capacitor current of the submodules (SMs) are presented as the preferred feature set. The auxiliary mathematical feature based on capacitor current was screened using Maximal Information Coefficient (MIC), then the selected auxiliary mathematical feature and preferred feature set were inputted into the RNN for FR to realize fault diagnosis based on optimal feature set. The proposed strategy can directly achieve accurate fault localization and fault type judgment of SM faults without additional detection steps and diagnostic delay. Additionally, the determined optimal feature set greatly simplifies the network computation, thus avoiding deviation caused by multi-dimensional and redundant features on the diagnosis outputs. Simulation and experimental studies confirm the effectiveness of the strategy.