Fault diagnosis of PEMFC systems based on an auxiliary transfer network |
| |
| Affiliation: | 1. School of Automotive Studies, Tongji University, Shanghai 201804, China;2. Chinesisch-Deutsches Hochschulkolleg, Tongji University, Shanghai 201804, China;1. Science and Technology on Surface Physics and Chemistry Laboratory, Mianyang, 621907, PR China;2. Institute of Materials, China Academy of Engineering Physics, Mianyang, 621900, China;1. Engineering Laboratory for Energy System Process Conversion & Emission Control Technology of Jiangsu Province, School of Energy and Mechanical Engineering, Nanjing Normal University, Nanjing 210042, China;2. Guangdong Provincial Key Laboratory of Plant Resources Biorefinery, Guangzhou 510006, China;3. Environmental and Renewable Energy Systems, Gifu University, Gifu 501-1193, Japan;4. Zhenjiang Institute for Innovation and Development, Nanjing Normal University, Zhenjiang 212050, China;1. School of Materials Science and Engineering, Shenyang University of Technology, Shenyang 110870, China;2. School of Materials Science and Engineering, Harbin Institute of Technology, Harbin 150001, China;3. Multi-discipline Research Division, Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, China;4. Northwest Institute for Nonferrous Metal Research, Shaanxi Key Laboratory of Biomedical Metal Materials, Xi''an 710016, China;1. School of Physics, University of Electronic Science and Technology of China, Chengdu, 611731, China;2. Institute of Nuclear Physics and Chemistry, China Academy of Engineering Physics, Mianyang, 621900, China;3. Unit of Properties, Department of Materials Science and Engineering, KTH Royal Institute of Technology, Stockholm SE, 10044, Sweden;4. Institute of Modern Physics, Fudan University, Shanghai 200433, China |
| |
| Abstract: | Data-driven fault diagnosis methods require huge amounts of expensive experimental data. Due to the irreversible damage of severe fault embedding experiments to proton exchange membrane fuel cell (PEMFC) systems, rare available data can be obtained. In view of this issue, a fault diagnosis method based on an auxiliary transfer network (ATN) is proposed. This method uses two parallel neural networks (main and auxiliary neural network) and a prediction fusion module to realize fault diagnosis. The auxiliary neural network is a fault diagnosis classifier pretrained based on both slight and severe fault simulative data, and its weights are transmitted into the ATN structure and frozen. After that, the main neural network is trained based on a large number of slight fault experimental data and a small number of severe fault experimental data. Through ATN, the main neural network learns the abstract features of severe faults under the guidance of auxiliary neural network, and realizes the transfer learning from simulation-based fault diagnosis classifier to experiment-based fault diagnosis classifier. Through testing, the accuracy and precision of ATN-based fault diagnosis classifier with LSTM as both main and auxiliary neural network reaches 0.993 and 1.0 respectively, which is higher than the common data-driven methods. |
| |
| Keywords: | PEMFC system Data-driven Transfer learning Fault diagnosis Simulation modeling |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
