A health index-based approach for fuel cell lifetime estimation
Hangyu Wu,
Ruiming Zhang,
Wenchao Zhu,
Changjun Xie,
Yang Li,
Yang Yang,
Bingxin Guo,
Changzhi Li,
Rui Xiong
Affiliations
Hangyu Wu
Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, China
Ruiming Zhang
Guangdong Hydrogen Energy Institute of Wuhan University of Technology, Foshan 528000, China
Wenchao Zhu
Hubei Provincial Key Laboratory of Fuel Cells, Wuhan 430070, China; School of Automation, Wuhan University of Technology, Wuhan 430070, China; Corresponding author
Changjun Xie
Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, China; School of Automation, Wuhan University of Technology, Wuhan 430070, China
Yang Li
The Department of Electrical Engineering, Chalmers University of Technology, 41296 Gothenburg, Sweden
Yang Yang
Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, China; School of Automation, Wuhan University of Technology, Wuhan 430070, China
Bingxin Guo
School of Automation, Wuhan University of Technology, Wuhan 430070, China
Changzhi Li
School of Automation, Wuhan University of Technology, Wuhan 430070, China
Rui Xiong
National Engineering Research Center of Electric Vehicles, School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China
Summary: Efficient health indicators (HI) and prediction methods are crucial for assessing the remaining useful life (RUL) of fuel cells. However, obtaining HI under dynamic conditions with frequently changing loads is highly challenging. Therefore, this study proposes a prediction framework based on dynamic conditions. A method combining complete ensemble empirical mode decomposition with adaptive noise, power spectral density, and energy analysis (CPE) is proposed to extract HI under dynamic conditions from the perspectives of frequency and energy. Furthermore, the time convolution network with adaptive Bayesian optimization (AB-TCN) is introduced to address parameter optimization and prediction challenges. Effective feature parameters of the data are identified using random forest and used to train the AB-TCN. Results show that the extracted HI can effectively determine the end-of-life. The AB-TCN achieves accurate RUL estimation with a prediction error of only 6.825% and shows strong adaptability to various prediction tasks.
