Data-driven approaches for predicting performance degradation of solid oxide fuel cells system considering prolonged operation and shutdown accumulation effect

• Published in: Journal of power sources 2024-04, Vol.598, p.234186, Article 234186
• Main Authors: Wu, Xiao-long, Li, Yu, Cai, Shiyun, Xu, Yuanwu, Hu, Lingyan, Chi, Bo, Peng, Jingxuan, Li, Xi
• Format: Article
• Language: English
• Subjects: Data-driven; Degradation prediction; Neural network; Shutdowns factors; Solid oxide fuel cells (SOFC)
• ISSN: 0378-7753; 1873-2755
• DOI: 10.1016/j.jpowsour.2024.234186

Solid oxide fuel cell system is widely acknowledged as the leading alternative energy generation system in the field. Due to their high efficiency, low emissions, low noise, and various other advantages, solid oxide fuel cell systems are being considered for use in automobiles as a replacement for traditional internal combustion engines. However, prolonged operation and abnormal shutdowns can lead to performance degradation, which affects the efficiency, stability, and lifespan of stack. In the context of prolonged operation, considering the fluctuations in stack performance parameters and balance of plant, several regression models based on voltage parameters are established to accurately predict changes in stack performance. The results reveal that the genetic algorithm optimized backpropagation neural network model is highly sensitive in predicting the system performance degradation. Further analysis reveals that abnormal shutdowns can cause system performance fluctuations. As a result, the number and duration of shutdowns are incorporated into genetic algorithm optimized backpropagation neural network model for analysis. This model exhibits the best performance degradation evolution prediction compared to the long short-term memory and particle swarm optimization backpropagation neural network methods. This finding is important for monitoring and controlling the operational status of stack. [Display omitted] •This paper develops multiple models to predict performance degradation.•The models consider prolonged operation and abnormal shutdowns.•The proposed method reduces the prediction error by 68.47%.