Abstract
This article presents a prediagnosis approach for identifying water imbalance faults in proton exchange membrane fuel-cell (PEMFC) systems, aiming to provide early warning alarms to support proactive protection measures. Unlike traditional fixed-model methods, the proposed approach introduces a dynamic framework to handle the complexity of PEMFC fault conditions with improved efficiency and accuracy. First, the minimal redundancy maximal relevance (mRMR) algorithm is employed for feature selection to optimally balance input data quality and quantity. Subsequently, multiple encoder layers enhanced by a mixture of experts (MoE) mechanism are utilized to extract key information. By dynamically activating only the most relevant experts, the model’s adaptability to diverse input is improved, and computational load is reduced. Next, an adaptive multitask learning (MTL) framework is developed to train time-series forecasting and fault classification tasks simultaneously. Finally, the proposed method is validated on a 5-kW PEMFC stack under various operating conditions. Experimental results demonstrate that the proposed method achieves rapid and accurate identification of diverse PEMFC water management faults, detecting anomalies 25 s before occurrence with approximately 98.0% diagnostic accuracy at a fast response time of 1.15 ms.
Funding Information
  • National Natural Science Foundation of China (62573383)
  • National Natural Science Foundation of China (625B2164)
  • Zhejiang Provincial Natural Science Foundation of China (LR26F030003)
  • State Key Laboratory of Industrial Control Technology (ICT2024A11)

This publication has 30 references indexed in Scilit: