An Online Fault Diagnosis Method for PEMFC Based on Output Voltage and Transfer Convolutional Neural Network

Abstract

To achieve accurate and fast online fault diagnosis of proton exchange membrane fuel cell (PEMFC) under complex operating conditions, this article proposes a diagnostic method based on voltage-transfer learning convolutional neural network (V-TCNN). The sensitive analysis for PEMFC is conducted for pattern identifications first, and the output voltage response which can accurately characterize the internal mechanisms of the fuel cell stacks is applied to improve the fault diagnosis accuracy. Besides, to reduce the computation time and improve the portability of the diagnostic algorithm, transfer learning methods are applied to optimize the conventional neural network (CNN) architecture. The comparison tests show that the proposed algorithm can improve the diagnostic accuracy by 7.5% and reduce the computation time by 20% compared with the current existing deeply layered neural networks. Comprehensive analysis shows that the algorithm can reach a fault diagnosis accuracy of 99.56%, which can help to contribute to the development and implementation of fuel cell online fault diagnosis methods in fuel cell electric vehicles (FCEVs).