Fault diagnosis of proton exchange membrane fuel cell system of tram based on information fusion and deep learning

Abstract

The reliability of fuel cell tram depends largely on the normal operation of on-board proton exchange membrane fuel cell (PEMFC) system. Therefore, timely and accurate fault diagnosis is necessary to further commercialize the fuel cell tram. And, a new fault diagnosis method BPNN-InceptionNet based on information fusion and deep learning is proposed in this paper. In this method, high-dimensional abstract features are extracted from the original measurement information by back propagation neural network (BPNN) and converted into feature maps for information fusion in feature level. Then the feature maps are transferred to a proposed Convolutional Neural Network (CNN) based on InceptionNet to realize fault classification. From the experiments, it is found that the kappa coefficient by BPNN-InceptionNet for the test set can reach 0.9884, which is better than that by BPNN, BPNN-VGG, and support vector machine (SVM) classifiers, meaning that the proposed method can achieve better diagnostic performance.