Online Fault Diagnosis of Multi-function Vehicle Bus Based on Decision Tree

Abstract

AbstractAs an important part of the train communication network, the multi-function vehicle bus (MVB) is used for data transmission and information sharing between various devices in the train. The fault of the MVB network will seriously affect the stable operation of the train. In this paper, an online fault diagnosis method of MVB based on waveform features and decision tree is proposed. By extracting features of MVB physical waveform under normal and different fault conditions, the decision tree is used for fault diagnosis of MVB. In the classification process, Gini index is selected as the selection standard of the optimal features, and the depth of the tree is limited to reduce the scale and the space occupancy of the model. Transplant the model to the hardware board, complete online fault diagnosis in the embedded environment. Finally, a test platform was built in the laboratory environment, and the experimental results verified the effectiveness of the method.KeywordsMVBFeature extractionDecision treeOnline fault diagnosis