Research on Fault Detection of High-Speed Train Bogie

Abstract

With the rapid development of railway network, the safety, comfort and efficiency of high-speed train (HST) is attracting more and more attention from people. Bogie is one of the most important components in the train system. By means of sensors distributed in each position of the train, the real-time data of a large number of HST are obtained. These data contain abundant train operation information, through data mining, analysis and detection of a series of means to obtain the status of the bogie, then comparative analysis of the fault characteristics of the bogie. This paper summarizes the currently widely used in the HST bogie faults diagnosis method, mainly describes the polymerization of empirical mode decomposition and support vector machine (SVM), BP neural network, depth learning algorithm, etc. According to the advantages and disadvantages of different algorithms, puts forward the characteristics and difficulties of the fault diagnosis, and the future research direction and development trend in this field.