High-speed train traction system fault diagnosis method

Abstract

The invention discloses a high-speed train traction system fault diagnosis method, and relates to the field of high-speed train fault diagnosis, the method comprises the following steps: acquiring sequence data from a semi-physical simulation platform and preprocessed to obtain a data set, and the data set comprises a training set and a test set; improving an LSTM auto-encoder through state differential feedback control, obtaining a first LSTM auto-encoder, and the first LSTM auto-encoder is composed of L LSTM units; training the LSTM auto-encoder I by using the data set to obtain an LSTM auto-encoder II; extracting an original feature vector of the test set by using the LSTM auto-encoder II; performing feature dimension reduction on the original feature vector by using a t-SNE algorithm;and performing fault diagnosis on the dimension-reduced original feature vector through a DBSCAN clustering method to obtain a diagnosis result. According to the method, the problems of difficult diagnosis and low diagnosis accuracy of the micro gradient fault of the high-speed train traction system can be effectively solved.

Description

technical field [0001] The invention relates to the field of fault diagnosis of high-speed trains, in particular to a method for diagnosing small gradual faults of traction systems of high-speed trains based on data learning. Background technique [0002] At present, high-speed trains are playing an increasingly important role in China's passenger and freight transportation. As the core power system of high-speed trains, the failure of the traction system will lead to train stoppages, delays and other accidents, resulting in huge losses. Among them, small gradual faults occur in the initial stage of significant faults, and have the characteristics of inconspicuous fault characteristics and easy to be covered by unknown disturbances and noises. Therefore, the detection and diagnosis of minor gradual faults in the traction system are more difficult than significant faults. Effective detection and diagnosis of small and gradual faults in the traction system, and timely effecti...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a high-speed train traction system fault diagnosis method to solve the technical problems of small gradient fault diagnosis difficulties and low diagnostic accuracy in the prior art

Images