High-speed train bogie fault detection method based on multi-sensor data fusion

Abstract

The invention discloses a high-speed train bogie fault detection method based on multi-sensor data fusion. The detection method comprises the steps that S1 original data signals acquired by a number of sensors arranged on a bogie are collected; S2 the collected original data signals are divided into separate signals of each channel; S3 a spectrum map corresponding to the signals of each channel isgenerated; S4 the classification result of the spectrum map of each channel is acquired through a random forest algorithm; and S5 a voting method is used to merge the classification results of all channel spectrum maps to acquire the fault type. The method provided by the invention has the advantages that the process of extracting the features of bogie vibration signals is simple and efficient, and the accuracy of fault detection is greatly improved through an automatic multi-channel fusion method.

Description

technical field [0001] The invention belongs to the field of train fault detection, in particular to a high-speed train bogie fault detection method based on multi-sensor data fusion. Background technique [0002] In recent years, with the continuous increase of the operating mileage of my country's railways and the gradual increase of train speed, the transportation needs of the society have been gradually met. At the same time, people's safety requirements for high-speed train transportation are also increasing. In this context, more and more research is focused on the fault diagnosis of high-speed trains. The bogie is the only connection unit between the train body and the track, and the deterioration of its key components will seriously threaten the safety of train operation. Therefore, high-speed train bogie fault detection has important research significance. [0003] The high-speed train bogie structure mainly includes two sets of wheelsets, frame, braking device an...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above-mentioned deficiencies in the prior art, the high-speed train bogie fault detection method based on multi-sensor data fusion provided by the present invention solves the problem that the process of extracting bogie vibration signal characteristics in the existing fault detection method is complex and the extracted signal characteristics are unstable. , the problem of manually selecting reliable channels

Images