Fault diagnosis method for high-speed train bogie

Abstract

The invention discloses a fault diagnosis method for a high-speed train bogie, proposes a full vector sample entropy feature extraction algorithm, and combines the full vector sample entropy feature extraction algorithm with noise-assisted multi-element empirical modal decomposition to perform high-speed train bogie failure diagnosis. The fault diagnosis method comprises the steps of: acquiring vibration signal data during train operation by means of sensors; decomposing the signals by means of noise-assisted multi-element empirical modal decomposition to obtain a series of multi-element intrinsic mode functions (IMFs); selecting IMF components most relevant to an original signal by adopting a correlation coefficient method; performing full vector sample entropy feature extraction on the valid IMF components to obtain feature vectors, and finally, using the feature components as input of a support vector machine to identify a running state of a train. The fault diagnosis method fuses the information of two homologous channels, introduces the full vector concept to obtain a fusion result, fully considers the information fusion between signals, and can better reflect the features ofthe signals of each channel, thereby acquiring higher identification rate.

Description

technical field [0001] The invention relates to the technical field of high-speed train fault diagnosis, in particular to a high-speed train bogie fault diagnosis method combined with full vector sample entropy and noise-assisted multiple empirical modes. Background technique [0002] High-speed train technology is the most technologically advanced and one of the most important subsystems in the world's high-speed railway operation system. In recent years, with the rapid development of high-speed trains, the running speed of trains has been increasing, and the safety and reliability of trains have also received more and more attention. The key components of the train will be damaged during the long-term operation and service, which will have a certain impact on the safe operation of the high-speed train. Therefore, in order to ensure the stability and safety of high-speed trains during long-term service, we use sensors installed on the running part to obtain vibration signa...

AI Technical Summary

Problems solved by technology

In feature extraction, the commonly used traditional sample entropy algorithm is for one-dimensional signals, and if the multi-channel signal processing method of noise-assisted multivariate empirical mode is used to decompose the vibration signal, a series of multivariate IMF components will be obtained. Therefore, the sample entropy algorithm is still used for feature extraction for multi-dimensional signals, but only one of the dimensions is processed, and the obtained eigenvalues ​​cannot reflect the connection between channels, and the results of a single channel cannot reflect the overall characteristics of the vehicle body motion state. , so the best result cannot be obtained

The low recognition rate in high-speed train bogie fault diagnosis will bring greater danger, because the loss cost caused by not correctly judging the faulty parts is very high

Therefore, for multi-channel signal feature extraction, the information obtained by single-channel signal processing is not perfect. In order to overcome the singleness of multi-channel signal processing, it is very interesting to find a feature extraction method that can fuse multi-channel signal information. meaningful

Images