High-speed train operation condition identification method

Abstract

The invention discloses a high-speed train operation condition identification method, which is characterized by, to begin with, carrying out pretreatment on vibration signal data of a high-speed train; then, carrying out variational mode decomposition on different channels of monitoring data to obtain mode function characteristics; calculating fuzzy entropy correspondingly, and obtaining feature vectors of different conditions under of a plurality of channels as samples to be tested in multi-view learning; and finally, carrying out identification through a Multi-View K-means cluster. The method has the advantages of more complete knowledge learning, simpler flow and higher operability and the like, and is mainly applied to identification of operation conditions of the high-speed train.

Description

technical field [0001] The invention relates to the technical field of high-speed train operation mode recognition. Background technique [0002] With the rapid development of my country's high-speed train industry, the advantages of high-speed trains such as fast speed, high punctuality rate, comfort and convenience, and light environmental impact have attracted more and more people to choose to travel by high-speed trains, thus causing hidden troubles in the operation of high-speed trains. received more and more attention. The bogie of the running part is an important part of the train. The damping springs and shock absorbers on the bogie ensure the smooth running of the train and make passengers more comfortable during the train running. Since the bogie in the running part of the high-speed train may occasionally fail or become unstable during actual operation, we need to identify the detection data of several types of trains collected by the sensor during operation, and ...

AI Technical Summary

Problems solved by technology

[0006] It can be seen that although the existing methods have certain advantages, there are also some shortcomings: EMD decomposition will produce modal aliasing for abnormal signals, resulting in incomplete separation of frequencies during signal decomposition, so the effect of feature extraction is not obvious; and EEMD The algorithm has achieved good results in suppressing modal aliasing, but the EEMD algorithm introduces Gaussian white noise, which damages the purity of the original signal

[0007] And at present, the processing of high-speed train vibration signals is mostly learned through the data of a single channel, and the information of multiple channels has diversity and inconsistency. In order to use the supplementary information that may exist in multiple channels at the same time, we use multi-view. Learning method, and clustering can overcome the disadvantages of large amount of calculation and lack of a large amount of prior knowledge in traditional fault identification technology

Images