High-speed train bearing fault diagnosis method based on ensemble learning

Abstract

The invention discloses a high-speed train bearing fault diagnosis method based on ensemble learning, and the method specifically comprises the following steps: obtaining a noisy original signal, carrying out the fault marking and dividing, carrying out the CEEMDAN decomposition, and carrying out the noise reduction of an obtained IMF component; iMF component reconstruction is carried out, and then feature extraction is carried out; respectively transmitting the extracted features into a first-layer single model of an integrated learning model to obtain a classification result; according to the classification result, different weights are distributed to the first layer of single models of the integrated learning model, then the first layer of single models are integrated into a training set, the generated training set is transmitted into a second layer of random forest model of the integrated learning model for training, and a final bearing fault diagnosis result is obtained. According to the invention, the extracted fault signal is high in precision, the classification accuracy is improved, and the problem of low fault diagnosis accuracy of the high-speed train bearing in the prior art is solved.

Description

technical field [0001] The invention belongs to the technical field of high-speed train bearing fault diagnosis, and relates to a high-speed train bearing fault diagnosis method based on integrated learning. Background technique [0002] As an important mode of public transportation, rail transit has the characteristics of large capacity and high speed. Its operating environment is complex and the passenger capacity is large. Once a fault occurs, it is directly related to the life safety of passengers. High-speed train rolling bearing is not only an important component of various mechanical systems in the running part of the train, but also one of the fault-prone components. It supports the axle and bears the load between the wheelset and the car body. Safety has an important impact and ensuring that it is in good operating condition is the key to the safe running of trains. Because high-speed trains need to experience complex operating conditions such as curves, high speed...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a high-speed train bearing fault diagnosis method based on integrated learning, which solves the problem of low accuracy of the existing high-speed train bearing fault diagnosis

Images