Train rolling bearing state identification method based on parameter optimization MOMEDA-MIA-CNN

Abstract

The invention relates to the technical field of train key component operation state identification, and discloses a train rolling bearing state identification method based on parameter optimization MOMEDA-MIA-CNN, and the method comprises the following steps: (1), obtaining train rolling bearing data; step (2), optimization of MOMEDA parameters is carried out; step (3), data preprocessing; (4) carrying out modal interval processing on the train rolling bearing operation data; step (5), establishing a train rolling bearing MIA-CNN initial model; step (6), optimizing the train rolling bearing MIA-CNN model; and (7) identifying the running state of the rolling bearing of the train. And the MIA-CNN model is used to carry out adaptive feature extraction and state identification on the denoised interval signal, so that end-to-end transmission of data is realized, human influence is reduced, and a train rolling bearing operation state identification result has good reliability.

Description

technical field [0001] The invention relates to the technical field of running state identification of key components of a train, in particular to a state identification method of a rolling bearing of a train based on parameter optimization MOMEDA-MIA-CNN. Background technique [0002] The rapid development of rail transit has brought infinite convenience to the lives of the public. At the same time, the safety of trains has received more and more attention. Rolling bearing is one of the most important components in the transmission system as a key component of the bogie frame and axle. The timely identification of its running status is of great significance to ensure the safe and smooth operation of the train and the safety of train personnel. [0003] During the actual operation of the train, the rolling bearing of the train bears a huge load for a long time, and the complex and harsh operating environment of high speed and high temperature in which the bearing is located ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the train rolling bearing vibration signal is affected by the transmission path and background noise, and the operating state recognition rate is not high due to the weak fault characteristics, and proposes a train rolling bearing state based on parameter optimization MOMEDA-MIA-CNN combination recognition methods

Images