Train bearing fault diagnosis method based on Bayesian blind source separation technology

Abstract

The invention discloses a train bearing fault diagnosis method based on the Bayesian blind source separation technology. The method comprises the steps that observation acoustic signals of a bearing in the train running process are obtained through a plurality of microphones; determining sound source signals of a plurality of fault sources according to the observation acoustic signals based on a Bayesian blind source separation model; and performing spectral analysis on the sound source signal of each fault source, and determining the damage position of the bearing. The sound generated by the bearing in the running process of a train is obtained through a microphone, observation acoustic signals are formed, sound source signals of all fault sources are separated from the observation acoustic signals based on a Bayesian blind source separation model, spectral analysis is conducted on the sound source signals of all the fault sources, the damage position of the bearing is determined, and the damage position of the bearing is obtained. And fault diagnosis of the bearing is realized. The observation acoustic signals are separated by adopting the Bayesian blind source separation model, the sound source signals of the fault source on the bearing are separated, and the difficulty of bearing fault diagnosis is reduced. 本发明公开了一种基于贝叶斯盲源分离技术的列车轴承故障诊断方法，包括：通过若干个传声器获取列车行驶过程中轴承的观测声学信号；基于贝叶斯盲源分离模型，根据观测声学信号确定若干个故障源的声源信号；对每一个故障源的声源信号进行频谱分析，确定轴承的损伤位置。通过传声器获取列车在行驶过程中轴承所产生的声音，形成观测声学信号，并基于贝叶斯盲源分离模型，从观测声学信号中分离出各故障源的声源信号，针对每一个故障源的声源信号进行频谱分析，确定轴承的损伤位置，实现轴承的故障诊断。采用贝叶斯盲源分离模型对观测声学信号进行分离，分离出轴承上故障源的声源信号，降低了轴承故障诊断的难度。