非平稳信号的盲源分离在机械故障诊断中的应用

BLIND SOURCE SEPARATION FOR NONSTATIONARY SIGNAL AND IT'S APPLICATION IN MECHANICAL FAULT DIAGNOSIS

机械设备发生故障时,故障特征的提取很重要。对于多通道的设备故障振动信号,应用非平稳信号的盲源分离算法,可以有效地提取各自独立的非平稳振动源,从而可以准确地进行机械故障诊断。针对不同时频分布的非平稳盲源分离算法,比较了它们的分离效果。以转子的复合故障为例,验证了该算法在故障诊断中可行性。

It is important to extract fault features when machine would be in fault state.The nonstationary vibration sources that are mutually independent can be effectively identified by using the nonstationary blind source separation(method) from the multi-channel fault vibration signals.The separation efficiency of the nonstationary blind source(seperation) method is assessed by using different time-frequency distribution.The results of an experiment under the rotor's multi-faults case show that this method is feasible for fault diagnosis.