针对传统的机械故障源分离方法忽略信号非平稳性的不足,结合时频分析和盲源分离的各自优点,提出一种基于时频分析的机械设备非平稳信号的盲分离方法,并与传统的机械故障源分离方法进行对比。实验结果表明,对于机械设备非平稳混迭信号,必须充分利用信号的非平稳性,才能达到很好的分离效果。文中的研究为机械设备非平稳混迭信号的分离提供一种新方法。
The traditional blind source separation of machine faults is usually neglected the nonstationarity of fault signals. Based on this deficiency, here, combined the advantage of time-frequency analysis (TFA) and blind source separation (BSS), a blind separation method of non-stationary signals in the mechanical equipment based on time-frequency distributions, which is named the TFA-BSS method, is proposed. The proposed method is compared with the traditional separation method of machine fault sources. The experiment results show that non-stationarity is fully considered in the separation of the machine faults. This research provides a new method for the blind separation of non-stationary mixture signals in the mechanical equipment.