粒子滤波在含噪齿轮箱故障盲源分离中的应用

Application of Particle Filter in Blind Source Separation of Gearbox Fault under Complex Noise Environment

在机械故障诊断中,传感器所获得的信号不可避免地受到各种未知噪声的干扰,针对这种复杂噪声环境下的机械信号盲源分离不能得到较好分离效果的问题,提出了一种将粒子滤波用于含噪信号盲分离的方法,首先利用Rao-blackwellised粒子滤波对观测信号进行降噪处理,然后再进行独立分量分析。仿真和实验结果表明该方法是有效的。

In gearbox fault diagnosis,the signals collected by sensors were suffered generally by the disturbance from various types of unknown noises.Under the complex noise environments,the blind source separation of the gearbox faults can not obtain perfect results of separation.In order to solve this problem,a new noisy blind source separation method of gearbox faults was proposed based on particle filter.A denoising process to the observation signals was implemented using Rao-blackwellised particle filter before the independent component analysis.The simulation and experimental results show that the proposed method is effective.