基于粒子群优化的全变分降噪在轴承故障诊断中的应用

Application of Total Variation Denoising Based on Particle Swarm Optimization in Bearing fault diagnosis

滚动轴承是旋转机械的重要部件。针对强噪声下滚动轴承振动信号故障特征难以提取的问题,提出了基于粒子群优化(PSO)全变分降噪(TVD)的滚动轴承故障诊断方法。通过粒子群优化算法确定全变分降噪的最优参数,然后利用优化的全变降噪算法对滚动轴承振动信号进行降噪,最后对降噪信号进行频谱分析获取滚动轴承故障特征。将所提方法应用于滚动轴承故障诊断,并与基于小波降噪的轴承诊断方法相比较,结果表明了本文方法的有效性和优越性。

Rolling bearings are important parts of rotating machinery.It is difficult to extract the fault characteristics of rolling bearing vibration signals under strong noise.In order to solve the problem,this paper proposes a rolling bearing fault diagnosis method,Total Variation Denoising(TVD)based on Particle Swarm Optimization(PSO).Firstly,a PSO algorithm is used to determine the optimal parameters of TVD.And then the optimized TVD algorithm is used to reduce the noise of the rolling bearing vibration signal.Finally the noise reduction signal is subjected to spectrum analysis to obtain the rolling bearing fault characteristics.The proposed method is applied to the fault diagnosis of rolling bearings.Compared with the bearing diagnosis method based on wavelet noise reduction,the results show the effectiveness and superiority of this method.