基于自适应噪声参数优化ELMD的行星齿轮箱故障诊断研究

Fault diagnosis of planetary gearboxes based on adaptive parameter optimized ensemble local mean decomposition

针对总体局部平均分解(ELMD)中添加白噪声的振幅和集成次数两个关键参数设置依赖使用者经验,以及添加噪声后在信号重构过程中存在残余噪声污染和运算量大的问题,提出一种自适应噪声参数优化的总体局部均值分解(APOELMD)方法。该方法在局部均值分解(LMD)过程中添加成对高频正负白噪声,噪声的幅值和集成次数分别固定为0.01 SD(SD为原始信号的标准差)和2;不断地改变白噪声的上限频率,利用相对均方根误差这一指标来自适应地选取白噪声的最佳上限频率;白噪声的最佳上限频率确定之后,APOELMD方法即可实现最理想的分解效果。仿真实验结果表明,该方法显著提升了ELMD的性能,提高了诊断效率;将该方法应用于行星轮箱故障诊断中,能够精确提取故障特征信息,实现了对行星齿轮箱局部损伤故障的准确判别。

How to select the two critical parameters(the amplitude of added white noise and the number of ensemble trials)is quite essential for adding white noise in the ensemble local mean decomposition(ELMD)technology.Adding white noises will generate some tough problems including the pollution of the residual noise in the signal reconstruction and the large computational cost.To overcome these problems,an adaptive noise parameter optimized ensemble local mean decomposition(APOELMD)was proposed.In the method,a pair of high frequency positive and negative white noises were added in the process of local mean decomposition.The amplitude of the added white noise was fixed as 0.01 times the standard deviation of the original signal and the number of ensemble trids was taken as 2.Then the upper limit frequency of white noise was continually altered to search adaptively the best upper limit frequency of white noise according to the index of relative root-mean-square error.After determining the best upper limit frequency of white noise,the APOELMD method can achieve the most ideal decomposition effect.The simulation results show that the proposed method greatly improves the performance of ensemble local mean decomposition and improves the diagnostic efficiency.The method has been applied to fault diagnosis of a planetary gearbox,which can extract fault feature information accurately,and achieve accurate discrimination of local damage faults of the planetary gearbox.