基于WOA-VMD及综合评价指标的轴承故障诊断

针对轴承振动信号的冗余信息过多、故障特征提取率较低的问题,提出一种基于鲸鱼算法及综合评价指标优化变分模态分解(VMD)参数的轴承故障特征提取方法。首先构建了一种模糊熵与峭度倒数和的综合评价指标,作为鲸鱼优化算法(WOA)的适应度函数;其次对VMD的相关参数进行寻优;然后使用优化的参数对原始信号进行VMD分解,得到固有模态函数(IMFs),选取模糊熵与峭度倒数和最小的IMF作为目标模态;最后对目标分量进行希尔伯特包络谱分析来提取故障特征。在仿真信号实验和实测数据实验中与传统方法对比,结果表明,鲸鱼算法与综合指标的结合能选取最优VMD分解参数,故障频率提取率较传统方法有所提高。

Bearing Fault Diagnosis Based on WOA-VMD and Comprehensive Evaluation Index

In order to solve the problem of too much redundant information and low fault feature extraction rate of bearing vibration signals,a bearing fault feature extraction method based on whale optimization algorithm(WOA)and comprehensive evaluation index to optimize variational mode decomposition(VMD)parameters is proposed.Firstly,a comprehensive evaluation index of fuzzy entropy and reciprocal of kurtosis is constructed,which is used as the fitness function of WOA to optimize the relevant parameters of VMD.Then the original signal is decomposed by VMD using the optimized parameters,and the intrinsic mode function(IMFs),selects fuzzy entropy and reciprocal of kurtosis and the minimum IMF as target mode.Finally,Hilbert envelope spectrum analysis is used to extract fault features.Compared with the traditional method in the simulation signal experiment and measured data experiment,the results show that the combination of whale algorithm and comprehensive index can select the optimal VMD decomposition parameters,and the fault frequency extraction rate is higher than that of the traditional method.