基于参数优化VMD的滚动轴承故障诊断方法

Fault Diagnosis Method of Rolling Bearing Based on Parameter Optimization VMD

针对机械设备中滚动轴承的早期故障识别问题,提出了一种基于参数优化变分模态分解的轴承故障诊断方法。该方法以包络熵为适应度函数,利用鲸鱼优化算法对变分模态分解算法的最佳影响参数组合[K,α]进行搜索,确定变分模态分解的分量个数K值和惩罚参数α。然后对轴承振动信号进行变分模态分解得到若干IMF分量,并选取包络熵最小的最佳IMF分量进行包络解调分析,提取该分量包含的故障特征频率,从而判断滚动轴承的故障类型。通过对实测轴承振动信号的处理分析以及与EMD方法的对比分析,证明了该方法的有效性。

Aiming at the early fault identification of rolling bearings in mechanical equipment,a bearing fault diagnosis method based on parameter optimization variational mode decomposition is proposed.In this method,envelope entropy is taken as fitness function,and the whale optimization algorithm is used to search for the optimal influence parameter combination of the variational modal decomposition algorithm,so as to determine the number of components k value and penalty parameter.Then,some IMF components are obtained by variational modal decomposition of bearing vibration signals,the optimal IMF component with the minimum envelope entropy is selected for envelope demodulation analysis,and the fault characteristic frequency contained in this component is extracted,so as to determine the fault type of rolling bearing.Through processing and analyzing the vibration signal of the bearing measured and comparing with EMD method,the effectiveness of the method is proved.