一种基于遗传算法的VMD参数优化轴承故障诊断新方法

New fault diagnosis approach for bearings based on parameter optimized VMD and genetic algorithm

为准确提取轴承故障特征信息,提出以峭度指标和包络熵为综合目标函数的变分模态分解(variational mode decomposition,VMD)参数优化方法,并改进了诊断流程实现了无需指定参数优化范围的自适应参数优化算法。通过遗传算法对综合目标函数最小值进行搜索,以确定模态分量个数及惩罚参数的最佳组合。原始故障信号经最佳参数组合下的VMD方法分解为若干个本征模态函数,选择最小综合目标函数值对应的模态分量进行包络解调分析,进而通过模态分量的包络谱判断轴承故障类型。通过实测故障信号分析表明,该方法能够从噪声干扰中有效提取到早期故障信号的微弱故障特征,实现了轴承故障类型的准确判定,验证了该方法的有效性。

In order to extract fault features of bearings accurately,a method of parameter optimized VMD with a synthetic objective function composed of kurtosis criterion and envelope entropy was proposed.The genetic algorithm was used to search for the minimum value of the synthetic objective function so as to determine.The best combination of the number of modal components and the secondary penalty factor.The original fault signal was decomposed into several intrinsic mode function components by the parameter optimized VMD method,and the best signal component was selected and processed by an envelope demodulation algorithm,then the fault type of bearing was judged by the envelope spectrum of the modal component.Through analyzing the measured signals of fault bearings,it is shown that the proposed method can effectively distinguish the weak features of incipient fault signals from strong noises and achieve to judge the type of faults accurately.The effectiveness of proposed method is thus verified.