基于优化VMD与BP神经网络结合的滚动轴承故障诊断方法研究

Rolling Bearing Fault Diagnosis Method Based on Optimized VMD and BP Neural Network

为解决滚动轴承微弱故障信号不明显、识别故障类型准确率不高及变分模态分解(VMD)分解时参数主要依靠人为设定的问题,提出一种基于麻雀搜索算法(SSA)优化VMD参数与BP神经网络相结合的故障诊断方法。首先,使用麻雀搜索算法对VMD分解的模态分解个数及惩罚因子进行优化,搜索全局得出最优参数组合;利用优化后的参数对故障信号进行VMD分解,将分解后的本征模态分量导入BP神经网络进行模式识别。结果表明:与EMD、未优化VMD相比,优化参数后的VMD具有更高的故障诊断率99.53%,使故障诊断效果进一步提升。

In order to solve the problems that the weak fault signal of rolling bearings is not obvious,the accuracy of identifying fault types is not high,and the parameters of variational mode decomposition(VMD)decomposition mainly rely on artificial settings,a troubleshooting method was proposed,in which Sparrow Search Algorithm(SSA)is adopted to optimize VMD parameters by integrating BP neural networks.Firstly,the sparrow search algorithm is used to optimize the number of modal decompositions and penalty factors of VMD decomposition,and the optimal parameter combination is obtained by global search.The optimized parameters are used to decompose the fault signal by VMD,and the decomposed eigenmode components are introduced into the BP neural network for pattern recognition.The results show that compared with EMD and unoptimized VMD,the optimized VMD has a higher fault diagnosis rate of 99.53%,which further improves the fault diagnosis effect.