基于 SVD-VMD 和 SVM 滚动轴承故障诊断方法

针对故障滚动轴承振动信号中含有干扰信号，难以准确提取出故障信息，提出了一种基于奇异值分解(SVD)、变分模态分解(VMD)、和支持向量机(SVM)的滚动轴承故障诊断方法。首先利用奇异值分解对信号进行处理，根据奇异值峰度差分谱来确定分解后重构矩阵的有效阶数，然后根据该有效阶数重构信号，对重构后的信号进行VMD分解，根据上述有效阶数确定分解的本征模态函数(IMF)分量的个数，从分解后的IMF分量中提取故障特征参数，将其作为支持向量机的输入参数进行故障诊断。最后采用合肥工业大学轴承试验机进行验证，并与直接进VMD分解及基于带通滤波器信号去噪的故障诊断方法进行对比，结果表明该方法能有效识别滚动轴承的故障类型，可用于滚动轴承故障诊断。

Rolling bearing fault diagnosis method based on SVD-VMD and SVM

Vibration signals of fault rolling bearings contain interference signals, which makes it difficult to extract fault informationaccurately. In this paper, a fault diagnosis method for fault rolling bearings was proposed based on singular value decomposition (SVD),variational mode decomposition ( VMD) and support vector machine ( SVM). First, the singular value decomposition was used toprocess the signal, and the effective order of the reconstructed matrix was determined according to the kurtosis difference spectrum of thesingular value. Then, the reconstructed signal was reconstructed according to the effective order, and the VMD decomposition wasperformed on the reconstructed signal. The number of the decomposed intrinsic mode function ( IMF) components was determinedaccording to the above effective order. From the IMF component of the decomposed to extract the fault characteristic parameters, as theinput parameters of support vector machine ( SVM) to fault diagnosis. Finally validated bearing tester adopts Hefei university oftechnology, and directly into the decomposition of VMD and band-pass filter signal denoising based fault diagnosis method is compared,the results show that the method can effectively identify roller bearing fault type and can also be used for rolling bearing fault diagnosis.