点击次数：

论文类型：会议论文

发表时间：2013-03-30

收录刊物：EI、CPCI-S、Scopus

卷号：694-697

页面范围：1160-1166

关键字：roller bearing; fault diagnosis; kurtosis; EMD; support vector machine

摘要：This paper presents a fault diagnosis method of roller bearings based on intrinsic mode function (IMF) kurtosis and support vector machine (SVM). In order to improve the performance of kurtosis under strong levels of background noise, the empirical mode decomposition (EMD) method is used to decompose the bearing vibration signals into a number of IMFs. The IMF kurtosis is then calculated because of its sensitivity of impulses caused by faults. Subsequently, the IMF kurtosis values are treated as fault feature vectors and input into SVM for fault classification. The experimental results show the effectiveness of the proposed approach in roller bearing fault diagnosis.