EMD based fault diagnosis for the sliding bearings with measurement noise

Empirical Mode Decomposition (EMD) is a decomposition algorithm which is used to analyze signal. In this paper, a new fault diagnosis approach, which is the EMD based on the optimization of noise reduction, is proposed for bearings. Firstly, the original signal is decomposed into a set of Intrinsic Mode Functions (IMFs) by EMD combined with Genetic Algorithm (GA) for reconstruction. Then effective IMFs are selected as characteristics by sample entropy, which are trained and classified by Support Vector Machine (SVM) to make fault diagnosis. Finally, an experiment is carried out to verify the efficiency of the proposed method.