An intelligent fault diagnosis of rolling bearing based on EMD and correlation analysis

A feature extraction method using joint empirical mode decomposition (EMD) and correlation analysis is proposed. The vibration signal of a rolling bearing is decomposed into a number of IMF (Intrinsic Mode Function) components by using EMD method, after adopting large numbers of correlation analysis of the IMF components and vibration signal is decomposed, we found that the correlation coefficients between IMF and vibration signal is decomposed have great differences under different state, and can be regarded as the feature vectors of the bearing. Finally, the running state of bearing is recognized and classified by using support vector machine (SVM) classifier. The simulation result shows the effectiveness and feasibility of the proposed approach for recognizing the state of rolling bearing.