FAULT DIAGNOSIS METHOD OF ROLLING BEARING BASED ON EEMD-CNN

In order to improve the rolling bearing fault diagnosis accuracy,this paper presents a fault diagnosis method based on Ensemble Empirical Mode Decomposition（ EEMD） and Convolution Neural Networks（ CNN）. At first,using the EEMD decompose the signal. After that,choose appropriate IMFs according to the correlation coefficent and kurtosis calculating results to reconstruct the signal. After calculating a series of indexes of reconstructed signals,using CNN and various methods to diagnose faults. The results shows that the method used in this paper can effectively carry out fault diagnosis. The accuracy can reach 96. 7%. It has certain application significance to fault diagnosis.