Fault Diagnosis of the Motor Bearing Based on the Wavelet Package-Elman Neural Network

Based on the frequency domain characteristic of vibration signals of the ball bearings.The vibration signals were decomposed into different frequency bands through the method of wavelet package analysis.Energy of various frequency bands acting as the fault feature vector is input into the Elman neural network to realize the mapping between the feature vector and the fault mode since the Elman neural network has strong fault tolerance and better dynamic capability.The emluator results verified the effectiveness of the proposed methods in motor bearing fault diagnosis.