Motor Bearing Fault Diagnosis based on Hilbert-Huang transform and Convolutional Neural Networks

Abstract

Motor Bearing vibration signal contains its operating state information and can be used for bearing fault diagnosis. Facing the nonlinear and non-stationary signal of bearing vibration, the accuracy of existing methods still needs to be improved. In this paper, Hilbert-Huang transform is proposed to process these signals and obtain the time frequency spectrums. Then Convolutional neural network is applied to diagnose bearing faults for its perfect ability of image recognition. Comparing with other signal processing methods, this method achieves better accuracy.