The development of neural network cepstrum method for bearing fault detection

A bearing diagnosis system that combines cepstrum coefficient method for feature extraction from bearing vibration signals and artificial neural network (ANN) models for the classification is proposed in this paper. We first segment the vibration signal and obtain the corresponding cepstrum coefficients, then classify the motor systems through ANN models. Utilizing the proposed method, one can identify the characteristics hiding inside the vibration signal and then diagnose the abnormalities. To evaluate this method, several experiments for the normal and abnormal conditions have been performed in the laboratory and the results are used to verify the method. It is shown that the proposed method had effectively distinguished the difference between the normal and abnormal cases and classified correctly the corresponding feature conditions.