Bearing Fault Diagnosis Based On Improved Cepstrum

Abstract

Jian Wang and Yongjian Sun

Rolling bearing is widely used in various mechanical equipment, which affects the performance and safety of the equipment. In order to ensure the normal operation of the equipment, a new method based on improved cepstrum for bearing fault diagnosis is proposed. In the cepstrum peaks, the largest four peaks are extracted, then the four peaks are improved to complete the feature extraction of bearing fault. Simulation experiment was carried out to verify the accuracy of the proposed method. The experimental results show that the accuracy is up to 92.44%, which has achieved high accuracy.

PDF