A New Robust Rolling Bearing Vibration Signal Analysis Method

As bearing vibration signal is of nonlinear and nonstationary characteristics, and the condition-indicating information distributed in the rolling bearing vibration signal is complicated, a new rolling bearing health status estimation approach using holder coefficient and gray relation algorithm was proposed based on bearing vibration signal in the paper. Firstly, the holder coefficient algorithm was proposed for extracting health status feature vectors based on the bearing vibration signals, and secondly the gray relation algorithm was developed for achieving bearing fault pattern recognition intelligently using the extracted feature vectors. At last, the experimental study has illustrated the proposed approach can efficiently and effectively recognize different fault types and in addition different severities with good real-time performance.