Bearing Fault Signals Analysis Based on Alpha-Stable Distribution
Guo Weigong;Zhou Hongtao;Tan Xuexiang;School of Mechanical Engineering, University of Shanghai for Science and Technology;
A new bearing fault signals analysis is proposed based on Alpha-stable distribution. Such a non-Gaussian model can describe the characteristics of bearing fault signals with impulsive behavior. The characteristic exponent for different fault degrees is estimated by a stable distribution parameter estimation method. Estimation result suggests that the bearing fault signals belongs to the Alpha-stable process. The Alpha-stable densities of every bearing fault signal fit well with the empirical probability density in log-log plots, and their tails possess the same heavy tail behavior. This validates the statistical model for different fault degree bearing signals.