Research on rolling element bearing fault diagnosis based on genetic algorithm matching pursuit

6th Global Conference on Materials Science and Engineering

Rong, R.W.^1 ; Ming, T.F.^2

Department of Technology Information, Hubei Police University, Wu Han

430034, China^1

College of Power Engineering, Naval University of Engineering, Wu Han

430033, China^2

关键词: Algorithm matching;    Computation speed;    Matching pursuit algorithms;    Rolling bearings;    Rolling Element Bearing;    Searching speed;    Time-frequency analysis methods;    Time-frequency localization;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/283/1/012009/pdf
DOI  :  10.1088/1757-899X/283/1/012009

来源: IOP

【 摘 要 】

In order to solve the problem of slow computation speed, matching pursuit algorithm is applied to rolling bearing fault diagnosis, and the improvement are conducted from two aspects that are the construction of dictionary and the way to search for atoms. To be specific, Gabor function which can reflect time-frequency localization characteristic well is used to construct the dictionary, and the genetic algorithm to improve the searching speed. A time-frequency analysis method based on genetic algorithm matching pursuit (GAMP) algorithm is proposed. The way to set property parameters for the improvement of the decomposition results is studied. Simulation and experimental results illustrate that the weak fault feature of rolling bearing can be extracted effectively by this proposed method, at the same time, the computation speed increases obviously.