Rolling Bearing Fault Degree Recognition Based on Ensemble Empirical Mode Decomposition and Support Vector Regression
The research in bearing fault diagnosis has been attracting great attention in the past decades.Development of feasible fault diagnosis procedures to prevent failures that could cause huge economic loss timely is necessary.Bearing faults with different degrees differ from each other in the aspects of signal amplitudes,impact intervals,etc.Besides,the whole life of the bearing is also a developing process for some sensitive features related to the fault trend.Much work in machine fault diagnosis ignores this point and focuses on the decision of fault existence.Hence,to investigate the fault degree is of great meaning for timely maintenance action.In this paper,a new scheme based on ensemble empirical mode decomposition (EEMD) and support vector regression (SVR) to conduct bearing fault degree recognition is proposed.This analysis first extracts the sensitive features from the intrinsic mode functions (IMFs) produced by EEMD which is a potential time-frequency analysis method,and then constructs an intelligent nonlinear model with input feature vectors extracted from the IMFs and defect size as output.Through validation of experimental data,the results indicated that the bearing fault degree could be effectively and precisely recognized.
fault degree recognition ensemble empirical mode decomposition time-frequency analysis support vector regression
H. Y. Liu C.Q. Shen Z.K. Zhu W.G. Huang
School of Urban Rail Transportation Soochow University Suzhou 215006,China
国际会议
南京
英文
1-5
2013-08-20（万方平台首次上网日期，不代表论文的发表时间）