Research on Fault Diagnosis Method for Rolling Bearings Based on Time Frequency Domain Features and Naive Bayes
[Purposes]In order to solve the problems of difficult feature extraction and low diagnostic per-formance of rolling bearings,a fault diagnosis method based on time-frequency domain features and na-ive Bayes is proposed.[Methods]This method first processes the original vibration signal through local mean decomposition to obtain multiple product function(PF)components.Secondly,based on the origi-nal vibration signal and various PF components,time-frequency domain features are extracted,and prin-cipal component analysis is used to achieve feature dimension reduction,obtaining low dimensional sen-sitive features.Finally,based on the low dimensional sensitive feature set and combined with the naive Bayesian model,the analysis of the rolling bearing dataset from Jiangnan University School of Mechani-cal Engineering is achieved.[Findings]The experimental results show that the accuracy of this method is 39.49%higher than that of traditional naive Bayes,and 5.94%higher than that of principal component analysis.Therefore,it can be concluded that this method performs well in diagnosing rolling bearing faults.[Conclusions]Compared to traditional single fault diagnosis models,fault diagnosis models based on time-frequency domain features and naive Bayes have higher accuracy and solve the problems of diffi-cult feature extraction and low diagnostic performance in rolling bearing faults.
rolling bearingstime-frequency domain featureslocal mean decompositionprincipal com-ponent analysisnaive bayes
NETL
NSTL
万方数据
