Font Size: a A A

Research On Fault Diagnosis Method Of Rolling Bearing Based On Wavelet Packet And Support Vector Machine

Posted on:2019-05-13Degree:MasterType:Thesis
Country:ChinaCandidate:B QinFull Text:PDF
GTID:2518306470999389Subject:Ordnance Science and Technology
Abstract/Summary:PDF Full Text Request
Rolling bearings are the key components of many rotating machinery.The state monitoring and fault diagnosis of rolling bearings can effectively improve the maintainability and safety of the mechanical system and reduce the human and economic losses caused by the rolling bearing failure.A variety of rolling bearing failure can be diagnosed through the analysis of rolling bearing vibration signals.In this paper,the cause of rolling bearing failure,the method of feature extraction of vibration signal of rolling bearing and the fault diagnosis method are studied.Aiming at the feature extraction and feature selection of fault features based on wavelet packet decomposition,two methods of fault feature extraction based on wavelet packet decomposition are analyzed and studied.According to the collected vibration signal data of rolling bearing,wavelet packet decomposition is used to extract the energy features of the wavelet packet frequency band and the sample entropy of the wavelet packet frequency band respectively,and the support vector machine(SVM)is used to diagnose the rolling bearing fault.The applicability and influencing factors of two fault feature parameters are analyzed emphatically.The results show that the energy feature parameter based on wavelet packet is effective in the early fault diagnosis of rolling bearings,and the samples entropy feature parameter based on wavelet packet is more advantageous in the serious fault diagnosis.In order to further improve the accuracy and accuracy of SVM model in rolling bearing fault diagnosis,a fault diagnosis method of rolling bearing based on nonlinear inertia weighted particle swarm optimization algorithm and support vector machine(IPSO-SVM)is proposed.Based on the collected vibration signal data of rolling bearing,an improved Particle Swarm Optimization(IPSO)algorithm was used to optimize the SVM model parameters,and conduct fault diagnosis with the optimized SVM.Compared with PSO-SVM based on particle swarm optimization and GA-SVM based on genetic algorithm,the fault diagnosis method based on IPSO-SVM proposed in this paper is more effective,which improves the efficiency and accuracy of fault diagnosis of rolling bearing.
Keywords/Search Tags:Rolling bearing, Fault diagnosis, Wavelet packet decomposition, Support vector machine, Improved particle swarm optimization
PDF Full Text Request
Related items