SVM与PSO相结合的电机轴承故障诊断  

Fault diagnosis of motor bearings based on SVM and PSO

作　　者：李嫄源 袁梅 王瑶 程安宇[1] 

机构地区：[1]重庆邮电大学自动化学院,重庆400065

出　　处：《重庆大学学报（自然科学版）》2018年第1期99-107,共9页Journal of Chongqing University

基　　金：重庆市科技人才培养计划资助项目(CSTC2013KJRC-TDJS40010)~~

摘　　要：针对电机轴承故障问题,提出一种基于支持向量机(SVM,support vector machine)与粒子群优化(PSO,particle swarm optimization)相结合的电机轴承故障诊断方法。结合振动信号的时域与小波包能量特征,使表征振动信号的特征具有较好的可靠性和敏感性,提高了故障的诊断准确率。采用PSO算法对SVM的惩罚参数和径向基核函数参数进行寻优,并与其它参数寻优算法进行比较分析。实验表明,研究提出的轴承故障诊断方法不仅对电机轴承的外圈故障、内圈故障和滚珠故障有很好的识别效果,而且还对每一类故障的严重程度有较好的区分,具有较强的实用性。A fault diagnosis method for motor bearings based on support vector machine（SVM）and particle swarm optimization（PSO）is proposed.The characteristic of the vibration signal is characterized by the time-domain and the wavelet packet energy characteristics,which makes the characteristic of the vibration signal has good reliability and sensitivity and improves the accuracy of fault diagnosis.The PSO algorithm is used to optimize the parameters of the penalty parameter and the radial basis kernel function of SVM,and compared with other parameter-optimization algorithms.Experimental results show that the proposed bearing fault diagnosis method has a very good effect not only on the recognition of motor bearing outer race fault,inner race fault and ball fault,but also on the severity differentiation of every kind of fault.It has strong practicability.

关 键 词：支持向量机 粒子群优化算法 小波包分析 特征提取 电机轴承 故障诊断 

分 类 号：TH165.3[机械工程—机械制造及自动化]