摘要
为提高电机轴承故障诊断的准确性,提出了一种基于极点对称模态分解算法(Extreme-point Symmetric Mode Decomposition,ESMD)熵融合与粒子群算法(PSO)优化支持向量机(SVM)的诊断方法。首先采用ESMD将故障数据分解获得数个固有模态分量(Intrinsic Mode Function,IMF),根据相关性筛选IMF并计算其多种特征熵;采用核主成分分析(KPCA)用于融合特征熵,增大区分度;利用PSO寻优SVM参数,提高故障识别率。最后通过试验分析表明,该方法可有效提取电机轴承故障特征并精确判别出故障类型,与其它方法相比识别率较高。
In order to improve the accuracy of motor bearing fault diagnosis,a diagnostic method based on Extreme-point Symmetric Mode Decomposition(ESMD)entropy fusion and Particle Swarm Optimization(PSO)optimization Support Vector Machine(SVM)is proposed.Firstly,ESMD is used to decompose the fault data to obtain several Intrinsic Mode Functions(IMF).The IMF is selected according to the correlation and its various feature entropy is calculated.The Kernel Principal Component Analysis(KPCA)is used to fuse the feature entropy and enlarge discrimination;PSO is used to optimize SVM parameters to improve fault recognition rate.Finally,the experimental analysis shows that the method can effectively extract the fault characteristics of the motor bearing and accurately determine the fault type.Compared with other methods,the recognition rate is higher.
作者
宿文才
张树团
刘涛
井超
SU Wencai;ZHANG Shutuan;LIU Tao;JING Chao(Navy Aviation University,Yantai 264001,China;The 92212th Unit of PLA,Qingdao 266109,China)
出处
《大电机技术》
2019年第5期24-28,共5页
Large Electric Machine and Hydraulic Turbine
基金
国家自然科学基金(51377168)
