基于广义复合多尺度排列熵与PCA的滚动轴承故障诊断方法  

Generalized composite multiscale permutation entropy and PCA based fault diagnosis of rolling bearings

作　　者：郑近德[1] 刘涛[1] 孟瑞[1] 刘庆运[1] ZHENG Jinde;LIU Tao;MENG Rui;LIU Qingyun(School of Mechanical Engineering,Anhui University of Technology,Ma’anshan 243032,China)

机构地区：[1]安徽工业大学机械工程学院,安徽马鞍山243032

出　　处：《振动与冲击》2018年第20期61-66,共6页Journal of Vibration and Shock

基　　金：国家自然科学基金(51505002);安徽省高校自然科学研究重点资助项目(KJ2015A080);国家重点研发计划(2017YFC0805100)

摘　　要：多尺度排列熵能够有效地反映滚动轴承振动信号的随机性变化和非线性动力学突变行为。针对其多尺度过程中粗粒化方式的不足,提出了广义复合多尺度排列熵(Generalized Composite Multiscale Permutation Entropy,GCMPE)。研究了参数对GCMPE计算的影响,并通过分析仿真数据将GCMPE与MPE进行了对比。将GCMPE应用于滚动轴承非线性故障特征的提取,提出一种基于GCMPE、主元分析和支持向量机的滚动轴承智能故障诊断方法。将提出的方法应用于实验数据分析,结果表明,所提方法能够有效地实现滚动轴承故障诊断,且故障识别率较高。Multiscale permutation entropy(MPE)can effectively extract the nonlinear dynamic fault feature from vibration signals of rolling bearings.Aiming at the problem of coarse-graining in MPE,a new nonlinear dynamic method called generalized composite multiscale permutation entropy(GCMPE)was proposed.GCMPE was compared with the MPE by analyzing simulation data and also the influence of parameters on GCMPE calculation was studied.Then GCMPE was applied to the extraction of nonlinear fault feature from vibration signal of rolling bearings and a new rolling bearing fault diagnosis method based on GCMPE,principal component analysis and support vector machine was presented.Finally,the proposed method was applied to analyze experimental data of rolling bearing and the results show that the proposed method can effectively realize the fault diagnosis of rolling bearings and has a higher fault recognition rate.

关 键 词：排列熵 多尺度排列熵 主分量分析 滚动轴承 故障诊断 

分 类 号：TH165.3[机械工程—机械制造及自动化] TN911.7[电子电信—通信与信息系统]