摘要
分别将集成经验模态分解(Ensemble Empirical Mode De-composition,EEMD)、经验小波变换(EmpiricalWaveletTransform,EWT)、排列熵(PermutationEntropy,PE)、支持向量机(Support Vector Machine,SVM)方法进行结合,形成了基于EEMD、PE、SVM的EEMDPS和基于EWT、PE、SVM的EWTPS这两种电机滚动轴承故障诊断方法。异步电机轴承的故障诊断实验表明:在相同实验条件下,两种方法对电机轴承的内圈单点故障、外圈单点故障和内外圈复合故障均可实现100%诊断,但EWTPS方法诊断时间更短;在电机轴承的滚动体-保持架复合故障和正常状态的诊断方面,EWTPS诊断方法具有更好的诊断效果。
In this paper,the Ensemble Empirical Mode De-composition(EEMD)and the Empirical Wavelet Transform(EWT)are combined with Permutation Entropy(PE)and Support Vector Machine(SVM),respectively,fault diagnosis methods for motor rolling bearings based on EEMDPS(based on EEMD,PE and SVM)and EWTPS(based on EWT,PE,and SVM)is formed.The fault diagnosis experiments of induction motor bearings(C&U 6201 RZ)show that both methods can realize 100%diagnosis of single fault of outer ring and compound fault of inner and outer ring of motor bearing,but the EWTPS method has shorter diagnostic time under the same experimental conditions.However,in terms of diagnosis of motor bearing inner ring single point fault,rolling cage compound fault and normal state,EWTPS has better diagnosis effect than EEMDPS.
作者
仇芝
顾磊
杜坚
刘雪梅
秦连升
Qiu Zhi;Gu Lei;Du Jian;Liu Xuemei;Qin Liansheng(College of Mechanical and Electrical Engineering,Southwest Petroleum University,610500,Chengdu,China;College of Automation,University of Electronic Science and Technology of China,611731,Chengdu,China)
出处
《应用力学学报》
CAS
CSCD
北大核心
2021年第2期721-729,共9页
Chinese Journal of Applied Mechanics
基金
四川省教育厅2016科研项目(16ZA0076)。
关键词
电机轴承故障
集成经验模态分解
经验小波变换
排列熵
支持向量机
motor bearing fault
ensemble empirical mode de-composition
empirical wavelet transform
permutation entropy
support vector machine