基于多元经验模态分解互近似熵及GG聚类的轴承故障诊断

中国机械工程

基于多元经验模态分解互近似熵及GG聚类的轴承故障诊断

张淑清1;李威1;张立国1，2;胡永涛1;钱;磊1;姜万录1

1.燕山大学河北省测试计量技术与仪器重点实验室,秦皇岛,066004
2.河北省自动化研究所，石家庄，050000

出版日期:2016-12-25 发布日期:2016-12-28
基金资助:
国家自然科学基金资助项目(51475405，61077071)；河北省自然科学基金资助项目(F2015203413，F2015203392)；河北省高等学校科学技术研究重点资助项目(ZD2014100)；秦皇岛市科技计划资助项目（201502A043）
National Natural Science Foundation of China（No. 51475405，61077071）
Hebei Provincial Natural Science Foundation of China（No. F2015203413，F2015203392）

Bearing Fault Diagnosis Based on multi-EMD, cApEn and GG Clustering Algorithm

Zhang Shuqing1;Li Wei1;Zhang Liguo1，2;Hu Yongtao1;Qian Lei1;Jiang Wanlu1

1.Measurement Technology and Instrumentation Key Lab of Hebei Province，Yanshan University，Qinhuangdao，Hebei，066004
2.Automatic Research Institute of Hebei Province,Shijiazhuang,050000

Online:2016-12-25 Published:2016-12-28
Supported by:

National Natural Science Foundation of China（No. 51475405，61077071）
Hebei Provincial Natural Science Foundation of China（No. F2015203413，F2015203392）

摘要/Abstract

摘要： 提出了一种基于多元经验模态分解（Multi-EMD）、互近似熵和GG聚类的滚动故障轴承诊断方法。首先，将振动信号进行多元经验模态分解，得到若干个内禀模态函数（IMF）分量和一个趋势项。然后，将IMF分量分别与原始信号进行相关性分析，筛选出前7个含主要特征信息的IMF分量，并将筛选的IMF分量的互近似熵作为特征向量。最后，将特征向量输入到GG模糊分类器中进行聚类识别。通过聚类三维图，对两种算法机械运行的4种状态进行了对比，验证了多元经验模态分解方法不仅可解决采样的不均衡问题，而且可解决EMD算法聚类的混叠问题。

关键词: 轴承故障诊断, 多元经验模态分解, 互近似熵, GG聚类

Abstract: A new method for rolling bearing fault diagnosis was introduced based on the multi-EMD, cApEn and GG clustering algorithm. The rolling bearing vibration signals were decomposed first by multi-EMD to obtain several intrinsic mode function (IMF) components and a tendency item. Then the first seven IMF components involving the primary feature informations were chosen by the criteria of correlation with the original signals, and the cApEn entropies of each IMF component were composed eigenvectors. Finally, the constructed eigenvectors were put into GG classifier to recognize different fault types. The four kinds of operating states of the machine were presented by means of clustering three-dimensional graph, which instates that the unproportional sampling may be solved by the multi-EMD method and the cluster aliasing of EMD can be further solved.

Key words: bearing fault diagnosis, multivariate empirical mode decomposition(multi-EMD), cross approximate entropy(cApEn), Gath-Geva clustering

中图分类号:

TH17

张淑清1;李威1;张立国1，2;胡永涛1;钱;磊1;姜万录1. 基于多元经验模态分解互近似熵及GG聚类的轴承故障诊断[J]. 中国机械工程.

Zhang Shuqing1;Li Wei1;Zhang Liguo1，2;Hu Yongtao1;Qian Lei1;Jiang Wanlu1. Bearing Fault Diagnosis Based on multi-EMD, cApEn and GG Clustering Algorithm[J]. China Mechanical Engineering.

参考文献

[1]Looney D, Mandic D P. Multiscale Image Fusion Using Complex Extensions of EMD[J]. IEEE Transactions on Signal Processing, 2009,57(4):1626-1630. [2]Cui J, Freeden W. Equidistribution on the Sphere[J].SIAM Journal on Scientific Computing， 1997,18(2):595-609. [3]Rehman N, Mandic D P. Multivariate Empirical Mode Decomposition[J].Proceeding of the Royal Society A: Mathematical, Physical and Engineer-ing Science,2010,466:1291-1302. [4]刘霖雯，刘超，江成顺. EMD新算法及其应用[J]. 系统仿真学报，2007,19(2):446-447. Liu Linwen, Liu Chao, Jiang Chengshun. Novel EMD Algorithm and Its Application[J]. Journal of System Simulation, 2007,19(2):446-447. [5]时培明，丁雪娟，李庚，等. 一种EMD改进方法及其在旋转机械故障诊断中的应用[J].振动与冲击，2013,32(4):185-190. Shi Peiming, Ding Xuejuan, Li Geng, et al. An Improved Method of EMD and Its Applications in Rotation Machinery Fault Diagnosis[J].Journal of Viration and Shock, 2013,32(4):185-190. [6]黄建，胡晓光，巩玉楠.基于经验模态分解的高压短路器机械故障诊断方法[J]. 中国电机工程学报，2011,31(12):108-113. Huang Jian, Hu Xiaoguang, Gong Yunan. Machinery Fault Diagnosis of High Voltage Circuit Breaker Based on Empirical Mode Decomposition[J]. Proceedings of the CSEE，2011,31(12):108-113. [7]于德介，程军圣，杨宇. 基于EMD和AR 模型的滚动轴承故障诊断方法[J]. 振动工程学报，2004,17(3):332-335. Yu Dejie, Cheng Junsheng, Yang Yu. Rolling Bearing Fault Diagnosis Method Based on EMD and AR Model[J]. Journal of Viration and Shock，2004,17(3):332-335. [8]刘源，基于多元EMD的BCI信号处理研究[D].秦皇岛：燕山大学,2013. [9]张淑清，包红燕，李盼，等. 基于RQA与GG聚类的滚动轴承故障识别[J]. 中国机械工程,2015,26(10):1385-1390. Zhuang Shuqing,Bao Hongyan, Li Pan, et al. Fault Diagnosis of Rolling Bearing Based on RAQ and GG Clustering[J].China Mechanical Engineering,2015,26(10):1385-1390. [10]张立国，李盼，李梅梅，等. 基于ITD模糊熵和GG聚类的滚动轴承故障诊断[J]. 仪器仪表学报,2014(11):2624-2632. Zhang Liguo, Li Ban, Li Meimei, et al. Fault Diagnosis of Rolling Bearing Based on ITD Fuzzy Entropy and GG Clustering[J].Chinese Jounal of Scientific Instrument,2014(11):2624-2632. [11]洪波，唐庆玉，杨福生，等. 近似熵、互近似熵的性质、快速算法及其在脑电与认知研究中的初步应用[J]. 信号处理,1999(2):100-108. Hong Bo, Tang Qingyu, Yang Fusheng, et al. Study of EEG and Cognition on the Properties and Fast Algorithm of Mutual Approximate Entropy and Its Application[J]. Journal of Signal Processing,1999(2):100-108. [12]包红燕. 基于MEMD和条件熵相空间重构的滚动轴承故障诊断[D].秦皇岛：燕山大学,2014. [13]Henderson D W. Experiencing Geometry in Euclidean, Spherical, and Hyperbolic Spaces[M]. Upper Saddle River,New Jersey: Prentice Hall,1996. [14]Rilling G, Flandrin P, Gonalves P, et al. Bivariate Empirical Mode Decomposition[J]. Signal Processing Letters, IEEE, 2007,14(12):936-939.