多尺度排列熵及其在滚动轴承故障诊断中的应用

中国机械工程 ›› 2013, Vol. 24 ›› Issue (19): 2641-2646.

多尺度排列熵及其在滚动轴承故障诊断中的应用

郑近德;程军圣;杨宇

湖南大学汽车车身先进设计制造国家重点实验室，长沙，410082

出版日期:2013-10-10 发布日期:2013-10-11
基金资助:
国家自然科学基金资助项目（51075131）；湖南省自然科学基金资助项目（11JJ2026）；中央高校基本科研业务费专项基金资助项目
National Natural Science Foundation of China（No. 51075131）;

Hunan Provincial Natural Science Foundation of China（No. 11JJ2026）;
Fundamental Research Funds for the Central Universities

Multi-scale Permutation Entropy and Its Applications to Rolling Bearing Fault Diagnosis

Zheng Jinde;Cheng Junsheng;Yang Yu

State Key Laboratory of Advanced Design and Manufacture for Vehicle Body,Hunan University,Changsha,410082

Online:2013-10-10 Published:2013-10-11
Supported by:

National Natural Science Foundation of China（No. 51075131）;

Hunan Provincial Natural Science Foundation of China（No. 11JJ2026）;
Fundamental Research Funds for the Central Universities

摘要/Abstract

摘要：

引入多尺度排列熵（MPE）的概念，用来检测振动信号不同尺度下的动力学突变行为，并将其应用于机械故障诊断中滚动轴承故障特征的提取，结合支持向量机(SVM)，提出了一种基于MPE和SVM的滚动轴承故障诊断方法，将新提出的滚动轴承故障诊断方法应用于实验数据分析，并通过与BP神经网络对比，结果表明，该方法能够有效地提取故障特征，实现故障类型的诊断。

关键词: 排列熵, 多尺度排列熵, 滚动轴承, 故障诊断, 支持向量机

Abstract:

A definition of MPE was presented to extract the fault characteristics of dynamics changes from bearing vibration signals. And in combination with SVM, a bearing fault diagnosis approach was put forward based on MPE and SVM.Firstly the algorithms of PE and MPE were introduced. Then experimental data were used to demonstrate the validity of the approach. Also for comparision with SVM, the BP neural network was used and the analysis results indicate that the proposed approach can extract the fault feature and identify the fault categories effectively.

Key words: permutation entropy(PE), multi-scale permutation entropy(MPE), rolling bearing, fault diagnosis, support vector machine(SVM)

中图分类号:

郑近德;程军圣;杨宇. 多尺度排列熵及其在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2013, 24(19): 2641-2646.

Zheng Jinde;Cheng Junsheng;Yang Yu. Multi-scale Permutation Entropy and Its Applications to Rolling Bearing Fault Diagnosis[J]. China Mechanical Engineering, 2013, 24(19): 2641-2646.

参考文献

[1]于德介,程军圣,杨宇.机械故障诊断的Hilbert-Huang变换方法[M].北京:科学出版社,2007.
[2]何正嘉.机械故障诊断理论及应用[M].北京:高等教育出版社,2010.
[3]程军圣,于德介,邓乾旺,杨宇.连续小波变换在滚动轴承故障诊断中的应用[J].中国机械工程,2003,14(23):2037-2040.
[4]Huang N E, Wu Z. A Review on Hilbert-Huang Transform: Method and Its Applications to Geo- physical Studies [J]. Advances in Adaptive Data Analysis, 2009, 1: 1-23.
[5]Yu Dejie, Cheng Junsheng, Yang Yu. Application of EMD Method and Hilbert Spectrum to the Fault Diagnosis of Roller Bearings[J]. Mechanical Sys- tems and Signal Processing, 2005, 19:259-270.
[6]Yan Ruqiang, Liu Yongbin, Gao R X. Permutation Entropy: A Nonlinear Statistical Measure for Status Characterization of Rotary Machines[J]. Mechani- cal Systems and Signal Processing, 2012, 29 : 474- 484.
[7]徐玉秀 [1],钟建军 [2],闻邦椿 [3].旋转机械动态特性的分形特征及故障诊断[J].机械工程学报,2005,41(12):186-189.
[8]Yan Ruqiang, Gao R X. Approximate Entropy as a Diagnostic Tool for Machine Health Monitoring[J]. Mech. Syst. Signal Process, 2007,21:824-839.
[9]Zhang Long, Xiong Guoliang, Liu Hesheng. Bear- ing Fault Diagnosis Using Multi-scale Entropy and Adaptive Neuro- fuzzy Inference[J]. Expert Sys- tems with Applications, 2010, 37:6077-6085.
[10]Richman J S, Moorman J R. Physiological Time- series Analysis Using Approximate Entropy and Sample Entropy[J]. American Journal of Physiol- ogy- Heart and Circulatory Physiology, 2000, 278 :2039-2049.
[11]Costa M, Goldberger A L, Peng C K. Multiscale Entropy Analysis of Physiologic Time Series[J]. Physical Review Letters, The American Physio- logical Society, 2002 : 068102 (1-4).
[12]Bandt C, Pompe B. Permutation Entropy: a Natu- ral Complexity Measure for Time Series[J]. Phys- ical Review Letters, The American Physiological Society, 2002:174102(1-4).
[13]袁明[1],罗志增[1].基于排列组合熵的表面肌电信号特征分析[J].杭州电子科技大学学报,2012,32(1):64-67.
[14]马千里[1],卞春华[2].改进排列熵方法及其在心率变异复杂度分析中的应用[J].中国组织工程研究与临床康复,2010,14(52):9781-9785.
[15]侯威[1,2],封国林[2,3],董文杰[2,3],李建平[4].利用排列熵检测近40年华北地区气温突变的研究[J].物理学报,2006,55(5):2663-2668.
[16]Aziz W, Arif M. Multiscale Permutation Entropy of Physiological Time Series[C]//Proceeding of IEEE International Multi- topic Conference, IN- MIC, 2005.
[17]李岳[1],陶利民[1],温熙森[1].用于滚动轴承故障检测与分类的支持向量机方法[J].中国机械工程,2005,16(6):498-501.
[18]Yang Yu, Yu Dejie, Cheng Junsheng. A Fault Di- agnosis Approach for Roller Bearing Based on IMF Envelope Spectrum and SVM[J]. Measurement, 2007,40:943-950.
[19]李永强 [1],刘杰 [2],侯祥林 [2],李允公 [2].人工神经网络的混合算法及其工程应用[J].机械工程学报,2004,40(1):127-130.
[20]飞思科技产品研发中心．神经网络理论与MAT-LAB7实现[M]．北京：电子工业出版社，2005．