A New Feature Extraction Method Based on EEMD and Multi-Scale Fuzzy Entropy for Motor Bearing

被引:183
|
作者
Zhao, Huimin [1 ,2 ,3 ,4 ,5 ]
Sun, Meng [1 ]
Deng, Wu [1 ,2 ,3 ,4 ,5 ]
Yang, Xinhua [1 ]
机构
[1] Dalian Jiaotong Univ, Software Inst, Dalian 116028, Peoples R China
[2] Sichuan Univ Sci & Engn, Sichuan Prov Key Lab Proc Equipment & Control, Zigong 64300, Peoples R China
[3] Southwest Jiaotong Univ, Tract Power State Key Lab, Chengdu 610031, Peoples R China
[4] Chongqing Univ, State Key Lab Mech Transmiss, Chongqing 400044, Peoples R China
[5] Dalian Jiaotong Univ, Dalian Key Lab Welded Struct & Its Intelligent Mf, Dalian 116028, Peoples R China
来源
ENTROPY | 2017年 / 19卷 / 01期
基金
中国国家自然科学基金;
关键词
feature extraction; motor bearing; ensemble empirical mode decomposition (EEMD); multi-scale fuzzy entropy; correlation coefficient method; SVM; fault diagnosis; SUPPORT VECTOR MACHINE; ROLLING ELEMENT BEARING; FAULT-FEATURE-EXTRACTION; PERMUTATION ENTROPY; WAVELET TRANSFORM; ROLLER-BEARINGS; APPROXIMATE ENTROPY; REDUCTION METHOD; EMD METHOD; DIAGNOSIS;
D O I
10.3390/e19010014
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Feature extraction is one of the most important, pivotal, and difficult problems in mechanical fault diagnosis, which directly relates to the accuracy of fault diagnosis and the reliability of early fault prediction. Therefore, a new fault feature extraction method, called the EDOMFE method based on integrating ensemble empirical mode decomposition (EEMD), mode selection, and multi-scale fuzzy entropy is proposed to accurately diagnose fault in this paper. The EEMD method is used to decompose the vibration signal into a series of intrinsic mode functions (IMFs) with a different physical significance. The correlation coefficient analysis method is used to calculate and determine three improved IMFs, which are close to the original signal. The multi-scale fuzzy entropy with the ability of effective distinguishing the complexity of different signals is used to calculate the entropy values of the selected three IMFs in order to form a feature vector with the complexity measure, which is regarded as the inputs of the support vector machine (SVM) model for training and constructing a SVM classifier (EOMSMFD based on EDOMFE and SVM) for fulfilling fault pattern recognition. Finally, the effectiveness of the proposed method is validated by real bearing vibration signals of the motor with different loads and fault severities. The experiment results show that the proposed EDOMFE method can effectively extract fault features from the vibration signal and that the proposed EOMSMFD method can accurately diagnose the fault types and fault severities for the inner race fault, the outer race fault, and rolling element fault of the motor bearing. Therefore, the proposed method provides a new fault diagnosis technology for rotating machinery.
引用
收藏
页数:21
相关论文
共 50 条
  • [31] A feature extraction method based on composite multi-scale permutation entropy and Laplacian score for shearer cutting state recognition
    Si, Lei
    Wang, Zhongbin
    Tan, Chao
    Liu, Xinhua
    MEASUREMENT, 2019, 145 : 84 - 93
  • [32] Feature extraction of cavitation noise based on CEEMDAN multi-scale improved permutation entropy and SVM
    Wu, Chenglong
    Gao, Hardin
    Zhu, Dandan
    Li, Ya'an
    Zhendong yu Chongji/Journal of Vibration and Shock, 2024, 43 (13): : 190 - 197
  • [33] Feature extraction of bearing faults based on adaptive weighted multi-scale combination morphological filtering
    Han X.
    Hu T.
    Yu J.
    Zhendong yu Chongji/Journal of Vibration and Shock, 2020, 39 (01): : 245 - 252
  • [34] Novel feature extraction method of pipeline signals based on multi-scale dispersion entropy partial mean of multi-modal component
    Zhou, Yina
    Lu, Jingyi
    Hu, Zhongrui
    Dong, Hongli
    Yan, Wendi
    Yang, Dandi
    MEASUREMENT, 2022, 205
  • [35] A new fault diagnosis approach for bearing based on multi-scale entropy of the optimized VMD
    Huang D.-R.
    Ke L.-Y.
    Lin M.-T.
    Sun G.-X.
    Kongzhi yu Juece/Control and Decision, 2020, 35 (07): : 1631 - 1638
  • [36] Rolling Bearing Fault Diagnosis Method based on EEMD Permutation Entropy and Fuzzy Clustering
    Han, Long
    Li, Chengwei
    Zhan, Liwei
    Li, Xiaoli
    2015 FIFTH INTERNATIONAL CONFERENCE ON INSTRUMENTATION AND MEASUREMENT, COMPUTER, COMMUNICATION AND CONTROL (IMCCC), 2015, : 469 - 473
  • [37] Application of EEMD and improved frequency band entropy in bearing fault feature extraction
    Li, Hua
    Liu, Tao
    Wu, Xing
    Chen, Qing
    ISA TRANSACTIONS, 2019, 88 : 170 - 185
  • [38] Research on the Multi-scale Fuzzy Entropy based on Index Energy
    Wei, Zhonglin
    Ma, Liyuan
    Cui, Xinhan
    PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS RESEARCH AND MECHATRONICS ENGINEERING, 2015, 121 : 2138 - 2143
  • [39] A rolling bearing fault diagnosis method based on multi-scale fuzzy entropy and variable predictive model-based class discrimination
    Zheng, Jinde
    Cheng, Junsheng
    Yang, Yu
    Luo, Songrong
    MECHANISM AND MACHINE THEORY, 2014, 78 : 187 - 200
  • [40] Application of Multi-scale Fuzzy Entropy for roller bearing fault detection and fault classification based on VPMCD
    Mehta, Priyanka
    Gaikwad, Jitendra A.
    Kulkarni, Jayant V.
    2016 IEEE INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ELECTRONICS, INFORMATION & COMMUNICATION TECHNOLOGY (RTEICT), 2016, : 256 - 261