|
|
|
| Feature extraction of mechanical fault diagnosis based on MPE-LLTSA |
| ZHAO Jiangang1, NING Jing1,2, NING Yunzhi1, CHEN Chunjun1, LI Yanping1 |
1. School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China;
2. Sichuan Provincial Key Lab of Rail Transit Operation and Maintenance Technology and Equipment, Chengdu 610031, China |
|
|
|
|
Abstract A large number of signals collected by mechanical equipment monitoring system are usually nonlinear signals with multiple natural oscillation modes, so the single-scale feature extraction can’t characterize these nonlinear signals. For high dimensional feature matrix, its main lower dimensional features need to be further extracted. Here, to solve these two problems, a nonlinear feature extraction method combining multiscale permutation entropy and linear local tangent space alignment (MPE-LLTSA) was proposed. Firstly, signals were calculated using MPE to obtain multi-scale features with high dimensions. Then, LLTSA was used to excavate the embedded intrinsic structure, and realize low dimensional feature extraction. Finally, least squares support vector machine (LSSVM) was introduced to train and recognize low dimensional features. The test results showed that the proposed method has application potential in fields of mechanical pattern classification and fault recognition.
|
|
Received: 18 December 2019
Published: 15 July 2021
|
|
|
|
［1］KANKAR P K, SHARMA S C, HARSHA S P. Fault diagnosis of ball bearings using machine learning methods［J］. Expert Systems with Applications, 2011,36: 1876-1886.
［2］YAN R, GAO R X. Approximate entropy as a diagnostic tool for machine health monitoring［J］. Mechanical Systems and Signal Processing, 2007,21: 824-839.
［3］RICHMAN J S, MOORMAN J R. Physiological time-series analysis using approximate entropy and sample entropy［J］. American Journal of Physiology-Heart and Circulatory Physiology, 2000,278:2039-2049.
［4］COSTA M, GOLDBERGER A L, PENG C K. Multiscale entropy analysis of complex physiologic time series［J］. Physical Review Letters, 2002,92: 068102.
［5］HE Q B. Time-frequency manifold for nonlinear feature extraction in machinery fault diagnosis［J］. Mechanical Systems and Signal Processing, 2013,35: 200-218.
［6］BANDT C, POMPE B. Permutation entropy: a natural complexity measure for time series［J］. Physical Review Letters, 2002,88:174102.
［7］TIAN Y, WANG Z L, LU C. Self-adaptive bearing fault diagnosis based on permutation entropy and manifold-based dynamic time warping［J］. Mechanical Systems and Signal Processing, 2019,114:658-673.
［8］YAN R Q, LIU Y B, GAO R X. Permutation entropy: a nonlinear statistical measure for status characterization of rotary machines［J］. Mechanical Systems and Signal Processing, 2012, 49: 474-484.
［9］JIA F, LEI Y G, LIN J, et al. Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data［J］. Mechanical Systems and Signal Processing, 2016,72/73: 303-315.
［10］WORDEN K, STASZEWSKI W J, HENSMAN J J. Natural computing for mechanical systems research: a tutorial overview［J］. Mechanical Systems and Signal Processing, 2011,25: 4-111.
［11］ZHANG L, XIONG G L, LIU H S. Bearing fault diagnosis using multi-scale entropy and adaptive neuro-fuzzy inference［J］. Expert Systems with Applications, 2010,37: 6077-6085.
［12］AZIZ W, ARIF M. Multiscale permutation entropy of physiological time series［C］∥9th International Multitopic Conference. Karachi, Pakistan, 2005.
［13］WU S D, WU P H, WU C W, et al. Bearing fault diagnosis based on multiscale permutation entropy and support vector machine［J］. Entropy, 2012,14: 1343-1356.
［14］LI F, TANG B P, YANG R S. Rotating machine fault diagnosis using dimension reduction with linear local tangent space alignment［J］.Measurement,2013,46:2525-2539.
［15］PINHEIRO E, POSTOLACHE O, GIRO P. Empirical mode decomposition and principal component analysis implementation in processing non-invasive cardiovascular signals［J］. Measurement, 2012,45: 175-181.
［16］JIANG Q S, JIA M P, HU J Z, et al. Machinery fault diagnosis using supervised manifold learning［J］. Mechanical Systems and Signal Processing, 2009,23: 2301-2311.
［17］HUANG Y X, ZHANG X F, LEE J, et al. Discriminant diffusion maps analysis: a robust manifold learner for dimensionality reduction and its applications in machine condition monitoring and fault diagnosis［J］. Mechanical Systems and Signal Processing, 2013,34: 277-297.
［18］ZHANG T H, YANG J, ZHAO D L, et al. Linear local tangent space alignment and application to face recognition［J］. Neurocomputing, 2007,70: 1547-1553.
［19］丁吉,姜涛,蒋宁.基于悬臂梁振动的主动控制技术研究［J］.长春工业大学学报(自然科学版),2007(3):312-315.
DING Ji, JIANG Tao, JIANG Ning. Research on active control technology based on vibration of cantilever beam ［J］. Journal of Changchun University (Natural Science Edition),2007(3):312-315.
［20］孙自强,陈长征,孟强,等.基于小波分形理论的风电轴承故障识别［J］.沈阳工业大学学报,2014,36(6):666-670.
SUN Ziqiang, CHEN Changzheng, MENG Qiang, et al. Wind power bearing fault identification based on wavelet fractal theory［J］. Journal of Shenyang University of Technology, 2014,36(6):666-670.
［21］向丹,葛爽.基于EMD样本熵-LLTSA的故障特征提取方法［J］.航空动力学报,2014,29(7):1535-1542.
XIANG Dan, GE Shuang. Fault feature extraction method based on EMD sample entropy-LLTSA ［J］. Journal of Aerospace Power, 2014,29(7):1535-1542.
［22］苏祖强,汤宝平,姚金宝.基于敏感特征选择与流形学习维数约简的故障诊断［J］.振动与冲击,2014,33(3):70-75.
SU Zuqiang, TANG Baoping, YAO Jinbao. Fault diagnosis based on sensitive feature selection and manifold learning dimension reduction ［J］. Journal of Vibration and Shock, 2014,33(3):70-75.
［23］熊庆,张卫华.基于MF-DFA与PSO优化LSSVM的滚动轴承故障诊断方法［J］.振动与冲击,2015,34(11):188-193.
XIONG Qing, ZHANG Weihua. Rolling bearing fault diagnosis method based on MF-DFA and PSO optimized LSSVM ［J］. Journal of Vibration and Shock, 2015,34(11):188-193.
［24］李永健,宋浩,刘吉华,等.基于改进多尺度排列熵的列车轴箱轴承诊断方法研究［J］.铁道学报,2020,42(1):33-39.
LI Yongjian, SONG Hao, LIU Jihua,et al. Research on diagnosis method of train axle box bearing based on improved multi scale permutation entropy ［J］. Journal of the China Railway Society, 2020,42(1):33-39.
［25］ZHENG J D, PAN H Y, YANG S B, et al. Generalized composite multiscale permutation entropy and Laplacian score based rolling bearing fault diagnosis［J］. Mechanical Systems and Signal Processing, 2018,99: 229-243.
［26］TENENBAUM J B. A global geometric framework for nonlinear dimensionality reduction［J］. Science, 2000,
290: 2319-2323.
［27］ZHANG T, YANG J, ZHAO D, et al. Linear local tangent space alignment and application to face recognition［J］. Neurocomputing, 2007,70: 1547-1553.
［28］TENENBAUM J B. A global geometric framework for nonlinear dimensionality reduction［J］. Science, 2000,290: 2319-2323.
［29］ROWEIS S T. Nonlinear dimensionality reduction by locally linear embedding［J］. Science, 2000,290: 2323-2326.
［30］QIN G F, LU X J. Integration of weighted LS-SVM and manifold learning for fuzzy modeling［J］. Neurocomputing, 2018,282: 184-191.
［31］GUO Y L, KAREEM A. System identification through nonstationary data using time-frequency blind source separation［J］. Journal of Sound and Vibration, 2016,371: 110-131.
［32］LEI Y G, HE Y J, ZI Y Y. Application of the EEMD method to rotor fault diagnosis of rotating machinery［J］. Mechanical Systems and Signal Processing, 2009,23: 1327-1338.
［33］Bearing Data Center, Case Western Reserve University［J/OL］. http://csegroups.case.edu/bearingdatacenter/pages/download-data-file.
|
|
|
|
