Abstract:In order to accurately extract the nonlinear fault features from mechanical vibration signal, a novel method for complexity measuring termed Multiscale Time Irreversibility (MSTI) was proposed. Meanwhile,combining with t-Distributed Stochastic Neighbor Embedding (t-SNE) and Particle Swarm Optimization-Support Vector Machine (PSO-SVM), a new fault diagnosis method for rolling bearings was proposed. Firstly, the MSTI is used to extract the characteristic information from the complex vibration signal. Secondly, t-SNE is used to reduce the high dimension of features. Then the selected low dimensional features are input to the PSO-SVM based multiple fault classifier for fault diagnosis. Finally, the proposedmethodwas applied to the experiment data analysis and was compared with the existing methods. Simulation and experimental results show that the proposed method can effectively diagnose the working status and fault types of rolling bearings and is superior to the existing methods.
姜战伟,郑近德,潘海洋,潘紫微. 基于多尺度时不可逆与t-SNE流形学习的滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(17): 61-68.
JIANG Zhan-wei,ZHENG Jin-de,PAN Hai-yang,PAN Zi-wei. Rolling bearing fault diagnosis method based on multiscale time irreversibility and t-SNE manifold learning. JOURNAL OF VIBRATION AND SHOCK, 2017, 36(17): 61-68.
[1] Pincus S M. Assessing Serial Irregularity and Its Implications for Health [J]. Annals of the New York Academy of Sciences, 2001, 954(1):245–267.
[2] Cui B Z, Pan H X, Wang Z B. Fault Diagnosis of Roller Bearings Base on the Local Wave and Approximate Entropy [J]. Journal of North University of China (Natural Science Edition), 2012, 33(5):552-558.
[3] 何志坚, 周志雄. 基于ELMD的样本熵及Boosting-SVM的滚动轴承故障诊断[J]. 振动与冲击, 2016, 35(18).
HE Zhijian, ZHOU Zhixiong. Fault diagnosis of roller bearings based on ELMD sample entropy and Boosting-SVM [J].Journal of Vibration and Shock, 2016, 35(18).
[4] Zhu K. Fault Diagnosis of Rolling Bearings Based on IMF Envelope Sample Entropy and Support Vector Machine [J]. Journal of Information & Computational Science, 2013, 10(16):5189-5198.
[5] Bandt C, Pompe B. Permutation entropy: a natural complexity measure for time series [J]. Physical Review Letters, 2002, 88(17):174102.
[6] 郝旺身, 王洪明, 董辛,等. 基于全矢排列熵的齿轮故障特征提取方法研究[J]. 振动与冲击, 2016, 35(11):224-228.
HAO Wangshen, WANG Hongming, DONG Xin, et.al. Gear fault feature extraction based on full vector permutation entropy [J].Journal of Vibration and Shock, 2016, 35(11):224-228.
[7] Chen W, Wang Z, Xie H, et al. Characterization of surface EMG signal based on fuzzy entropy [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2007, 15(2): 266-272.
[8] 舒思材, 韩东. 基于多尺度最优模糊熵的液压泵特征提取方法研究[J]. 振动与冲击, 2016, 35(9):184-189.
SHU Sicai, HAN Dong. Approach for a hydraulic pump's feature extraction based on multiscale optimal fuzzy entropy. [J].Journal of Vibration and Shock, 2016, 35(9):184-189.
[9] Zheng J, Cheng J, Yang Y. A rolling bearing fault diagnosis approach based on LCD and fuzzy entropy [J]. Mechanism & Machine Theory, 2013, 70(6):441-453.
[10] Costa M, Goldberger A L, Peng C K. Multiscale entropy analysis of biological signals [J]. Physical Review E Statistical Nonlinear & Soft Matter Physics, 2005, 71(1):021906-021906.
[11] Costa M D, Peng C K, Goldberger A L. Multiscale analysis of heart rate dynamics: entropy and time irreversibility measures [J]. Cardiovascular Engineering, 2008, 8(2): 88-93.
[12] Costa M, Goldberger A L, Peng C K. Broken asymmetry of the human heartbeat: loss of time irreversibility in aging and disease [J]. Physical review letters, 2005, 95(19): 198102.
[13] Van der Heyden M J, Diks C, Pijn J P M, et al. Time reversibility of intracranial human EEG recordings in mesial temporal lobe epilepsy[J]. Physics Letters A, 1996, 216(6): 283-288.
[14] Porta A, Guzzetti S, Montano N, et al. Time reversibility in short-term heart period variability[C]//2006 Computers in Cardiology. IEEE, 2006: 77-80.
[15] Cox D R, Gudmundsson G, Lindgren G, et al. Statistical analysis of time series: Some recent developments [with discussion and reply] [J]. Scandinavian Journal of Statistics, 1981: 93-115.
[16] Diks C, Van Houwelingen J C, Takens F, et al. Reversibility as a criterion for discriminating time series [J]. Physics Letters A, 1995, 201(2): 221-228.
[17] Casali K R, Casali A G, Montano N, et al. Multiple testing strategy for the detection of temporal irreversibility in stationary time series [J]. Physical Review E, 2008, 77(6): 066204.
[18] Prigogine I, Antoniou I. Laws of nature and time symmetry breaking [J]. Annals of the New York Academy of Sciences, 1999, 879(1): 8-28.
[19] Porta A, Casali K R, Casali A G, et al. Temporal asymmetries of short-term heart period variability are linked to autonomic regulation [J]. Ajp Regulatory Integrative & Comparative Physiology, 2008, 295(2):R550-7.
[20] Porta A, Guzzetti S, Montano N, et al. Time reversibility in short-term heart period variability[C]// Computers in Cardiology. 2006:77 - 80.
[21] Guzik P, Piskorski J, Krauze T, et al. Heart rate asymmetry byPoincaré plots of RR intervals [J]. Biomedizinische Technik Biomedical Engineering, 2006, 51(4):272-5.
[22] Kramer O, Luckehe D. Visualization of evolutionary runs with isometric mapping[C]// Evolutionary Computation. IEEE, 2015.
[23] Dybowski R, Collins T D, Hall W, et al. Visualization of Binary String Convergence by Sammon Mapping [J]. First Student Workshop of the Psychology of Programming Interest Group, 1996.
[24] Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding [J]. Science, 2000, 290(5500):2323-6.
[25] Laurens V D M, Hinton G. Visualizing Data using t-SNE [J]. Journal of Machine Learning Research, 2008, 9(2605):2579-2605.
[26] Hinton G E. Visualizing High-Dimensional Data Using t-SNE [J]. Vigiliae Christianae, 2008, 9(2):2579-2605.
[27] Kaski B S. t-distributed stochastic neighbor embedding[C]// In Proc. 2010.
[28] Laurens V D M. Accelerating t-SNE using tree-based algorithms [J]. Journal of Machine Learning Research, 2014, 15(1):3221-3245.
[29] Subasi A. Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders [J]. Computers in Biology & Medicine, 2013, 43(5):576-586.
[30] Abdi M J, Giveki D. Automatic detection of erythemato-squamous diseases using PSO–SVM based on association rules [J]. Engineering Applications of Artificial Intelligence, 2013, 26(1):603-608.
[31] http://csegroups.case.edu/bearingdatacenter/pages/download-data-file. Bearing Data Center, Case Western Reserve University.
[32] 朱永生, 袁幸, 张优云,等. 滚动轴承复合故障振动建模及Lempel-Ziv复杂度评价[J]. 振动与冲击, 2013, 32(16):23-29.
ZHU Yong-sheng, YUAN Xing, ZHANG You-yun, et al. Vibration modeling of rolling bearings considering compound multi-defect and appraisal with Lempel-Ziv complexity [J]. Journal of Vibration and Shock, 2013, 32(16):23-29.