Fault diagnosis of EMU rolling bearing based on EEMD and SVM

Rolling bearing is an important and fragile component in the EMU. To give a safe condition assessment of rolling bearing, especially for early fault diagnosis, is very necessary and become an urgent thing to the EMU. A fault detection and diagnosis method based on EEMD, sample entropy and SVM is proposed in this paper. Firstly, the investigated signal is decomposed into several IMFs by EEMD. Then, the values of sample entropy of IMFs are extracted as the feature vectors, and finally the fault detection and classification are carried out with feature vectors by using SVM. The method can effectively diagnose the fault. Compared with the results of EMD and SVM combination, this method is more accurate and valid.Rolling bearing is an important and fragile component in the EMU. To give a safe condition assessment of rolling bearing, especially for early fault diagnosis, is very necessary and become an urgent thing to the EMU. A fault detection and diagnosis method based on EEMD, sample entropy and SVM is proposed in this paper. Firstly, the investigated signal is decomposed into several IMFs by EEMD. Then, the values of sample entropy of IMFs are extracted as the feature vectors, and finally the fault detection and classification are carried out with feature vectors by using SVM. The method can effectively diagnose the fault. Compared with the results of EMD and SVM combination, this method is more accurate and valid.

[1]  Yaguo Lei,et al.  Application of the EEMD method to rotor fault diagnosis of rotating machinery , 2009 .

[2]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[3]  Tung Khac Truong,et al.  A Roller Bearing Fault Diagnosis Method Based on LCD Energy Entropy and ACROA-SVM , 2014 .

[4]  Lili Ding,et al.  Gear Fault Diagnosis Using Dual Channel Data Fusion and EEMD Method , 2017 .

[5]  Wang Ping,et al.  Application study of EMD-AR and SVM in the fault diagnosis , 2014, 2014 Prognostics and System Health Management Conference (PHM-2014 Hunan).

[6]  Jiang Wan-l.  Fault diagnosis of ball bearing based on EEMD morphological spectrum and support vector machine , 2015 .

[7]  Nathaniel H. Hunt,et al.  The Appropriate Use of Approximate Entropy and Sample Entropy with Short Data Sets , 2012, Annals of Biomedical Engineering.

[8]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[9]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[10]  Kun Yu,et al.  A bearing fault diagnosis technique based on singular values of EEMD spatial condition matrix and Gath-Geva clustering , 2017 .

[11]  Norden E. Huang,et al.  Ensemble Empirical Mode Decomposition: a Noise-Assisted Data Analysis Method , 2009, Adv. Data Sci. Adapt. Anal..

[12]  Ivan Prebil,et al.  EEMD-based multiscale ICA method for slewing bearing fault detection and diagnosis , 2016 .

[13]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[14]  N. Huang,et al.  A study of the characteristics of white noise using the empirical mode decomposition method , 2004, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[15]  Tang Gui-j.  Fault diagnosis for roller bearings based on EEMD de-noising and 1.5-dimensional energy spectrum , 2014 .

[16]  Gabriel Rilling,et al.  Empirical mode decomposition as a filter bank , 2004, IEEE Signal Processing Letters.