A DWT and SVM based method for rolling element bearing fault diagnosis and its comparison with Artificial Neural Networks

Document Type : Research Paper


1 Defence Institute of Advanced Technology

2 Defence Institute of Advanced Technology Girinagar, Pune - 411025, India


A classification technique using Support Vector Machine (SVM) classifier for detection of rolling element bearing fault is presented here.  The SVM was fed from features that were extracted from of vibration signals obtained from experimental setup consisting of rotating driveline that was mounted on rolling element bearings which were run in normal and with artificially faults induced conditions. The time-domain vibration signals were divided into 40 segments and simple features such as peaks in time domain and spectrum along with statistical features such as standard deviation, skewness, kurtosis etc. were extracted. Effectiveness of SVM classifier was compared with the performance of Artificial Neural Network (ANN) classifier and it was found that the performance of SVM classifier is superior to that of ANN. The effect of pre-processing of the vibration signal by Discreet Wavelet Transform (DWT) prior to feature extraction is also studied and it is shown that pre-processing of vibration signal with DWT enhances the effectiveness of both ANN and SVM classifiers. It has been demonstrated from experiment results that performance of SVM classifier is better than ANN in detection of bearing condition and pre-processing the vibration signal with DWT improves the performance of SVM classifier.


Main Subjects

[1]     Randall RB, Antoni J. Rolling element bearing diagnostics—a tutorial. Mechanical systems and signal processing. 2011 Feb 28; 25(2):485-520.
[2]     Norton MP, Karczub DG. Fundamentals of noise and vibration analysis for engineers. Cambridge university press; 2003 Oct 16.
[3]     Tandon N, Choudhury A. A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings. Tribology international. 1999 Aug 31; 32(8):469-80.
[4]     Holmes DE, Jain LC. Innovations in machine learning. Springer-Verlag Berlin Heidelberg; 2006.
[5]     Bangalore P and Tjernberg LB. An Artificial Neural Network Approach for Early Fault Detection of Gearbox Bearings. IEEE Transactions on Smart Grid 2015, 6(2): 980-987.
[6]     Yu Y, Junsheng C. A roller bearing fault diagnosis method based on EMD energy entropy and ANN. Journal of sound and vibration. 2006 Jun 27; 294(1):269-77.
[7]     Samanta B, Al-Balushi KR. Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mechanical systems and signal processing. 2003 Mar 1; 17(2):317-28.
[8]     Yang J, Zhang Y, Zhu Y. Intelligent fault diagnosis of rolling element bearing based on SVMs and fractal dimension. Mechanical Systems and Signal Processing. 2007 Jul 31; 21(5):2012-24.
[9]     FernáNdez-Francos D, MartíNez-Rego D, Fontenla-Romero O, Alonso-Betanzos A. Automatic bearing fault diagnosis based on one-class ν-SVM. Computers & Industrial Engineering. 2013 Jan 31; 64(1):357-65.
[10] Wu SD, Wu PH, Wu CW, Ding JJ, Wang CC. Bearing fault diagnosis based on multiscale permutation entropy and support vector machine. Entropy. 2012 Jul 27; 14(8):1343-56.
[11] Daubechies I. The wavelet transform, time-frequency localization and signal analysis. IEEE transactions on information theory. 1990 Sep; 36(5):961-1005.
[12] Peng ZK, Chu FL. Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography. Mechanical systems and signal processing. 2004 Mar 31; 18(2):199-221.
[13] Jain AK, Mao J, Mohiuddin KM. Artificial neural networks: A tutorial. IEEE computer. 1996 Mar 1; 29(3):31-44.
[14] Demuth HB, Beale MH, De Jess O, Hagan MT. Neural network design. Martin Hagan; 2014 Sep 1.
[15] Jardine AK, Lin D, Banjevic D. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical systems and signal processing. 2006 Oct 31; 20(7):1483-510.
[16] Hagan MT, Menhaj MB. Training feedforward networks with the Marquardt algorithm. IEEE transactions on Neural Networks. 1994 Nov; 5(6):989-93.
[17] Zacksenhouse M, Braun S, Feldman M, Sidahmed M. Toward helicopter gearbox diagnostics from a small number of examples. Mechanical Systems and Signal Processing. 2000 Jul 1; 14(4):523-43.
[18] Foody GM, Mathur A. The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM. Remote Sensing of Environment. 2006 Jul 30; 103(2):179-89.
[19] Guo G, Li SZ, Chan KL. Support vector machines for face recognition. Image and Vision computing. 2001 Aug 1; 19(9):631-8.
[20] Barzilay O, Brailovsky VL. On domain knowledge and feature selection using a support vector machine. Pattern Recognition Letters. 1999 May 31; 20(5):475-84.
[21] Yan W, Shao H. Application of support vector machine nonlinear classifier to fault diagnoses. InIntelligent Control and Automation, 2002. Proceedings of the 4th World Congress on 2002 (Vol. 4, pp. 2697-2700). IEEE.
[22] Vapnik VN, Vapnik V. Statistical learning theory. New York: Wiley; 1998 Sep 16.
[23] Tse PW, Yang W and Tama HY. Machine fault diagnosis through an effective exact wavelet analysis. Journal of Sound and Vibration 2004; 277: 1005–1024.
[24] Peng YH, Yam R. Wavelet analysis and envelope detection for rolling element bearing fault diagnosis—their effectiveness and flexibilities. Journal of Vibration and Acoustics, Transactions of the ASME. 2001; 123:303-10.
[25] Prabhakar S, Mohanty AR, Sekhar AS. Application of discrete wavelet transform for detection of ball bearing race faults. Tribology International. 2002 Dec 31; 35(12):793-800.
[26] Nikolaou NG, Antoniadis IA. Rolling element bearing fault diagnosis using wavelet packets. Ndt & E International. 2002 Apr 30; 35(3):197-205.
[27] Samar VJ, Bopardikar A, Rao R, Swartz K. Wavelet analysis of neuroelectric waveforms: a conceptual tutorial. Brain and language. 1999 Jan 31; 66(1):7-60.
[28] Mallat SG. A theory for multiresolution signal decomposition: the wavelet representation. IEEE transactions on pattern analysis and machine intelligence. 1989 Jul; 11(7):674-93.