A Comparative Study of SVM Classifiers and Artificial Neural Networks Application for Rolling Element Bearing Fault Diagnosis using Wavelet Transform Preprocessing
Effectiveness of Artificial Neural Networks (ANN)
and Support Vector Machines (SVM) classifiers for fault diagnosis of
rolling element bearings are presented in this paper. The
characteristic features of vibration signals of rotating driveline that
was run in its normal condition and with faults introduced were used
as input to ANN and SVM classifiers. Simple statistical features such
as standard deviation, skewness, kurtosis etc. of the time-domain
vibration signal segments along with peaks of the signal and peak of
power spectral density (PSD) are used as features to input the ANN
and SVM classifier. The effect of preprocessing of the vibration
signal by Discreet Wavelet Transform (DWT) prior to feature
extraction is also studied. It is shown from the experimental results
that the performance of SVM classifier in identification of bearing
condition is better then ANN and pre-processing of vibration signal
by DWT enhances the effectiveness of both ANN and SVM classifier
[1] J. Pineyro, A. Klempnow and V. Lescano, Effectiveness of new spectral
techniques in the anomaly detection of rolling element bearings," J of
Alloys and Compounds,310, 2000, p.276-279.
[2] N. Tandon and A. Choudhury, "A review of vibration and acoustic
measurement methods for the detection of defects in rolling element
bearings," Tribology International, 32, 1999, p.469-80.
[3] T. Miyachi and K. Seki, "An investigation of early detection of defects
in ball bearings using vibration monitoring- practical limit of
detectability," Proceedings of the International Conference on
Rotodynamics, JSME-IFToMM, Tokyo, 14-17 September,1986,p.403-8.
[4] D. Dyer and R.M. Stewart, "Detection of rolling element bearing
damage by statistical vibration analysis," Trans ASME, J Mech Design,
100(2), 1978, p.229-35.
[5] A.A. Rush, "Kurtosis - A crystal ball for maintenance engineers," Iron
and Steel Int, February 1979, p. 23-27.
[6] D.E. Butler, "The shock pulse method for the detection of damaged
rolling bearings," NDT Int 1973, p.92-95.
[7] N. Tandon and BC.Nakra, "Detection of defects in rolling element
bearings by vibration monitoring," J Instn Engrs (India) ÔÇö Mech Eng
Div 73,1993, p.271-82.
[8] G.K. Chaturvedi and DW. Thomas, "Bearing fault detection using
adaptive noise canceling," ASME Paper 81-DET-7, New York, ASME,
1981, p.10.
[9] J. Courrech, "Envelop Analysis for effective rolling element bearing
fault detection - Facts or fiction?" Up Time Magazine, 8, 2000, p.113-
117.
[10] P.W. Tse, Y.H Peng and R.Yam, "Wavelet analysis and envelope
detection for rolling element bearing fault diagnosis - Their
effectiveness and flexibilities," J Vibration and Acoustics, ASME, 123,
2001, p.303-310.
[11] W. Youshang, S. Quio and L. Xiaolei, "The application of wavelet
transform and artificial neural networks in machinery fault diagnosis,"
Proceedings of ICSP, 1996.p. 1609-12.
[12] I.E. Alguindigue, A.L. Buczak and R.E. Uhrig, "Monitoring of rolling
element bearings using artificial neural networks," IEEE Transactions on
Industrial Electronics, Vol.40, No.2, April1993.p.209-217.
[13] J.D. Wu and C.H. Liu, "Investigation of engine fault diagnosis using
discreet wavelet transform and neural network," Expert Systems with
Applications, 2007, doi:10.1016/J.eswa.2007.08.021.
[14] S. Rajakarunakaran, P. Venkumar, D. Devaraj and K.S.P Rao, "Artificial
neural network approach for fault detection in rotary system," Applied
Soft Computing, 8, 2008, p.740-8.
[15] J.A. Anderson, ÔÇÿA simple neural network generating an interactive
memory- Mathmetical Bioscience, 14, 1972, pp. 197-220.
[16] M.T. Hagan, H.B. Demuth and M. Beale, Neural Network Design, PWS
Publishing Company, Boston, 2002.
[17] D.E. Rumelhart, G.E. Hinton and R.J. Williams, "Learning
representations by back propagating errors," Nature, 1986, 323, p. 533-
36.
[18] M.T. Hagan and M. Menhaj, "Training feed forward networks with the
Marquardt algorithm," IEEE transactions on Neural Networks, 5(6),
1994.
[19] M. Zacksenhouse, S. Braun and M. Feldman, "Toward helicopter
gearbox diagnostics from a small number of examples," Mechanical
systems and Signal Processing, 14(4), 2000, 523-43.
[20] S.R. Gunn, "Support vector machines for classification and regression,"
technical report, University of Southampton, 1998.
[21] G. Goudong, Z.S. Li and K.L. Chan, "Support vector machines for face
recognition," Image and Vision Computing, 19, 2001, 631-8.
[22] O. Barzilay and V.L. Brailovsky, "On domain knowledge and feature
selection using a support vector machine," Pattern Recognition Letters,
20(5), 1999, 475-84.
[23] M. Ge, R. Du, G.C. Zhang and YS. Xu, "Fault diagnosis using a support
vector machine with application in sheet metal stamping operations,"
Mech. Systems and Signal Processing, 18, 2004, 143-159.
[24] B. Samantha, "Gear fault detection using artificial neural networks and
support vectors machines with genetic algorithms," Mech. Systems and
Signal Processing, 18, 2004, 625-44.
[25] Q. Hu, Z. He, Z, Zang and Y. Zi, "Fault diagnosis of rotating machinery
based on improved wavelet package transform and SVMs ensemble,"
Mech. Systems and Signal Processing, 21, 2007, 688-705.
[26] Y. Yang, D. Yu and J. Cheng, "A fault diagnosis approach for roller
bearing based on envelop spectrum and SVM," Measurement, 40, 2007,
943-50.
[27] V.N. Yapnic, Statistical Learning Theory, John Willy, New Yourk,
1998.
[28] D.E. Newland, "Wavelet Analysis of vibration, Part1 :Theory," J Vib.
and acoustics, 116, 1994. p. 409-24
[29] W. J. Wang and PD McFadden, "Application of wavelets to gearbox
vibration signals for fault detection," J of Sound and Vib., 192(5), 1996.
p. 927-39.
[30] Z.K. Peng, PW. Tse and F.L Chu, "A comparative study of improved
Hilbert-Huang transform and wavelet transform: Application to fault
diagnosis for rolling bearing," Mech. System and Signal Processing,
19(2005), p. 974-988.
[31] V.J. Samar, A. Bopardikar, R. Rao and K. Swartz, "Wavelet analysis of
neuroelectric waveforms: A conceptual tutorial," Brain Language, 66,
1999, 7-60.
[32] S.G. Mallat. "A theory for multiresolution signal decomposition: The
wavelet representation," IEEE Trans Pattern Anal Machine Intelligence",
11(7),1989, p.674-93.
[1] J. Pineyro, A. Klempnow and V. Lescano, Effectiveness of new spectral
techniques in the anomaly detection of rolling element bearings," J of
Alloys and Compounds,310, 2000, p.276-279.
[2] N. Tandon and A. Choudhury, "A review of vibration and acoustic
measurement methods for the detection of defects in rolling element
bearings," Tribology International, 32, 1999, p.469-80.
[3] T. Miyachi and K. Seki, "An investigation of early detection of defects
in ball bearings using vibration monitoring- practical limit of
detectability," Proceedings of the International Conference on
Rotodynamics, JSME-IFToMM, Tokyo, 14-17 September,1986,p.403-8.
[4] D. Dyer and R.M. Stewart, "Detection of rolling element bearing
damage by statistical vibration analysis," Trans ASME, J Mech Design,
100(2), 1978, p.229-35.
[5] A.A. Rush, "Kurtosis - A crystal ball for maintenance engineers," Iron
and Steel Int, February 1979, p. 23-27.
[6] D.E. Butler, "The shock pulse method for the detection of damaged
rolling bearings," NDT Int 1973, p.92-95.
[7] N. Tandon and BC.Nakra, "Detection of defects in rolling element
bearings by vibration monitoring," J Instn Engrs (India) ÔÇö Mech Eng
Div 73,1993, p.271-82.
[8] G.K. Chaturvedi and DW. Thomas, "Bearing fault detection using
adaptive noise canceling," ASME Paper 81-DET-7, New York, ASME,
1981, p.10.
[9] J. Courrech, "Envelop Analysis for effective rolling element bearing
fault detection - Facts or fiction?" Up Time Magazine, 8, 2000, p.113-
117.
[10] P.W. Tse, Y.H Peng and R.Yam, "Wavelet analysis and envelope
detection for rolling element bearing fault diagnosis - Their
effectiveness and flexibilities," J Vibration and Acoustics, ASME, 123,
2001, p.303-310.
[11] W. Youshang, S. Quio and L. Xiaolei, "The application of wavelet
transform and artificial neural networks in machinery fault diagnosis,"
Proceedings of ICSP, 1996.p. 1609-12.
[12] I.E. Alguindigue, A.L. Buczak and R.E. Uhrig, "Monitoring of rolling
element bearings using artificial neural networks," IEEE Transactions on
Industrial Electronics, Vol.40, No.2, April1993.p.209-217.
[13] J.D. Wu and C.H. Liu, "Investigation of engine fault diagnosis using
discreet wavelet transform and neural network," Expert Systems with
Applications, 2007, doi:10.1016/J.eswa.2007.08.021.
[14] S. Rajakarunakaran, P. Venkumar, D. Devaraj and K.S.P Rao, "Artificial
neural network approach for fault detection in rotary system," Applied
Soft Computing, 8, 2008, p.740-8.
[15] J.A. Anderson, ÔÇÿA simple neural network generating an interactive
memory- Mathmetical Bioscience, 14, 1972, pp. 197-220.
[16] M.T. Hagan, H.B. Demuth and M. Beale, Neural Network Design, PWS
Publishing Company, Boston, 2002.
[17] D.E. Rumelhart, G.E. Hinton and R.J. Williams, "Learning
representations by back propagating errors," Nature, 1986, 323, p. 533-
36.
[18] M.T. Hagan and M. Menhaj, "Training feed forward networks with the
Marquardt algorithm," IEEE transactions on Neural Networks, 5(6),
1994.
[19] M. Zacksenhouse, S. Braun and M. Feldman, "Toward helicopter
gearbox diagnostics from a small number of examples," Mechanical
systems and Signal Processing, 14(4), 2000, 523-43.
[20] S.R. Gunn, "Support vector machines for classification and regression,"
technical report, University of Southampton, 1998.
[21] G. Goudong, Z.S. Li and K.L. Chan, "Support vector machines for face
recognition," Image and Vision Computing, 19, 2001, 631-8.
[22] O. Barzilay and V.L. Brailovsky, "On domain knowledge and feature
selection using a support vector machine," Pattern Recognition Letters,
20(5), 1999, 475-84.
[23] M. Ge, R. Du, G.C. Zhang and YS. Xu, "Fault diagnosis using a support
vector machine with application in sheet metal stamping operations,"
Mech. Systems and Signal Processing, 18, 2004, 143-159.
[24] B. Samantha, "Gear fault detection using artificial neural networks and
support vectors machines with genetic algorithms," Mech. Systems and
Signal Processing, 18, 2004, 625-44.
[25] Q. Hu, Z. He, Z, Zang and Y. Zi, "Fault diagnosis of rotating machinery
based on improved wavelet package transform and SVMs ensemble,"
Mech. Systems and Signal Processing, 21, 2007, 688-705.
[26] Y. Yang, D. Yu and J. Cheng, "A fault diagnosis approach for roller
bearing based on envelop spectrum and SVM," Measurement, 40, 2007,
943-50.
[27] V.N. Yapnic, Statistical Learning Theory, John Willy, New Yourk,
1998.
[28] D.E. Newland, "Wavelet Analysis of vibration, Part1 :Theory," J Vib.
and acoustics, 116, 1994. p. 409-24
[29] W. J. Wang and PD McFadden, "Application of wavelets to gearbox
vibration signals for fault detection," J of Sound and Vib., 192(5), 1996.
p. 927-39.
[30] Z.K. Peng, PW. Tse and F.L Chu, "A comparative study of improved
Hilbert-Huang transform and wavelet transform: Application to fault
diagnosis for rolling bearing," Mech. System and Signal Processing,
19(2005), p. 974-988.
[31] V.J. Samar, A. Bopardikar, R. Rao and K. Swartz, "Wavelet analysis of
neuroelectric waveforms: A conceptual tutorial," Brain Language, 66,
1999, 7-60.
[32] S.G. Mallat. "A theory for multiresolution signal decomposition: The
wavelet representation," IEEE Trans Pattern Anal Machine Intelligence",
11(7),1989, p.674-93.
@article{"International Journal of Mechanical, Industrial and Aerospace Sciences:58438", author = "Commander Sunil Tyagi", title = "A Comparative Study of SVM Classifiers and Artificial Neural Networks Application for Rolling Element Bearing Fault Diagnosis using Wavelet Transform Preprocessing", abstract = "Effectiveness of Artificial Neural Networks (ANN)
and Support Vector Machines (SVM) classifiers for fault diagnosis of
rolling element bearings are presented in this paper. The
characteristic features of vibration signals of rotating driveline that
was run in its normal condition and with faults introduced were used
as input to ANN and SVM classifiers. Simple statistical features such
as standard deviation, skewness, kurtosis etc. of the time-domain
vibration signal segments along with peaks of the signal and peak of
power spectral density (PSD) are used as features to input the ANN
and SVM classifier. The effect of preprocessing of the vibration
signal by Discreet Wavelet Transform (DWT) prior to feature
extraction is also studied. It is shown from the experimental results
that the performance of SVM classifier in identification of bearing
condition is better then ANN and pre-processing of vibration signal
by DWT enhances the effectiveness of both ANN and SVM classifier", keywords = "ANN, Artificial Intelligence, Fault Diagnosis,
Pattern Recognition, Rolling Element Bearing, SVM. Wavelet
Transform", volume = "2", number = "7", pages = "905-9", }
