Abstract
Conventional vibration signals processing techniques are most suitable for stationary processes. However, most mechanical faults in machinery reveal themselves through transient events in vibration signals. That is, the vibration generated by industrial machines always contains nonlinear and non-stationary signals. It is expected that a desired time-frequency analysis method should have good computation efficiency, and have good resolution in both time domain and frequency domain. In this paper, the auto-regressive model based pseudo-Wigner-Ville distribution for an integrated time-frequency signature extraction of the machine vibration is designed, the method offers the advantage of good localization of the vibration signal energy in the time-frequency domain. Kernel principal component analysis (KPCA) is used for the redundancy reduction and feature extraction in the time-frequency domain, and the self-organizing map (SOM) was employed to identify the faults of the rotating machinery. Experimental results show that the proposed method is very effective.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Yen, G.G., Lin, K.C.: Wavelet Packet Feature Extraction for Vibration Monitoring. IEEE Transactions on Industrial Electronics 47, 650–667 (2000)
Pan, M.C., Sas, P.: Transient Analysis on Machinery Condition Monitoring. In: IEEE Proceedings of International Conference on Signal Processing, vol. 2, pp. 1723–1726 (1996)
Bastiaans, M.J.: Gabor’expansion of a Signal into Gaussian Elementary Signals. In: Proceedings of the IEEE, vol. 68, pp. 538–539 (1980)
Cohen, L.: Time-frequency Distribution—a Review. In: Proc. IEEE, vol. 77, pp. 941–981 (1989)
Cohen, L.: Time-Frequency Analysis. Prentice-Hall, Englewood Cliffs (1995)
Wise, B.M., Gallagher, N.B.: The Process Chemometrics Approach to Process Monitoring and Fault Detection. Journal of Process Control 6(6), 329–348 (1996)
Dong, D., McAvoy, T.J.: Nonlinear Principal Component Analysis Based on Principal Curves and Neural Networks. Computers and Chemical Engineering 20(1), 65–78 (1996)
Schölkopf, B., Smola, A.J., MJuller, K.: Nonlinear component analysis as a kernel eigen-value problem. Neural Computation 10(5), 1299–1399 (1998)
Mika, S., Schölkopf, B., et al.: Kernel PCA and De-noising in Feature Spaces. Advances in Neural Information Processing Systems 11, 536–542 (1999)
Romdhani, S., Gong, S., Psarrou, A.: A multi-view Nonlinear Active Shape Model Using Kernel PCA. In: Proceedings of BMVC, Nottingham, UK, pp. 483–492 (1999)
Kohonen, T.: Self-Organizing Maps, 3rd edn., pp. 138–140. Springer, Berlin (2001)
Kohonen, T.: Self-organized Formation of Topologically Correct Feature Maps. Biol. Cybernetics 43, 59–69 (1982)
Juha, V., Esa, A.: Clustering of the Self-organizing Map. IEEE Trans. Neural Networks 11, 586–600 (2000)
Kohonen, T., Kaski, S., Lagus, K., Salojärvi, J., et al.: Self-organizing of a Massive Docu-ment Collection. IEEE Trans. Neural Networks 11, 574–585 (2000)
Chang, C.H., Xu, P.F., Xiao, R., Srikanthan, T.: New Adaptive Color Quantization Method Based on Self-Organizing Maps. IEEE Trans. Neural Networks 16(1), 237–249 (2005)
Vermasvuori, M., et al.: The Use of Kohonen Self-organizing Maps in Process Monitoring. Proceedings of IEEE International Symposium Intelligent Systems 3, 2–7 (2002)
Qian, S., Chen, D.: Joint Time-frequency Analysis. IEEE Signal Processing Magazine 16(2), 52–67 (1999)
Qian, S.: Introduction to Time-Frequency and Wavelet Transforms. Prentice Hall, Englewood Cliffs (2002)
Classen, T.A.C.M., Mecklenbrauker, W.F.G.: The Wigner Distribution–a Tool for Time-frequency Analysis. Philips Journal of Research 35, 217-250, 276-300 (1980)
Hammond, J.K., White, P.R.: The analysis of Nonstationary Signals Using Time-Frequency Methods. Journal of Sound and Vibration 190, 419–447 (1996)
Mcfadden, P.D., Wang, W.J.: Analysis of Gear Vibration Signatures by the Weighted Wigner-Ville Distribution. In: Proceedings of the Fifth International Conference on Vibra-tions in Rotating Machinery, pp. 387–393. University of Bath, ImechE (1992)
Haykin, S.: Neural Networks. Prentice-Hall, Englewood Cliffs (1999)
Romdhani, S., Gong, S., Psarrou, A.: A Multi-view Nonlinear Active Shape Model Using Kernel PCA. In: Proceedings of BMVC, Nottingham, UK, pp. 483–492 (1999)
Christianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press, Cambridge (2000)
Hu, N.Q., Chen, M., Wen, X.S.: The Application of Stochastic Resonance Theory for Early Detecting Rubbing Caused Impacts Fault of Rotor System. Mechanical Systems and Signals Processing 17, 883–895 (2003)
Ultsch, A., Siemon, H.P.: Kohonen’s Self Organizing Feature Maps for Exploratory Data Analysis. In: Proceedings Intern. Neural Networks, pp. 305–308. Kluwer Academic Press, Paris (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Guo, Q., Yu, H., Nie, Y., Xu, A. (2006). Joint Time-Frequency and Kernel Principal Component Based SOM for Machine Maintenance. In: Wang, J., Yi, Z., Zurada, J.M., Lu, BL., Yin, H. (eds) Advances in Neural Networks - ISNN 2006. ISNN 2006. Lecture Notes in Computer Science, vol 3973. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11760191_167
Download citation
DOI: https://doi.org/10.1007/11760191_167
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34482-7
Online ISBN: 978-3-540-34483-4
eBook Packages: Computer ScienceComputer Science (R0)