Novelty detection for machinery condition monitoring

• Autorzy: Worden, K. , Staszewski, W.
• Języki publikacji: EN

Abstrakty

EN

This paper is concerned with novelty analysis for fault detection in machinery. The detection procedure employed here uses novelty detection based on two approaches: an auto-associative neural network and kernel density estimation. The methodology is illustrated on the detection of local tooth faults in pseudo-experimental gearbox vibration data. The study shows the possibility of automatic signalling of failure. The method can be extended to any data type representing normal and abnormal conditions.

Słowa kluczowe

PL

detekcja uszkodzeń; monitorowanie stanu maszyn; metody monitorowania; drgania skrzyni biegów

EN

fault detection; machine condition monitoring; monitoring methods; gearbox vibration

• Czasopismo: Vibrations in Physical Systems
• Rocznik: 1998
• Tom: Vol. 18
• Strony: 35--46
• Opis fizyczny: Bibliogr. 13 poz.

Twórcy

autor

Worden, K.

• Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Mappin Street, Sheffield SI 3JD, England,

autor

Staszewski, W.

• Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Mappin Street, Sheffield SI 3JD, England

Bibliografia

• [1] Schalkoff R., Pattern Recognition. Statistical, Structural and Neural Approaches, John Wiley & Sons, Inc., New York, 1992.
• [2] Tarassenko L., Hayton P., Cerneaz Z. and Brady M., ’’Novelty detection for the identification of masses in mammograms”, In Proc. 4th IEE Int. Conf. on Artificial Neural Networks, Cambridge, 1995, IEE Conf. Publication No. 409, pp. 442-447.
• [3] Pomerleau D.A., ’’Input reconstruction reliability estimation”, In Advances in Neural Information Processing Systems 5 ed. S.J. Hanson, J.D. Cowan & C.L. Giles, Morgan Kaufman Publishers, 1993.
• [4] Worden K., „Structural fault detection using a novelty measure”, Journal of Sound and Vibration, Vol. 201(1), 1997, pp. 85-101.
• [5] Worden K., ’’Damage detection using a novelty measure”, Proc. of the 15th IMAC, Orlando, Florida, 1997, pp.631-637.
• [6] Bishop C.M., ’’Novelty detection and neural network validation”, IEE Proc - Vis. Image Signal Process., Vol. 141(4), 1994, pp. 217-222.
• [7] Nairac A., Corbett-Clark T.A., Eipley R., Townsend N.W. and Tarassenko L., ’’Choosing an appropriate model for novelty detection”, Proceedings of the 5th International Conference on Artificial Neural Networks, Cambridge, UK, 1997, pp. 117-222.
• [8] Staszewski W.J., ’’Wavelet novelty measure for machinery diagnostics”, A Symposium on Time-Frequency and Wavelet Analysis at the Sixteenth Biennal Conference on Mechanical Vibration and Noise, ASME Design Engineering Conferences Sacramento, California, 14-17 September, 1997.
• [9] Staszewski W.J., Pierce S.G., Worden K., Philp W.R., Tomlinson G.R. and Culshaw B., ’’Wavelet signal processing for enhanced Lamb wave defect detection in composite plates using optical fibre detection”, Optical Engineering, Vol. 36(7), 1997, pp. 1877-1888.
• [10] Haykin S., Neural Networks. A Comprehensive Foundation, Macmillian College Publishing Company, New York, 1994.
• [11] Silverman B.W., Density estimation for statistics and data analysis, Chapman and Hall Monographs on Statistics and Applied Probability, 26, 1986.
• [12] Leuenberger D.G., Linear and Nonlinear Programming, Second Edition, Addison-Wesley, 1989.
• [13] Staszewski W.J., and Worden K., ’’Classification of faults in gearboxes - preprocessing algorithms and neural networks, Neural Computing and Applications, 5, 1996, pp.160-183.