PZT-Induced Lamb Waves and Pattern Recognition for On-Line Health Monitoring of Jointed Steel Plates

Abstract:

This paper presents a non-destructive evaluation (NDE) technique for detecting damages on a jointed steel plate on the basis of the time of flight and wavelet coefficient, obtained from wavelet transforms of Lamb wave signals. Probabilistic neural networks (PNNs) and support vector machines (SVMs) were applied for pattern classification. In this study, the applicability of the PNNs and SVMs was investigated for the damages in and out of the Lamb wave path. It has been found that the present methods are very efficient in detecting the damages simulated by the loose bolts on the jointed steel plate.

• Periodical: Key Engineering Materials (Volumes 321-323)
• Pages: 146-151
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.321-323.146
• Online since: October 2006
• Authors: Yong Rae Roh, Don Young Kim, Seung Han Yang, Seung Hee Park, Chung Bang Yun
• Keywords: Jointed Steel Plates, Lamb Wave, On-Line Health Monitoring, Pattern Recognition, Probabilistic Neural Network (PNN), PZT, Support Vector Machine (SVM)

References

[1] S. H. Park, Y. R. Roh, C. B. Yun, and J. H. Yi, Proceedings of 11 th International Symposium on Smart Structures and Materials, SPIE Vol. 5391 (2004), p.705.

[2] K. Luangvilai, W. Punurai and L. J. Jacobs, Journal of Engineering Mechanics, Vol. 128 (2002), p.1337.

[3] Z. Chang and A. Mal, Mechanics of Materials, Vol. 31 (1999), p.197.

[4] V. N. Vapnik, The Nature of Statistical Learning Theory (Springer-Verlag, New York 1995).