Abstract
Within the framework of non-destructive testing techniques, it is very important to quickly and cheaply recognize flaws into the inspected materials. Moreover, another requirement is to carry out the inspection in an automatic way, with a total departure from the inspector’s experience, starting from the experimental measurements. In this case, a further problem is represented by the fact that many open problems within the electromagnetic diagnostic are inverse ill-posed problems. This paper just studies a method for the analysis of metallic plates, with the aim of bumps detection and characterization starting from electromagnetic measurements. The ill-posedness of the inverse problem has been overcame by using an optimized heuristic method, i.e., the so called support vector regression machines.
This is a preview of subscription content, log in via an institution to check access.
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
M. Bertero, T.A. Poggio, V. Torre, Ill-posed problems in early vision, Proceedings of the IEEE, no. 76, pp. 869–889, 1988.
V.N. Vapnik, The Nature of Statistical Learning Theory. New York, USA: Springer Verlag, 1995.
A.J. Smola, Regression estimation with support vector learning machines, Master Thesis, Technische Universitat, Munchen, Germany, 1996.
M. Cacciola, F. La Foresta, F.C. Morabito, M. Versaci, Advanced Use of Soft Computing and Eddy Current Test to Evaluate Mechanical Integrity of Metallic Plates. NDT& E International, vol. 40 no. 5, pp. 357–362, 2007.
F.C. Morabito, M. Campolo, Location of Plural Defects in Conductive Plates via Neural Networks. IEEE Transactions on Magnetics, vol. 31, no. 3, pp. 1765–1768, 1995.
M. Cacciola, M. Campolo, F. La Foresta, F.C. Morabito, M. Versaci, A kernel based learning by sample technique for defect identification through the inversion of a typical electric problem, in Lecture Notes in Artificial Intelligence, Special Issue of Joint Conference WIRN2007-KES2007, vol. 4694, Part III, pp. 243–250, 2007.
R.J. Van De Graaff, A 1,500,000 Volt electrostatic generator, Physical Review, no. 38, pp. 1919–1920, 1931.
E. Durand, Electrostatique, Tome II. Paris: Masson, 1966.
B. Schölkopf, A. Smola, Learning with Kernels. New York, USA: MIT Press, 2002.
J. Weston, Leave-one-out support vector machines, Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, Stockholm, Sweden, July 31–August 6, pp. 727–733, 1999.
H. Ian, F. Eibe, I.H. Witten, Data Mining: Practical Machine Learning Tools and Techniques. New York: Morgan Kaufmann, 2005.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Cacciola, M., Megali, G., Morabito, F.C. (2008). An Optimized Support Vector Machine Based Approach for Non-Destructive Bumps Characterization in Metallic Plates. In: Wiak, S., Krawczyk, A., Dolezel, I. (eds) Intelligent Computer Techniques in Applied Electromagnetics. Studies in Computational Intelligence, vol 119. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-78490-6_16
Download citation
DOI: https://doi.org/10.1007/978-3-540-78490-6_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-78489-0
Online ISBN: 978-3-540-78490-6
eBook Packages: EngineeringEngineering (R0)