Abstract
Among the engineering applications of Intelligent Systems, the field of Non-Destructive Testing and Evaluation (NDT/NDE) appears to be particularly interesting for its industrial relevance. NDT plays an increasingly important role in diverse areas of modern society ranging from aerospace and nuclear power plants to oil and gas transportation. In addition, NDT techniques are of relevant interest in subsurface mine detection, seismic engineering and geophysical applications. The goal of most NDT techniques is to reveal anomalies in a test object without destroying or somehow perturb the test specimen. Various physical principles, ranging from acoustics, thermal, optics and mechanics to nuclear physics, have been proposed and utilized in NDT/NDE techniques. Measurements are affected by various sources of inaccuracies, namely, the imprecise contour and shape of the defect, the geometry of the inspected specimens, the measurement noise, and the imprecise location of sensors and probes. Intelligent processing techniques can be useful in various respects. The decision about the presence of the defect is a difficult task that involves prior knowledge on the problem in terms of human expertise. Computationally expensive optimization and iteration procedures are used to accurately extract any important information from raw data. Some information is basically a context property. Models based on Artificial Neural Networks (ANNs), fuzzy systems, approximate reasoning, and information decision trees can be of help in solving this problem. In this chapter, a critical analysis of novel computing techniques for treating the characterization problem (determining number, size, and location of defects in specimens) is carried out. Several examples of intelligent processing of NDT/NDE data will be proposed throughout this chapter.
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
W. F. Heiligenberg, Neural Nets in Electric Fish, A Bradford Book, The MIT Press, Cambridge, Mass.
D. L. Birx and S. J. Pipenberg,“A Complex Mapping Network for Phase Sensitive Classification,” IEEE Trans, on Neural Networks, Vol. 4, No. 1, pp. 127–135, January 1993.
F. C. Morabito and M. Campolo,“Advances in Neural Network Non-Destructive Testing,” Proc. 2nd Intl. Conf. on Comp. in Electromagnetics, IEE Conf. no. 384, pp. 76–80, Nottingham, UK, April 1994.
F. C. Morabito,“Multilayer Neural Networks for Identification of Nonlinear Electromagnetic Systems,” Proc. of the World Congr. on Neural Nets (WCNN), Vol. 1, pp. 428–432, Portland, OR, July 1993.
S. Haykin, Neural Networks, IEEE Press, Macmillan College Publishing Company, New York, 1994.
B. L. M. Happel and J. M. J. Murre,“Design and Evolution of Modular Neural Network Architectures,” Neural Networks, Vol. 7, Nos. 6/7, pp. 985–1004, 1994.
E. Coccorese, R. Martone and C. Morabito,“A Neural Network Approach for the Solution of Electric and Magnetic Inverse Problems,” IEEE Trans. on Magnetics, vol. 30, No. 5, pp. 2829–2839, Sept. 1994.
O. A. Mohammed, et al.,“Design Optimization of Electromagnetic Devices using Artificial Neural Networks,” IEEE Trans. on Magn., vol. 29, No. 2, pp. 1775–1778, Mar 1993.
B. Kosko, Neural Networks and Fuzzy Systems, Prentice Hall: Englewood Cliffs, 1992.
M. Enokizono, and Yuji Tsuchida,“Optimal Design by Boundary Element Method with Fuzzy Inference,” IEEE Trans. on Magnetics, Vol. 30, No. 5, pp. 3447–3450, Sept 1994.
J. Pavo, A. Gasparics, et al,“Proposal for Benchmark Problem Qualifying Some Aspects of the Performance of ECT Probes,” Electromagnetic Non-Destructive Evaluation (II), R. Albanese et al (Eds.), IOS Press, 1998, pp. 337–342.
F. C. Morabito, and M. Campolo,“Location of Plural Defects in Conductive Plates via Neural Networks,” IEEE Trans. on Magn., Vol. 31, No. 3, May 1995, pp. 1765–1768.
T. Poggio and F. Girosi,“A theory of Networks for approximating and learning;” Artif. Intell. Lab. Memo, 1140, MIT, (1989).
F. C. Morabito, and M. Campolo,“A Modular Neural Computation Architecture Related to Real Neural Organizations for the Solution of a Pattern Recognition Problem.” WIRN95, Springer-Verlag, Vietri S/M, Italy.
IEEE Trans. on Neural Networks, Special Issue on Fuzzy Logic and Neural Networks, Vol. 3, No. 5, September 1992.
J. L. Castro,“Fuzzy Logic Controllers Are Universal Approximators,” IEEE Trans. on Syst., Man, and Cybern., Vol. 25, No. 4, April 1995, pp. 629–635.
F. C. Morabito and M. Campolo,“Ill-Posed Problems in Electromagnetics: Advantages of Neuro-Fuzzy Approaches,” Proc. 2nd Intl. Symposium on Neuro-Fuzzy Systems, EPFL, Lausanne, CH, 31 August 1996.
G. Chen, Y. Yoshida, K. Miya, M. Kurokawa, Reconstruction of Defects from the Distribution of Current Vector Potential using Wavelets, Intl. Journ. of Applied Electr. in Materials 5, (1994) 189–199.
F. C. Morabito, M. Campolo, A novel neural network approach in nondestructive testing, in Proceedings of the Third Int. Conf. on Comp. in Electr., Bath, UK, (10–12 Apr 1996), 364–369, London, UK, Apr. 1996, IEE Conf. Publ. No. 420.
R. Albanese, A. Formisano, R. Martone, C. Morabito, G. Rubinacci, F. Villone, A Method for the Analysis of Metallic Tubes with ECT and Neuro-Fuzzy Processing, paper presented at IV Workshop on Optimization and Inverse Problems in Electromagnetism, Brno (June 1996).
C. Chui, Wavelets: A Tutorial in Theory and Applications. Academic Press, Inc. Boston, San Diego, 1992.
Proceedings of the IEEE, Special Issue on Wavelets, Vol. 84, April 1996.
Q. Zhang and A. Benveniste, Wavelet Networks, IEEE Transactions on Neural Networks, Vol. 3, pp. 889–898, Nov. 1992.
H. Szu, B. Telfer and Joseph Garcia,“Wavelet transforms and neural networks for compression and recognition,” Neural Networks, Vol. 9, No. 4, pp. 695–708, June 1996.
L. Udpa, S. S. Udpa,“Application of Signal Processing and Pattern Recognition Techniques to Inverse Problems in NDE,” Intl. J. Of Applied Electromagnetics and Mechanics, Vol. 8, pp. 99–117, 1997.
A. Gottvald,“A survey of inverse methodologies, meta-evolutionary optimization and Bayesian statistics: applications to in vivo MRS,” Intl. J. Applied Electromagnetics and Mechanics, Vol. 8, pp. 17–44, 1997.
Y. Sun,“An Introduction to Electromagnetic Nondestructive Testing,” In Non Linear Electromagnetic Systems, V. Kose, J. Sievert (Eds.), IOS Press, 1998, pp. 145–152.
H. Kaden,“Wirbelströme und Schirmung in der Nachrichtentechnik,” Tech. Physik in Einzeldarstellurgen, vol. 10, pp. 241–248, 1980.
F. C. Morabito, R. Albanese, E. Coccorese, R. Martone and G. Rubinacci,“Identification of Circular Holes in Thin Plates Using a Neural Network Approach,” in Nonlinear Electromagnetic Systems, vol. 10, A. J. Moses and A. Basak, (Eds.), Amsterdam: IOS Press, March 1996.
Q. Zhang, Wavenets, Public domain Matlab toolbox, Anonymous FTP, ftp.irisa.fr: /local/wavenet, 1993.
R. Albanese, A. Formisano, R. Martone and F. C. Morabito,“Multiple Defect Analysis via Neuro-Fuzzy Approaches,” in Proceedings of Electromagnetic Non Destructive Evaluation (E-NDE’ 97), Reggio Calabria, Italy, 17–21 September 1997.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Morabito, F.C. (2000). Intelligent Non-Destructive Testing and Evaluation with Industrial Applications. In: Teodorescu, HN., Mlynek, D., Kandel, A., Zimmermann, HJ. (eds) Intelligent Systems and Interfaces. International Series in Intelligent Technologies, vol 15. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-4401-2_12
Download citation
DOI: https://doi.org/10.1007/978-1-4615-4401-2_12
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6980-6
Online ISBN: 978-1-4615-4401-2
eBook Packages: Springer Book Archive