Identification of Conductivity Distribution Using Eddy Current Tomography System and Artificial Neural Networks

Abstract:

In certain applications (security, biomedical, food and wood testing etc.) it is necessary to detect and identify position of small metal particles with high precision. This paper presents an eddy current system designated for evaluation of conductivity distribution. The system was modeled using the finite element method as well as it was constructed and the measurements were carried out. Using these results a data base of the signals achieved for various configurations of the test objects were created. The data base was utilized to solve the identification problem. Artificial neural networks were utilized as the inverse models in order to reconstruct two-dimensional distribution of conductivity. Selected results achieved for simulated signals were presented.

• Periodical: Materials Science Forum (Volume 670)
• Pages: 336-344
• DOI: https://doi.org/10.4028/www.scientific.net/MSF.670.336
• Online since: December 2010
• Authors: Tomasz Chady, Ireneusz Spychalski, Takashi Todaka
• Keywords: Eddy Current, Eddy Current Tomography, Magnetic Induction Tomography (MIT), Neural Model, Transducer

References

[1] H. Griffiths, Magnetic Induction tomography, Measurement Science and Technology, (2001).

[2] H. Scharfetter, H. K. Lackner and J. Rosell, Magnetic induction tomography: hardware for multi-frequency measurements in biological tissues, Physiol. Meas. vol. 22(1), pp.131-146, (2001).

DOI: 10.1088/0967-3334/22/1/317

[3] Korjenevsky, V. Cherepenin, S. Sapetsky, Magnetic induction tomography: experimental realization, Physiol. Meas. 21 pp.89-94. (2000).

DOI: 10.1088/0967-3334/21/1/311

[4] T. Chady, M. Enokizono, T. Todaka, Y. Tsuchida, T. Yasutake, Identification of three-dimensional distribution of metal particles using electromagnetic tomography system, Journal of Materials Processing Technology 181, p.177–181, (2007).

DOI: 10.1016/j.jmatprotec.2006.03.022

[5] T. Chady, I. Spychalski, Computer Controlled Eddy Current Tomography System, Review of Quantitative Nondestructive Evaluation Vol. 28, D.O. Thompson, D. E.