Solution of Inverse Problems in Electromagnetic NDT Using Neural Networks

• Autorzy: Ayad A. , Benhamida F. , Bendaoud A. , Bihan Y. L. , Bensetti M.

Warianty tytułu

PL

Rozwiązanie problemu odwrotnego w defektoskopii elektromagnetycznej przy wykorzystaniu sieci neuronowych

• Języki publikacji: EN

Abstrakty

EN

This paper presents a technique for solving inverse problems in electromagnetic nondestructive testing (NDT), using neural networks (NN). They are trained to approximate the mapping from the signal to the defect space. A crucial problem is signal inversion, wherein the defects profiles must be recovered from calculated signals by using finite element method (FEM), this method give good results by using the refinement mesh but in very long time. The idea of this paper is the exploitation of the FEM but with a middle mesh where the results are approached in short time. This signal was exploited in the inversion problem, where the maps represent the defects in the plate. The inversion results obtained with the NN are presented. The presented approach has permitted to realize good maps in a very reasonable training time with respect to others approaches.

PL

Przedstawiono metodę rozwiązania odwrotnego z wykorzystaniem sieci neuronowych stosowanego w defektoskopii. Sieć jest trenowana na podstawie próbek z defektami. Pozwala to na stosowanie metody FEM ze znacznie mniejszą liczbą oczek.

Słowa kluczowe

EN

electrical technology; Eddy current; finite element method; defect characterization; neural networks; inverse problems

PL

metoda prądów wirowych; defektoskopia; sieci neuronowe; elektrotechnika

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2011
• Tom: R. 87, nr 9a
• Strony: 330--333
• Opis fizyczny: Bibliogr. 12 poz., rys., tab., wykr.

Twórcy

autor

Ayad A.

autor

Benhamida F.

autor

Bendaoud A.

autor

Bihan Y. L.

autor

Bensetti M.

• University of Djilali Liabes, IRECOM Laboratory, Engineering Faculty, Sidi Bel Abbes, Algeria,

Bibliografia

• [1] N. Ida, R. Palanismy, and W. Lord “Eddy Current Probe Design Using Finite Element Analysis”. Materials Evaluation, Nov.pp1389-94, 1983.
• [2] S. S. Udpa “Non-destructive Testing Handbook- Electromagnetic testing”, Third Edition,5, ASNT,chap-4,2004.
• [3] N. Ida “Alternative approaches to the numerical calculation of impedance”. NDT International Vol 21 1 February 1988.
• [4] M. Angeli, E. cardelli, “Numerical Analysis of Eddy Current Non-Destructive Testing (JSAEM Benchmark, Poblem#2 –Flat Plates with cracks” , Proc.of the E’NDE conference, Paris, September 1998, in Electromagnetic Nondestructive Evaluation(III), pp.303-314,IOS Press,1999.
• [5] S-J Song, Y-K Shin “Eddy current flaw characterization in tubes by neural networks and finite element modeling”. NDT&E International Vol 33,pp 233-243, 2000.
• [6] H. Pingjie, G. Zhang, Z. Wu, J. Cai, Z. Zhou “Inspection of defects in conductive multi-layered structures by an eddy current scanning technique: Simulation and experiments”. NDT&E International Vol 39,pp 578-584,15 June 2006.
• [7] M.Yan, S. Udpa, M. Shreekanth, Y. Sun, S. Paul, and W. Lord “Solution of inverse problems in electromagnetic NDE using finite element methods”, IEEE Transactions on Magnetics, Vol.34, No 5, September 1998.
• [8] ANSYS Theory Reference 001099 9th Editions.SAS IP,Inc.
• [9] F. Foucher, X. Brunotte, A. Kalai, Y. Le Floch G. Pichenot, D. Prémel “Simulation of eddy current testing with civa® and flux®” , Journées COFREND 2005.
• [10] A. Ayad, A. Semmah, A. Lahcen, Y. Ramdani“ Numerical and Analytical Analysis of Eddy Current Non Destructive Testing in JSAEM Benchmark ” Journal of Electrical Engineering JEE, Vol 08, Edition 03, 2008.
• [11] A. Ayad, A. Semmah, Y.Ramdani, H. Hamdaoui, K. M. Faraoun “ Design of an Optimal Neural Network for Evaluating the Thickness and Conductivity of the Metal Sheet ” Journal of Computer Science INFOCOMP, Vol 07,N°02,pp52-57, June 2008.
• [12] Hagan, M.T., Menhaj, M., "Training feedforward networks with the Marquardt algorithm". IEEE Transactions on Neural Networks.v.5, No.6, p989- 993, 1994.