Issue 45

S. Harzallah et al, Frattura ed Integrità Strutturale, 45 (2018) 147-155; DOI: 10.3221/IGF-ESIS.45.12 154 Results from the FEM for every figure have been inversed just for comparisons purposes with the ANN optimization and the true profile of the shape crack. These comparisons are shown in the Fig. 10 and give good maps representing the NN in very short time. However, the approach described in the paper identifies the problem fairly and effectively of admissible solutions for different shapes. Figure 10 : Comparison results from the NN Optimized, FEM profile. C ONCLUSION neural network approach for solving inverse problem in eddy current testing is presented in this paper. The main idea is the introduction of a categorization for the shape reconstruction using a neural network. Results are obtained for a simple eddy current problem using FEM method as an experimental support. On the other hand, NN responses which estimate the forms of cracks are given by the inverse model. It is shown herein that the application of artificial intelligence can be a good substitute or a help of the NDT operators’ work. R EFERENCES [1] Harzallah, S. Chabaat, M. and Chabane, K. (2017). Numerical study of eddy current by Finite Element Method for cracks detection in structures, Frattura ed Integrità Strutturale, 39, pp. 282-290. DOI: 10.3221/IGF-ESIS.39.26. [2] Hamia, R., Cordier, C. and Dolabdjian, C. (2014). Eddy-current non-destructive testing system for the determination of crack orientation, NDT & E International, 61, pp.. 24–28. [3] Harzallah, S. and Chabaat, M. (2017). 3D-FEM computation and experimental study of eddy currents for characterization of surface cracks. Int. J. of Structural Integrity, 8(5), pp.603-610, DOI: 10.1108/IJSI-02-2017-0013. 0.04 0.045 0.05 0.055 0.06 0.065 0.07 -4.5 -4 -3.5 -3 -2.5 -2 -1.5 -1 -0.5 0 0.5 FEM NN Optimized 0.04 0.045 0.05 0.055 0.06 0.065 -4 -3.5 -3 -2.5 -2 -1.5 -1 -0.5 0 0.5 FEM NNOptimized 0.03 0.035 0.04 0.045 0.05 0.055 0.06 0.065 -4 -3.5 -3 -2.5 -2 -1.5 -1 -0.5 0 0.5 NN Optimized FEM A