Artificial Neural Networks for Inverse Problems in Damage Detection using Computational and Experimental Eddy Current

Abstract

A new method for computing fracture mechanics parameters applicable for measuring tests relying on Eddy currents is proposed. This method is based on inversing Eddy current with simultaneous use of Artificial Neural Networks (ANN) for the localization and the shape classification of defects. It allows the reconstruction of cracks and damage in the plate profile of an inspected specimen to assess its material properties. The procedure consists on inverting all the Eddy current probe impedance measurements which are recorded according to the position of the probe, the excitation frequency or both. In the non-destructive evaluation by Eddy currents or in the case of an inverse problem which is difficult to solve, results from a lot of variety of concepts such as physics and complex mathematics are needed. The corresponding solution has a significant impact on the characterization of cracks in materials. On the other side, a simulation by a numerical approach based on the finite element method is employed to detect cracks in materials and eventually, study their propagation. It is shown here that this method has emerged as one of the most efficient techniques for prospecting cracks and enables the study of an increase in size of cracks and its propagation in aluminum material. Besides, it can easily predict future defects in different mechanical parts of a given material and be useful in the treatment of materials than the process of changing parts. It has been proven that it gives good results and high performance for different materials.