On the Use of Ferraris Effect and Artificial Intelligence for Characterizing Voids in Aeronautical Weldings

of the modern airplane), one of the most important aspects regards defects detection. In this context, it is important to plan a method able to distinguish the presence or absence of defects within welds as well as a robust procedure able to characterize the defect itself. In this paper, an innovative solution that employs a rotating magnetic field is presented. This approach has been carried out by a Finite Element Model. In this context, the requirement of a perfect state for used welded joints is unavoidable in order to assure both reliability and safety in industrial and civil application. Therefore, a real-time approach able to recognize and estimate defect dimensions starting from the simulated data could be a very useful support for inspectors. To this aim, it is necessary to solve inverse problems which are mostly ill-posed: in this case, the main problems consist on both the accurate formulation of the direct problem and the correct regularization of the inverse electromagnetic problem. In the last decades, a useful and very performing way to regularize ill-posed inverse electromagnetic problems is based on the use of a Neural Network approach, the so called “learning by sample techniques”. Obtained results assure good performances of the implemented method, with very interesting application.