Materials characterization by Inverse Neural Network approach

Carcangiu, S.;Fanni, A.;Montisci, A.;Cardelli, E.;Faba, A.;Quondam, S.

2016-01-01

---

Abstract

An Inverse Neural Network approach is proposed to solve inverse problems in the field of material characterization in different electrical engineering applications. The flexibility and robustness of the inverse approach is demonstrated making reference to two different problems: the model identification of a magnetic material and the electric capacitance tomography of a polymeric material.