Innovative machine learning approaches for nondestructive evaluation of materials

Roberto Miorelli (1) , Christophe Reboud (1) , Marco Salucci (2, 3)

1 LSME (CEA, LIST) - Laboratoire de Simulation et de Modélisation Électromagnétique (CEA, LIST)
2 UNITN - Università degli Studi di Trento = University of Trento
3 ELEDIA Research Group - Department of Information Engineering and Computer Science ELEDIA Research Group

This paper deals with a machine learning framework dedicated to nondestructive testing applications, in view of flaws detection and characterization. A supervised learning strategy is used on a training set made of characteristic features, extracted from eddy current testing (ECT) and ultrasounds testing (UT) signals. The approach is first presented and the key role of the feature extraction by means of Partial Least Squares is highlighted. Then, the performance of the proposed data-fusion approach, in terms of both localization and characterization, is compared to that of similar approaches exploiting one inspection technique only.

Mots clés: machine learning; NDT/E; eddy current testing; ultrasound testing

Domaines: Sciences de l'ingénieur [physics]

Roberto Miorelli, Christophe Reboud, Marco Salucci. Innovative machine learning approaches for nondestructive evaluation of materials. EuCAP 2019 - 13th European Conference on Antennas and Propagation, Mar 2019, Cracovie, Poland. ⟨cea-04555968⟩