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.
Innovative Machine Learning Approaches for Nondestructive Evaluation of Materials / Miorelli, R.; Reboud, C.; Salucci, M.. - STAMPA. - (2019), pp. 1-4. (Intervento presentato al convegno 13th European Conference on Antennas and Propagation, EuCAP 2019 tenutosi a Krakow, Poland, Poland nel 31 March-5 April 2019).
Innovative Machine Learning Approaches for Nondestructive Evaluation of Materials
Salucci M.
2019-01-01
Abstract
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.File | Dimensione | Formato | |
---|---|---|---|
Innovative Machine Learning Approaches for Nondestructive Evaluation of Materials.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
691.5 kB
Formato
Adobe PDF
|
691.5 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione