Advanced statistical learning method for multi-physics NDT-NDE

Abstract : This work presents an innovative multi-physics (MP) Learning-by-Examples (LBE) inversion methodology for real-time non-destructive testing (NDT). Eddy Current Testing (ECT) and Ultrasonic Testing (UT) data are effectively combined to deal with the localization and characterization of a crack inside a conductive structure. An adaptive sampling strategy is applied on ECT-UT data in order to build an optimal (i.e., having minimum cardinality and highly informative) training set. Support vector regression (SVR) is exploited to obtain a computationally-efficient and accurate surrogate model of the inverse operator and, subsequently, to perform real-time inversions on previously-unseen measurements provided by simulations. The robustness of the proposed MP-LBE approach is numerically assessed in presence of synthetic noisy test set and compared to single-physic (i.e., ECT or UT) inversion.
Type de document :
Article dans une revue
Journal of Physics: Conference Series, IOP Publishing, 2018, 1131, pp.1-7
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01962666
Contributeur : Andrea Massa <>
Soumis le : jeudi 20 décembre 2018 - 17:22:37
Dernière modification le : jeudi 10 janvier 2019 - 11:39:58

Identifiants

  • HAL Id : hal-01962666, version 1

Citation

Shamim Ahmed, Pier Calmon, Roberto Miorelli, Christophe Reboud, Andrea Massa. Advanced statistical learning method for multi-physics NDT-NDE. Journal of Physics: Conference Series, IOP Publishing, 2018, 1131, pp.1-7. 〈hal-01962666〉

Partager

Métriques

Consultations de la notice

36