A nonlinear Kernel-based adaptive learning-by-examples method for robust NDT/NDE of conductive tubes. Issue 6 (13th April 2019)

• Record Type: Journal Article
• Authors: Salucci, Marco; Anselmi, Nicola; Oliveri, Giacomo; Rocca, Paolo; Ahmed, Shamim; Calmon, Pierre; Miorelli, Roberto; Reboud, Christophe; Massa, Andrea
• Is Part Of: Journal of electromagnetic waves and applications. Volume 33:Issue 6(2019)
• Page Start: 669
• Page End: 696
• Publication Date: 2019-04-13
• Subjects: Non-destructive testing and evaluation -- inverse problems -- inverse scattering -- Eddy currents -- learning-by-examples techniques -- Kernel orthogonal partial least squares -- output space filling -- support vector regression -- conductive tubes; Electromagnetic waves -- Periodicals; Electromagnetic devices -- Periodicals; 621.3
• DOI: 10.1080/09205071.2019.1572546
• Languages: English
• ISSNs: 0920-5071

Abstract

ABSTRACT: In this work, the real-time non-destructive testing and evaluation ( NDT/NDE ) of faulty conductive tubes from eddy current ( EC ) measurements is addressed and solved in a computationally efficient way by means of an innovative learning-by-examples ( LBE ) methodology. More specifically, the estimation of the descriptors of a defect embedded within the cylindrical structure under test ( SUT ) is yielded by combining a non-linear feature extraction technique with an adaptive sampling strategy able to uniformly explore the arising feature space. Predictions are then performed during the on-line testing phase by means of a support vector regression ( SVR ). Representative results from a numerical/experimental validation are reported to assess the effectiveness of the proposed approach also in comparison with competitive state-of-the-art approaches.