NDT-NDE Crack Characterization Through a Learning-by-Examples Approach

Salucci, M. and Anselmi, N. and Oliveri, G. and Massa, A. (2016) NDT-NDE Crack Characterization Through a Learning-by-Examples Approach. Technical Report. University of Trento.

[img] Text
NDT-NDE_Crack_Characterization_Through_a_Learning-by-Examples_Approach.v2.pdf
Download (864kB)

Abstract

This document deals with the characterization of a single narrow crack in a planar conductive structure starting from eddy current testing (ECT) measurements. More precisely, the inversion problem at hand is formulated within the so-called learning-by-examples (LBE) paradigm, by considering the problem of estimating the dimensions of the defect as a regression one. Accordingly, a set of known input-output pairs is generated during an off-line phase and is given as input to a Support Vector Regressor (SVR) prediction model in order to train it on the relationship between defect and corresponding ECT data. Some numerical results are shown in order to verify the effectiveness, as well as the limits, of the proposed LBE technique when dealing with the presence of noise on testing data during the on-line inversion phase.

Item Type: Monograph (Technical Report)
Uncontrolled Keywords: Eddy current testing, inverse scattering, nondestructive testing and evaluation, statistical learning, learning-by-examples, support vector regression
Subjects: M Methodologies > M LBE Learning-by-Example Methods
URI: http://www.eledia.org/students-reports/id/eprint/714

Actions (login required)

View Item View Item
ELEDIA Student Project Activities and Theses Reports is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.