Assessing performance of flaw characterization methods through uncertainty propagation

• DOI: 10.1063/1.5031625
• Publication Date: 2018-04-20T17:00:44Z
• Authors: R. Miorelli; F. Le Bourdais; X. Artusi
• Keywords: [PHYS]Physics [physics]; 0211 other engineering and technologies; 02 engineering and technology

International audience<br/>In this work, we assess the inversion performance in terms of crack characterization and localization based on synthetic signals associated to ultrasonic and eddy current physics. More precisely, two different standard iterative inversion algorithms are used to minimize the discrepancy between measurements (i.e., the tested data) and simulations. Furthermore, in order to speed up the computational time and get rid of the computational burden often associated to iterative inversion algorithms, we replace the standard forward solver by a suitable metamodel fit on a database built offline. In a second step, we assess the inversion performance by adding uncertainties on a subset of the database parameters and then, through the metamodel, we propagate these uncertainties within the inversion procedure. The fast propagation of uncertainties enables efficiently evaluating the impact due to the lack of knowledge on some parameters employed to describe the inspection scenarios, which is a situation commonly encountered in the industrial NDE context.<br/>