Application of back-propagation neural networks to defect characterization using eddy current testing

Issue title: Selected papers from the International Symposium on Applied Electromagnetics and Mechanics - ISEM 2019

Guest editors: Jinhao Qiu, Ke Xiong and Hongli Ji

Article type: Research Article

Authors: Zhou, Xinwu^{a; b} | Urayama, Ryoichi^b | Uchimoto, Tetsuya^{b; c} | Takagi, Toshiyuki^{c; d;}

Affiliations: [a] Department of Mechanical Systems Engineering, Graduate School of Engineering, Tohoku University, Sendai, Japan | [b] Institute of Fluid Science, Tohoku University, Sendai, Japan | [c] ELyTMax UMI 3757, CNRS - Université de Lyon - Tohoku University, Tohoku University, Sendai, Japan | [d] Tohoku Forum for Creativity, Organization for Research Promotion, Tohoku University, Sendai, Japan

Correspondence: [*] Corresponding author: Toshiyuki Takagi, ELyTMax UMI 3757, CNRS - Université de Lyon - Tohoku University, Tohoku University, 2-1-1 Katahira, Aoba-ku, Sendai, Japan; Tohoku Forum for Creativity, Organization for Research Promotion, Tohoku University, 2-1-1 Katahira, Aoba-ku, Sendai, Japan. E-mail: [email protected]

Abstract: Eddy current testing is widely used for the automatic detection of defects in conductive materials. However, this method is strongly affected by probe scanning conditions and requires signal analysis to be carried out by experienced inspectors. In this study, back-propagation neural networks were used to predict the depth and length of unknown slits by analyzing eddy current signals in the presence of noise caused by probe lift-off and tilting. The constructed neural networks were shown to predict the depth and length of defects with relative errors of 4.6% and 6.2%, respectively.

Keywords: Eddy current testing, artificial intelligence, back-propagation neural network

DOI: 10.3233/JAE-209394

Journal: International Journal of Applied Electromagnetics and Mechanics, vol. 64, no. 1-4, pp. 817-825, 2020