|
Vol.61, No.12, 958 ~ 965, 2023
|
| Title |
| Diagnosis of Mechanoluminescent Crack Based on Double Deep Learning in Al 7075 |
| 박태오 Tae O Park , 신윤우 Youn Woo Shin , 이승환 Seung Hwan Lee , 좌비오 Pius Jwa , 권용남 Yong Nam Kwon , Suman Timilsina , 장성민 Seong Min Jang , 조철우 Chul Woo Jo , 김지식 Ji Sik Kim |
|
|
|
| Abstract |
| The phenomenon of mechanoluminescence (ML) refers to the emission of light induced by mechanical stimulation applied to mechano-optical materials for example SrAl2O3:Eu,Dy (SAO). Numerous technologies on the basis of ML have been presented to visualize the stress or strain in various structures for the applications including structural health monitoring. As a result, extensive attention has been devoted to the design, synthesis, characteristics, optimizations, and applications of ML materials. However, challenges still remain in the standardization of ML measurement and evaluation, thereby commercially viable ML applications are currently unavailable. To overcome these difficulties, present study proposes ML measurement and evaluation techniques employing the ML fracture mechanics, finite element method, and dual deep learnings. For the effective normalization of visualized ML images under fixed initial ML intensity condition, continuous UV irradiation above the critical ML power density has been subjected to tensile and compact tension (CT) specimens. Therefore, Plastic Stress Intensity Factor (SIF) as well as crack tip stress field have been extracted successfully from normalized ML images based on ML fracture mechanics. To complement and verify the ML analysis, numerical FEM simulation and analytical ASTM calculation have been also provided. Finally, a double deep learning consists of Generative Adversarial Networks (GAN) and Convolutional Neural Networks (CNN) has been trained and tested for the standard evaluation of in-situ ML images.
(Received 31 August, 2023; Accepted 21 October, 2023) |
|
|
| Key Words |
| Al 7075, mechanoluminescence, Plastic Stress Intensity Factor, Generative Adversarial Networks, Convolutional Neural Networks, Structural Health Monitoring |
|
|
 |
|
