Diagnosis of Mechanoluminescent Crack Based on Double Deep Learning in Al 7075
Source abstract
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.
Source: openalex_inverted_index · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Thermography and Photoacoustic Techniques · Industrial Vision Systems and Defect Detection · Image Processing Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (34)
Show source-provided references
1. Shin · 2022 · 2105889
2. 10.1063/1.12351010.1063/1.123510 ↗
3. 10.1016/j.isci.2022.10575810.1016/j.isci.2022.105758 ↗
4. 10.1016/j.jlumin.2023.12010910.1016/j.jlumin.2023.120109 ↗
5. Timilsina · 2022 · 2200036
6. 10.1016/j.jallcom.2022.16618710.1016/j.jallcom.2022.166187 ↗
7. Kim · 2018 · 12023
8. 10.1016/j.ijengsci.2017.11.01810.1016/j.ijengsci.2017.11.018 ↗
9. 10.1016/j.ijfatigue.2017.03.01110.1016/j.ijfatigue.2017.03.011 ↗
10. Sohn · 2016 · 34777
11. Sohn · 2016 · 106102
12. K · 2016 · 23
13. Timilsina · 2015 · 2197
14. Sohn · 2015 · 6073
15. 10.1016/j.sna.2014.07.02310.1016/j.sna.2014.07.023 ↗
16. Sohn · 2014 · 1410
17. 10.1088/0957-0233/25/1/01500910.1088/0957-0233/25/1/015009 ↗
18. Timilsina · 2013 · 7197
19. Kim · 2009 · 1915
20. Kim · 2007 · 241916
21. Sohn · 2005 · H161
22. Kim · 2005 · 4337
23. Kim · 2003 · 6437
24. Goodfellow · 2014 · 2672
25. 10.1109/cvpr.2017.63210.1109/cvpr.2017.632 ↗
26. Krizhevsky · 2012 · 1097
27. Lawrence · 1997 · 99
28. Lee · 2021 · 11012
29. Lee · 2021 · e12274
30. Lee · 2020 · 20443
31. Lee · 2020 · 86
32. Lee · 2023 · 2300140
33. 10.3365/kjmm.2021.59.5.34610.3365/kjmm.2021.59.5.346 ↗
34. 10.3365/kjmm.2022.60.10.79310.3365/kjmm.2022.60.10.793 ↗