Visualising delamination in CFRP: a combination of infrared thermography with image translation technique
Source abstract
Abstract
Delamination in carbon fibre reinforced polymer (CFRP) significantly degrades the performance of CFRP, and infrared thermography (IRT) is effective for detecting this type of internal defect. However, detection of some delaminations remains challenging due to either weak or absent indications in IRT results. This study proposed a novel approach to clearly visualise delamination by incorporating image translation technique into IRT. A strategy is constructed specifically for IRT to collect precisely aligned thermogram pairs, and a data augmentation method is developed considering both noise distribution in IRT results and delamination locations. Experiments on CFRP plates reveal that some delaminations, previously undetectable in raw IRT results, are distinctly visualised using the proposed method. Comparison analysis also demonstrates that the developed method exhibits superior performance compared to existing IRT methods. This study provides a new approach to effectively enhance the capability of IRT inspection technique, contributing to an accurate quality evaluation of CFRP material.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Thermography and Photoacoustic Techniques · Infrared Target Detection Methodologies · Calibration and Measurement Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
China University of Petroleum (East China)
China University of Petroleum (Beijing)
Funding
National Key Research and Development Program of China · Natural Science Foundation of Shandong Province, China
References (45)
Show source-provided references
1. 10.1016/j.compositesb.2021.10916710.1016/j.compositesb.2021.109167 ↗
2. 10.1016/j.compstruct.2023.11734510.1016/j.compstruct.2023.117345 ↗
3. 10.1016/j.compositesb.2018.01.00510.1016/j.compositesb.2018.01.005 ↗
4. 10.1016/j.isatra.2014.02.00310.1016/j.isatra.2014.02.003 ↗
5. 10.1016/j.isatra.2022.02.04810.1016/j.isatra.2022.02.048 ↗
6. 10.1016/j.isatra.2020.07.04010.1016/j.isatra.2020.07.040 ↗
7. 10.1177/1475921723122143510.1177/14759217231221435 ↗
8. 10.1016/j.infrared.2023.10457910.1016/j.infrared.2023.104579 ↗
9. 10.1080/10589759.2023.228424810.1080/10589759.2023.2284248 ↗
10. 10.1016/j.ndteint.2024.10314410.1016/j.ndteint.2024.103144 ↗
11. 10.1016/S1350-4495(02)00138-X10.1016/S1350-4495(02)00138-X ↗
12. 10.1117/12.47071110.1117/12.470711 ↗
13. 10.1016/S0263-8223(02)00161-710.1016/S0263-8223(02)00161-7 ↗
14. 10.1016/j.ndteint.2014.06.00310.1016/j.ndteint.2014.06.003 ↗
15. 10.1016/j.autcon.2022.10464310.1016/j.autcon.2022.104643 ↗
16. 10.3390/s1809280910.3390/s18092809 ↗
17. 10.1109/TII.2019.296379510.1109/TII.2019.2963795 ↗
18. 10.1109/JSEN.2021.305639410.1109/JSEN.2021.3056394 ↗
19. 10.1016/j.compositesb.2024.11121610.1016/j.compositesb.2024.111216 ↗
20. 10.1109/TIM.2023.327799610.1109/TIM.2023.3277996 ↗
21. 10.1016/j.ndteint.2023.10303310.1016/j.ndteint.2023.103033 ↗
22. 10.1016/j.compstruct.2022.11554310.1016/j.compstruct.2022.115543 ↗
23. 10.1784/insi.2021.63.9.52910.1784/insi.2021.63.9.529 ↗
24. 10.1016/j.compositesb.2022.11030910.1016/j.compositesb.2022.110309 ↗
25. 10.3390/sym1210170510.3390/sym12101705 ↗
26. 10.1109/ICCIKE47802.2019.900425410.1109/ICCIKE47802.2019.9004254 ↗
27. 10.3390/s2221854010.3390/s22218540 ↗
28. Lai BX, Wang YG. Unsupervised image-to-image translation with style consistency. In: 6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV); Xiamen, Peoples R China: Xiamen Univ; 2023. p. 322–334.
29. 10.1007/s10489-024-05522-x10.1007/s10489-024-05522-x ↗
30. Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. In: 28th Conference on Neural Information Processing Systems (NIPS); Montreal, Canada; 2014. p. 2672–2680.
31. 10.48550/arXiv.1411.178410.48550/arXiv.1411.1784 ↗
32. Isola P, Zhu JY, Zhou TH, et al. IEEE. Image-to-image translation with conditional adversarial networks. In: 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); Honolulu, HI; 2017. p. 5967–5976.
33. 10.1080/17686733.2023.225699810.1080/17686733.2023.2256998 ↗
34. 10.1007/s10845-024-02326-110.1007/s10845-024-02326-1 ↗
35. 10.1007/s10921-021-00827-010.1007/s10921-021-00827-0 ↗
36. 10.1109/TIM.2020.299287310.1109/TIM.2020.2992873 ↗
37. 10.1007/s12559-021-09922-w10.1007/s12559-021-09922-w ↗
38. 10.1190/geo2020-0193.110.1190/geo2020-0193.1 ↗
39. Feng RL, Zhao DL, Zha ZJ. Understanding noise injection in GANs. In: International Conference on Machine Learning (ICML). Electr Network; 2021.
40. 10.1109/TII.2023.326351710.1109/TII.2023.3263517 ↗
41. 10.1109/LGRS.2019.294974510.1109/LGRS.2019.2949745 ↗
42. 10.1016/j.imavis.2004.03.00210.1016/j.imavis.2004.03.002 ↗
43. 10.1007/s11042-020-10035-z10.1007/s11042-020-10035-z ↗
44. 10.1109/TIP.2003.81986110.1109/TIP.2003.819861 ↗
45. 10.1109/TIP.2011.210973010.1109/TIP.2011.2109730 ↗