journal article·2025-11-05Open access

Ectar: an integrated augmented reality and eddy current array system for non-destructive testing of metallic plate

Ruoxuan Zhu, Saibo She, Tian Meng, Xinnan Zheng, Anthony Peyton, Wuliang Yin

Abstract

We introduce ECTAR, a novel system that fuses eddy current testing (ECT) with augmented reality (AR) to enable real-time data sharing and boost inspection speed. Conventional ECT setups often struggle to deliver intuitive, live visual feedback. ECTAR overcomes this by projecting eddy-current defect maps directly onto the surface under examination as scanning proceeds, so that inspectors see flaw locations superimposed on the actual object through an AR display device. AprilTag markers provide accurate pose estimation; we explore how marker count and AR-device – marker distance affect performance. In tests, our system handled 1280 × 720 video at 30 fps, with average orientation error of 1.17 degrees and position error of 1.42 mm. Furthermore, we developed a deep-learning model that estimates defect depth and displays these depth predictions alongside the defect maps in real time. A demonstration video of ECTAR is available at https://drive.google.com/file/d/1Knqgzeb2X8mTea5V8R_fTkaE1fTRlzs8/view?usp = sharingthis link.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Non-Destructive Testing Techniques · Electromagnetic Compatibility and Measurements · Geophysical and Geoelectrical Methods

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

University of Manchester

References (33)

Show source-provided references
1. 10.1007/978-3-030-58468-9_2410.1007/978-3-030-58468-9_24 ↗
2. 10.1109/TIE.2018.288677510.1109/TIE.2018.2886775 ↗
3. 10.1016/j.optlaseng.2021.10663410.1016/j.optlaseng.2021.106634 ↗
4. 10.1007/s10921-022-00860-710.1007/s10921-022-00860-7 ↗
5. 10.1109/TIM.2022.314422810.1109/TIM.2022.3144228 ↗
6. 10.1016/j.ndteint.2024.10324710.1016/j.ndteint.2024.103247 ↗
7. 10.1109/TMAG.2024.339215610.1109/TMAG.2024.3392156 ↗
8. 10.1109/TIM.2021.311736710.1109/TIM.2021.3117367 ↗
9. 10.1109/JSEN.2020.299547210.1109/JSEN.2020.2995472 ↗
10. 10.1109/JSEN.2021.309355010.1109/JSEN.2021.3093550 ↗
11. 10.1109/MRA.2006.163802210.1109/MRA.2006.1638022 ↗
12. 10.24928/JC3-2017/023110.24928/JC3-2017/0231 ↗
13. 10.1088/1757-899X/767/1/01206210.1088/1757-899X/767/1/012062 ↗
14. 10.1016/j.promfg.2020.02.08110.1016/j.promfg.2020.02.081 ↗
15. 10.1002/dac.322310.1002/dac.3223 ↗
16. 10.1145/1044588.104468210.1145/1044588.1044682 ↗
17. 10.1109/ICUAS48674.2020.921397710.1109/ICUAS48674.2020.9213977 ↗
18. 10.1109/ICMSC.2017.795950510.1109/ICMSC.2017.7959505 ↗
19. 10.1007/s10846-020-01307-910.1007/s10846-020-01307-9 ↗
20. 10.3389/fmats.2020.57680610.3389/fmats.2020.576806 ↗
21. 10.1155/2020/886819010.1155/2020/8868190 ↗
22. Li S, Anees A, Zhong Y, et al. Learning to reconstruct crack profiles for eddy current nondestructive testing In: Second Workshop on Machine Learning and the Physical Sciences (NeurIPS 2019), NeurIPS, Vancouver, Canada; 2019.
23. 10.1109/I2MTC.2019.882685810.1109/I2MTC.2019.8826858 ↗
24. 10.1109/TIM.2023.326734010.1109/TIM.2023.3267340 ↗
25. 10.1109/JSEN.2024.336781610.1109/JSEN.2024.3367816 ↗
26. 10.1109/TIM.2024.341810110.1109/TIM.2024.3418101 ↗
27. 10.1016/j.measurement.2024.11581210.1016/j.measurement.2024.115812 ↗
28. 10.1109/JSEN.2022.318886310.1109/JSEN.2022.3188863 ↗
29. 10.1109/IROS.2016.775961710.1109/IROS.2016.7759617 ↗
30. Hartley R, Zisserman A. Multiple view geometry in computer vision. Cambridge university press; 2003
31. 10.1109/ICRA.2011.597994910.1109/ICRA.2011.5979949 ↗
32. 10.1007/978-981-99-7962-2_3910.1007/978-981-99-7962-2_39 ↗
33. 10.1109/TVCG.2024.335090110.1109/TVCG.2024.3350901 ↗