volume | PIER Journals

Abstract

Accurately identifying and calibrating reinforcement bars in concrete is a significant challenge due to their invisibility. This paper proposes a deep learning-based method using magnetic resonance eddy penetrating imaging (MREPI) to acquire data on steel bars embedded in concrete. The data is processed into images and input into the Skel-Unet neural network to extract angle and position information of the central axis of the steel bars. Based on this information, the steel bar diameters are determined. A novel image reconstruction method is also introduced to integrate rebar dimension variations for precise calibration. Experimental results show that the Skel-Unet model achieves high accuracy, with training and testing loss values below 0.01, and F1 score reaches 0.7436. The reconstructed images clearly delineate the position, dimensions, and orientation of the rebars, enhancing calibration and nondestructive testing in structural health monitoring.

1. Hu, J. Y., S. S. Zhang, E. Chen, and W. G. Li, "A review on corrosion detection and protection of existing reinforced concrete (RC) structures," Construction and Building Materials, Vol. 325, 126718, 2022. Google Scholar

2. Han, Xiaofeng, Gege Li, Penggang Wang, Zhaoyi Chen, Dongbo Cui, Hai Zhang, Li Tian, Xiangming Zhou, Zuquan Jin, and Tiejun Zhao, "A new method and device for detecting rebars in concrete based on capacitance," Measurement, Vol. 202, 111721, 2022. Google Scholar

3. Goffin, Brigitte, Nemkumar Banthia, and Noboru Yonemitsu, "Use of infrared thermal imaging to detect corrosion of epoxy coated and uncoated rebar in concrete," Construction and Building Materials, Vol. 263, 120162, 2020. Google Scholar

4. Chen, Ruoyu, Khiem T. Tran, Hung Manh La, Taylor Rawlinson, and Kien Dinh, "Detection of delamination and rebar debonding in concrete structures with ultrasonic SH-waveform tomography," Automation in Construction, Vol. 133, 104004, 2022. Google Scholar

5. Ham, Suyun and John S. Popovics, "Application of contactless ultrasound toward automated inspection of concrete structures," Automation in Construction, Vol. 58, 155-164, 2015. Google Scholar

6. Ichi, Eberechi and Sattar Dorafshan, "Effectiveness of infrared thermography for delamination detection in reinforced concrete bridge decks," Automation in Construction, Vol. 142, 104523, 2022. Google Scholar

7. Hwang, Soonkyu, Hyeonjin Kim, Hyung Jin Lim, Peipei Liu, and Hoon Sohn, "Automated visualization of steel structure coating thickness using line laser scanning thermography," Automation in Construction, Vol. 139, 104267, 2022. Google Scholar

8. Ghosh, Rishav, Mukund Lahoti, and Bhoomi Shah, "A succinct review on the use of NMR spectroscopy in monitoring hydration, strength development, and inspection of concrete," Materials Today: Proceedings, Vol. 61, 167-173, 2022. Google Scholar

9. Rubinacci, Guglielmo, Antonello Tamburrino, and Salvatore Ventre, "Concrete rebars inspection by eddy current testing," International Journal of Applied Electromagnetics and Mechanics, Vol. 25, No. 1-4, 333-339, 2007. Google Scholar

10. Pozzer, Sandra, Marcos Paulo Vieira De Souza, Bata Hena, Setayesh Hesam, Reza Khoshkbary Rezayiye, Ehsan Rezazadeh Azar, Fernando Lopez, and Xavier Maldague, "Effect of different imaging modalities on the performance of a CNN: An experimental study on damage segmentation in infrared, visible, and fused images of concrete structures," NDT & E International, Vol. 132, 102709, 2022. Google Scholar

11. Kasai, Naoya, Kouichi Sekino, Seishu Miyazaki, et al., "An eddy current convergence probe with copper core and single detection coil to detect flaws on aluminum plates," NDT & E International, Vol. 132, 102707, 2022. Google Scholar

12. Chen, Haitao, Leng Liao, Jianting Zhou, Hong Zhang, Senhua Zhang, Tian Lan, Zhengren Zhang, and Chunlian Hu, "Magnetic resonance eddy penetrating imaging for detecting reinforcement corrosion in concrete," Automation in Construction, Vol. 165, 105512, 2024. Google Scholar

13. Li, Xiaofeng, Hai Liu, Feng Zhou, Zhongchang Chen, Iraklis Giannakis, and Evert Slob, "Deep learning-based nondestructive evaluation of reinforcement bars using ground-penetrating radar and electromagnetic induction data," Computer-Aided Civil and Infrastructure Engineering, Vol. 37, No. 14, 1834-1853, 2022. Google Scholar

14. Feng, Chu-Qiao, Bao-Luo Li, Yu-Fei Liu, Fu Zhang, Yan Yue, and Jian-Sheng Fan, "Crack assessment using multi-sensor fusion simultaneous localization and mapping (SLAM) and image super-resolution for bridge inspection," Automation in Construction, Vol. 155, 105047, 2023. Google Scholar

15. Wang, Xiangyu, Hai Liu, Xu Meng, Jie Cui, and Yanliang Du, "Enhanced imaging of concealed defects behind concrete linings using Residual Channel attention network for rebar clutter suppression," Automation in Construction, Vol. 166, 105574, 2024. Google Scholar

16. Jeon, Dongho, Min Kyoung Kim, Yeounung Jeong, Jae Eun Oh, Juhyuk Moon, Dong Joo Kim, and Seyoon Yoon, "High-accuracy rebar position detection using deep learning-based frequency-difference electrical resistance tomography," Automation in Construction, Vol. 135, 104116, 2022. Google Scholar

17. Wang, Zhengfang, Jing Wang, Kefu Chen, Zhenpeng Li, Jing Xu, Yao Li, and Qingmei Sui, "Unsupervised learning method for rebar signal suppression and defect signal reconstruction and detection in ground penetrating radar images," Measurement, Vol. 211, 112652, 2023. Google Scholar

18. Nguyen, Nam Hoang, "U-net based skeletonization and bag of tricks," Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2105-2109, Montreal, BC, Canada, Oct. 2021.

19. Kim, Ki-Hwan, Pyoung-Seop Shim, and Seoleun Shin, "An alternative bilinear interpolation method between spherical grids," Atmosphere, Vol. 10, No. 3, 123, 2019. Google Scholar

20. Cordonnier, Jean-Baptiste, Andreas Loukas, and Martin Jaggi, "Multi-head attention: Collaborate instead of concatenate," arXiv preprint arXiv:2006.16362, 2020. Google Scholar

21. Woo, Sanghyun, Jongchan Park, Joon-Young Lee, and In So Kweon, "CBAM: Convolutional block attention module," Proceedings of the European Conference on Computer Vision (ECCV), 3-19, Munich, Germany, Sep. 2018.

22. Qin, Ruoxi, Kai Qiao, Linyuan Wang, Lei Zeng, Jian Chen, and Bin Yan, "Weighted focal loss: An effective loss function to overcome unbalance problem of chest X-ray14," IOP Conference Series: Materials Science and Engineering, Vol. 428, No. 1, 012022, Chengdu, China, Jul. 2018.

23. Zhao, Rongjian, Buyue Qian, Xianli Zhang, Yang Li, Rong Wei, Yang Liu, and Yinggang Pan, "Rethinking dice loss for medical image segmentation," 2020 IEEE International Conference on Data Mining (ICDM), 851-860, Sorrento, Italy, Nov. 2020.

24. Liebel, Lukas and Marco Körner, "Auxiliary tasks in multi-task learning," arXiv preprint arXiv:1805.06334, 2018. Google Scholar

25. Lu, Xiaohu, Jian Yao, Kai Li, and Li Li, "Cannylines: A parameter-free line segment detector," 2015 IEEE International Conference on Image Processing (ICIP), 507-511, Quebec City, QC, Canada, Sep. 2015.

26. Ronneberger, Olaf, Philipp Fischer, and Thomas Brox, "U-Net: Convolutional networks for biomedical image segmentation," Medical Image Computing and Computer-Assisted Intervention --- MICCAI 2015, 234-241, Munich, Germany, Oct. 2015.

Dr. Zhengxuan Zhang

Dr. Jinming Zhang

Professor Leng Liao