Article Article
Identification of Corroded Cracks in Reinforced Concrete Based on Deep Learning SCNet Model

In order to improve the efficiency and accuracy of corroded cracks detection and classification in reinforced concrete, a corroded cracks identification model Steel Corrosion Net (SCNet), based on deep learning Convolutional Neural Network (CNN), is proposed. Crack figures are collected by self-shooting, internet search and corrosion test, then the data set of 39,000 pictures is built by data enhancement. Afterward, a SCNet three-classification neural network model is built and tested using TensorFlow learning framework and Python. The SCNet combines massive initial data with a multi hidden layer neural network framework, and achieves feature learning and accurate classification through model training. According to the training and testing accuracy of the model, the structure and parameters of the SCNet network are optimized. The results of SCNet are compared with those obtained by two traditional testing methods. The results show that the proposed SCNet model achieves a classification accuracy of 96.8%, so it can effectively identify and classify the corroded cracks in reinforced concrete, with high accuracy and measurability. Under harsh condition of noise interference, such as shadows and distortions, the proposed SCNet model shows a relatively stable classification performance compared with two traditional methods.



1. K. Bhargava et al., Cem. Concr. Res. 35 (11), 2203–2218 (2005). DOI: 10.1016/j.cemconres.2005.06.007.

2. M. J. Anitha, R. Hemalatha, and S. Radha, Part Adv. Intell. Syst. Comput. Book Series (AISC). 1163, 639–654 (2021). DOI: 10.1007/978-981-15-5029-4_53.

3. X. D. Xu and D. Ph, Jilin Univ. 8–13 (2008). Chinese.

4. M. Kurata et al., J. Struct. Eng. 139 (10), 688–702 (2012). DOI: 10.1061/(ASCE)ST.1943-541X.0000609.

5. S. Jang et al., Smart. Struct. Syst. 6, 439–459 (2010). DOI: 10.12989/SSS.2010.6.5_6.439.

6. Y. J. Cha, J. G. Chen, and O. Buyukozturk, Eng. Struct. 132 (1), 300–313 (2017). DOI: 10.1016/j.engstruct.2016.11.038.

7. G. M. Cai and D. Ph, Beijing Jiaotong Univ. 8–10 (2011). Chinese.

8. A. Landstorm and M. J. Thurley, IEEE J. Sel Top Signal Proc. 6 (7), 866–875 (2012). DOI: 10.1109/JSTSP.2012.2212416.

9. Y. LeCun, Y. Bengio, and G. Hinton, Nature. 521 (7553), 436–444 (2015). DOI: 10.1038/nmeth.3707.

10. D. C. Ciresan et al., Int. Joint Conf. Art. Intell. 15 (6), 1234–1242 (2011). DOI: 10.5591/978-1-57735-516-8/IJCAI11-210.

11. A. Krizhevsky, I. Sutskever, and G. E. Hinton, Commun. ACM 60 (6), 84–90 (2017). DOI: 10.1145/3065386.

12. H. Moon and J. Kim, Proceedings of the 28th ISARC (Seoul, Korea, 2011), pp. 1461–1467. DOI: 10.22260/ISARC2011/0279.

13. L. Zhang et al., IEEE International Conference on Image Processing (ICIP), (2016), pp. 3708–3712. DOI: 10.1109/ICIP.2016.7533052.

14. Y. -J. Cha, W. Choi, and O. Buyukozturk, Comput.-Aided Civil Infrastruct. Eng. 32 (5), 361–378 (2017). DOI: 10.1111/mice.12263.

15. S. Dorafshan, R. Thomas, and M. Maguire, Const. Build. Mater. 186 (20), 1031–1045 (2018). DOI: 10.1016/j.conbuildmat.2018.08.011.

16. S. Li and X. Zhao, Adv. Civ. Eng. 6520620 (2019). DOI: 10.1155/2019/6520620.

17. Y. -J. Cha et al., Comput. Aided Civil Infrastruct. Eng. 00 (4), 1–17 (2017). DOI: 10.1111/mice.12334.

18. W. Choi and Y. -J. Cha, IEEE Trans. Ind. Electron. 99(1–1), (2019). DOI: 10.1109/TIE.2019.2945265.

19. D. H. Kang and Y. -J. Cha, Struct. Health Monit. 21 (5), 2190–2205 (2022). DOI: 10.1177/14759217211053776.

20. D. H. Kang et al., Autom. Constr. 118 (2020). DOI: 10.1016/j.autcon.2020.103291.

21. G. H. Beckman, D. Polyzois, and Y. -J. Cha, Autom. Constr. 99, 114–124 (2019). DOI: 10.1016/j.autcon.2018.12.006.

22. D. H. Kang and Y. -J. Cha, Comput. Aided Civil Infrastruct. Eng. 33, 885–902 (2018). DOI: 10.1111/mice.12375.

23. R. Ali and Y. -J. Cha, Const. Build. Mater. 226(30), 376–387 (2019). DOI: 10.1016/j.conbuildmat.2019.07.293.

24. R. Ali and Y. -J. Cha, Autom. Constr. 141, 104412 (2022). DOI: 10.1016/j.autcon.2022.104412.

25. K. Simonyan and A. Zisserman, Comput. Sci. 53 (07), 88–95 (2014). DOI: 10.48550/arXiv.1409.1556.

26. M. Otieno, H. Beushausen, and M. Alexander, Cem. Concr. Res. 79, 373–385 (2016). DOI: 10.1016/j.cemconres.2015.08.009.

27. Y. Yuan, X. Zhang, and Y. Ji, China Civil Engg. J. 39 (3), 42–46 (2006). DOI: 10.1016/j.jcis.2005.07.059.

28. S. Sukegawa et al., Biomol. 10 (7), 984 (2020). DOI: 10.3390/biom10070984.

29. J. Canny, IEEE Trans. Pattern Anal. Mach. Intell. 8(6), 679–698 (1986). DOI: 10.1016/B978-0-08-051581-6.50024-6.


Usage Shares
Total Views
21 Page Views
Total Shares
0 Tweets
0 PDF Downloads
0 Facebook Shares
Total Usage