Title:
Artificial Intelligence for Real-Time Crack Detection of Ultra-High-Performance Concrete
Author(s):
Jung Wang, Chao Liu, and Yail J. Kim
Publication:
Symposium Paper
Volume:
350
Issue:
Appears on pages(s):
153-166
Keywords:
crack-induced damage; deep learning; fibers; ultra-high-performance concrete (UHPC)
DOI:
10.14359/51734321
Date:
11/1/2021
Abstract:
This paper presents and explains an implementation of artificial intelligence for the real-time crack detection of ultra-high-performance concrete (UHPC). A deep learning algorithm is employed to process image data and to identify physical cracks. The state-of-the-art object detection method generates accurate results with small datasets. To provide training and validation images, UHPC specimens are cast with various fibers and loaded per an ASTM standard, including steel and synthetic (collated and monofilament polypropylene) fibers. After testing, sample images are labeled with an annotation tool and the algorithm is trained and validated with an image recognition approach, leading to a mean average precision (mAP) of 99%. The occurrence of cracking and propagation are linked with the applied load level to appraise the influence of the mixed fibers in the crack development of UHPC. It needs to be noted that the adopted deep learning architecture is incapable of quantifying crack width and area directly; therefore, a Java-based image processing program is used to measure these properties of the specimens. The characteristics of the load-induced cracks are dominated by the fiber types. Plain UHPC fails rapidly and the flexural capacity of UHPC increases with the presence of the fibers; especially, the UHPC with steel fibers demonstrates higher flexural capacities than other cases.
Related References:
1. AASHTO. 2010. AASHTO bridge element inspection guide manual, American Association of State Highway and Transportation Officials, Washington, D.C.
2. Jahanshahi, M.R., Jonathan, S.K., Sami, F.M., and Gaurav, S.S. 2009. A survey and evaluation of promising approaches for automatic image-based defect detection of bridge structures, Structure and Infrastructure Engineering, 5(6), 455-486.
3. Rose, P., Aaron, B., Tamir, D.E., Lu, L., Hu, J., and Shi, H. 2014. Supervised computer-vision-based sensing of concrete bridges for crack-detection and assessment, 93rd Annual Meeting of Transportation Research Board, 14 pp.
4. Krizhevsky, A., Sutskever, I., and Hinton, G.E. 2012. ImageNet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems (NIPS 2012), 1-9.
5. Chauhan, R., Ghanshala, K.K., and Joshi, R. C. 2018. Convolutional neural network (CNN) for image detection and recognition, 1st International Conference on Secure Cyber Computing and Communications (ICSCCC), Jalandhar, India, 278-282.
6. Komura, D. and Ishikawa, S. 2018. Machine learning methods for histopathological image analysis, Computational and Structural Biotechnology Journal, 16, 34-42.
7. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed., S.E., Fu., C., and Berg, A.C. 2016. SSD: single shot multibox detector, Lecture Notes in Computer Science, 9905, 21-37.
8. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. 2016. You only look once: unified, real-time object detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 779-788.
9. Girshick, R., Donahue, J., Darrell, T., and Malik, J. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2014), 580-587.
10. Girshick, R. 2015. Fast R-CNN, IEEE International Conference on Computation. Vision (ICCV 2015), 1440-1448.
11. Ren, S., He, K., Girshick, R., and Sun., J. 2017. Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137-1149.
12. Bochkovskiy, A., Wang, C., and Liao, H.M. 2020. YOLOv4: optimal speed and accuracy of object detection, arXiv:2004.10934.
13. Lee, J.H., Sohn, Y.S., and Lee, S.H. 2012. Fire resistance of hybrid fibre-reinforced, ultra-high-strength concrete columns with compressive strength from 120 to 200 MPa, Magazine of Concrete Research, 64(6), 539–550.
14. Ghafari, E., Costa, H., and Julio, E. 2015. Statistical mixture design approach for eco-efficient UHPC, Cement and Concrete Composites, 55, 17-25.
15. FHWA. 2013. Ultra-high performance concrete: a state-of-the-art report for the bridge community, Publication No. FHWA-HRT-13-060, Federal Highway Administration, Washington, D.C.
16. Kim, Y.J. and Wang, J. 2019. Development of ultra-high-performance concrete with various silica admixtures, ACI Materials Journal, 116(2), 33-44.
17. ASTM. 2017. Standard specification for portland cement (C150/C150M-17), ASTM International, West Conshohocken, PA.
18. Strunge, J. and Deuse, T. 2008. Special cements for ultra high performance concrete, 2nd International Symposium on Ultra High Performance Concrete, 61-68.
19. ASTM. 2010. Standard test method for flexural strength of concrete using simple beam with third-point loading (ASTM C78-10), American Society for Testing and Materials, West Conshohocken, PA.
20. Wang, C., Liao, H.M., Wu, Y., Chen, P., Hsieh, J., and Yeh, I. 2020. CSPNet: a new backbone that can enhance learning capability of CNN, IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 390-391.
21. Redmon, J. and Farhadi, A. 2018. YOLOv3: an incremental improvement, arXiv:1804.02767.
22. Liu, S., Qi, L., Qin, H., Shi, J., and Jia., J. 2018. Path aggregation network for instance segmentation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 8759-8768.
23. Maas, A.L., Hannun, A.Y., and Ng, A.Y. 2013. Rectifier nonlinearities improve neural network acoustic models, 30th International Conference on Machine Learning, 28, 6 pp.
24. Xu, D. and Wu, Y. 2020. Improved YOLO-V3 with DenseNet for multi-scale remote sensing target detection. Sensors (Basel), 20(15), 4276.
25. Dutta, A. and Zisserman, A. 2019. The VIA annotation software for images, audio, and video, 27th ACM International Conference on Multimedia, 2276-2279.
26. Nguyen, D.T., Nguyen, T.N., Kim, H., and Lee, H. 2019. A high-throughput and power-efficient FPGA implementation of YOLO CNN for object detection, IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 27(8), 1861-1873.
27. Radiuk, P.M. 2018. Impact of training set batch size on the performance of convolutional neural networks for diverse datasets, Information Technology and Management Science, 20(1), 20-24.
28. Song, P.S., Wu, J.C., Hwang, S., and Sheu, B.C. 2005. Statistical analysis of impact strength and strength reliability of steel-polypropylene hybrid fiber-reinforced concrete, Construction and Building Materials, 19(1), 1-9.
29. Wang, J. and Kim, Y.J. 2020. Functional characteristics of UHPC with various fibers, ACI Materials Journal, 117(5), 179-191.
30. Hearn, N. 1999. Effect of shrinkage and load-induced cracking on water permeability of concrete, ACI Materials Journal, 96(2), 234-241.
31. Ferreira, T., and Rashband, W. 2012. The ImageJ user guide, National Institute of Health, Bethesda, MD.