Title:
Deep Learning for Detection and Characterization of Cracking in Ultra-High-Performance Concrete
Author(s):
Jun Wang, Yail J. Kim, and Chao Liu
Publication:
Structural Journal
Volume:
120
Issue:
3
Appears on pages(s):
3-15
Keywords:
crack-induced damage; deep learning; discrete entity; ultra-high-performance concrete (UHPC)
DOI:
10.14359/51738344
Date:
5/1/2023
Abstract:
This paper presents a novel deep-learning method built upon a
convolutional neural network (CNN) combined with agent-based modeling for crack detection and damage characterization in ultra-high-performance concrete (UHPC). A total of 4400 digital images taken from previous experimental programs are employed to train and validate the proposed vision-based computational approach, including UHPC mixed with steel and synthetic (collated and monofilament polypropylene) fibers. The architecture of the CNN is established by four primary layers (transposed convolution,
batch normalization, activation, and max pooling layers)
and four auxiliary layers (global max pooling, flatten, dropout,
and dense layers), associated with the gradient descent algorithm. In accordance with percolation theory, autonomous agents sense chromatic aberration in the spatial domain of UHPC, differentiate between cracked and uncracked regions, and eliminate morphological noises at the surface level. Processing cropped images at 128 x 128 pixels alongside 64 filters is computationally efficient in the transposed convolution layer. The inclusion of the batch normalization and max pooling layers in conjunction with a rectified
linear unit expedites the calculation procedure. The maximum
error of the estimate is 1.31% in the validation of the developed
framework. The probability of observing cracks in each image is determined through the auxiliary layers with minimal overfitting. Cracking patterns dominate the failure rate of UHPC, and the steel fibers outperform their synthetic counterparts with regard to topological stability.
Related References:
1. Resplendino, J., “Ultra-High Performance Concretes—Recent Realizations and Research Programs on UHPFRC Bridges in France,” Ultra High Performance Concrete (UHPC): Proceedings of the Second International Symposium on Ultra High Performance Concrete, E. Fehling, M. Schmidt, and S. Stürwald, eds., Kassel, Germany, 2008, pp. 31-43.
2. Li, J.; Wu, Z.; Shi, C.; Yuan, Q.; and Zhang, Z., “Durability of Ultra-High Performance Concrete – A Review,” Construction and Building Materials, V. 255, Sept. 2020, Article No. 119296. doi: 10.1016/j.conbuildmat.2020.119296
3. Campione, G., and Giambanco, G., “Analysis of a Collapsed Long-Span Reinforced Concrete Roof in South Italy: Design Mistakes and Material Degradation,” Journal of Performance of Constructed Facilities, ASCE, V. 34, No. 2, Apr. 2020, p. 04020001. doi: 10.1061/(ASCE)CF.1943-5509.0001409
4. Luo, J.; Shao, X.; Fan, W.; Cao, J.; and Deng, S., “Flexural Cracking Behavior and Crack Width Predictions of Composite (Steel + UHPC) Lightweight Deck System,” Engineering Structures, V. 194, Sept. 2019, pp. 120-137. doi: 10.1016/j.engstruct.2019.05.018
5. Pyo, S.; Alkaysi, M.; and El-Tawil, S., “Crack Propagation Speed in Ultra High Performance Concrete (UHPC),” Construction and Building Materials, V. 114, July 2016, pp. 109-118. doi: 10.1016/j.conbuildmat.2016.03.148
6. Arora, A.; Yao, Y.; Mobasher, B.; and Neithalath, N., “Fundamental Insights into the Compressive and Flexural Response of Binder- and Aggregate-Optimized Ultra-High Performance Concrete (UHPC),” Cement and Concrete Composites, V. 98, Apr. 2019, pp. 1-13. doi: 10.1016/j.cemconcomp.2019.01.015
7. Hung, C.-C.; Lee, H.-S.; and Chan, S. N., “Tension-Stiffening Effect in Steel-Reinforced UHPC Composites: Constitutive Model and Effects of Steel Fibers, Loading Patterns, and Rebar Sizes,” Composites Part B: Engineering, V. 158, Feb. 2019, pp. 269-278. doi: 10.1016/j.compositesb.2018.09.091
8. Meng, W., and Khayat, K. H., “Mechanical Properties of Ultra-High-Performance Concrete Enhanced with Graphite Nanoplatelets and Carbon Nanofibers,” Composites Part B: Engineering, V. 107, Dec. 2016, pp. 113-122. doi: 10.1016/j.compositesb.2016.09.069
9. Wang, K.; Zhao, C.; Wu, B.; Deng, K.; and Cui, B., “Fully-Scale Test and Analysis of Fully Dry-Connected Prefabricated Steel-UHPC Composite Beam under Hogging Moments,” Engineering Structures, V. 197, Oct. 2019, Article No. 109380. doi: 10.1016/j.engstruct.2019.109380
10. Liu, H., and Zhang, Y., “Bridge Condition Rating Data Modeling Using Deep Learning Algorithm,” Structure and Infrastructure Engineering, V. 16, No. 10, 2020, pp. 1447-1460. doi: 10.1080/15732479.2020.1712610
11. Hamida, Z., and Goulet, J.-A., “Modeling Infrastructure Degradation from Visual Inspections Using Network‐Scale State‐Space Models,” Structural Control and Health Monitoring, V. 27, No. 9, Sept. 2020, Article No. e2582. doi: 10.1002/stc.2582
12. Koch, C.; Georgieva, K.; Kasireddy, V.; Akinci, B.; and Fieguth, P., “A Review on Computer Vision-Based Defect Detection and Condition Assessment of Concrete and Asphalt Civil Infrastructure,” Advanced Engineering Informatics, V. 29, No. 2, Apr. 2015, pp. 196-210. doi: 10.1016/j.aei.2015.01.008
13. Spencer, B. F. Jr; Hoskere, V.; and Narazaki, Y., “Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring,” Engineering, V. 5, No. 2, Apr. 2019, pp. 199-222. doi: 10.1016/j.eng.2018.11.030
14. Azimi, M.; Eslamlou, A. D.; and Pekcan, G., “Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review,” Sensors (Basel), V. 20, No. 10, May 2020, Article No. 2778. doi: 10.3390/s20102778
15. Valliani, A. A.-A.; Ranti, D.; and Oermann, E. K., “Deep Learning and Neurology: A Systematic Review,” Neurology and Therapy, V. 8, No. 2, Dec. 2019, pp. 351-365. doi: 10.1007/s40120-019-00153-8
16. Ning, Y.; He, S.; Wu, Z.; Xing, C.; and Zhang, L.-J., “A Review of Deep Learning Based Speech Synthesis,” Applied Sciences (Basel), V. 9, No. 19, Oct. 2019, Article No. 4050. doi: 10.3390/app9194050
17. Koumakis, L., “Deep Learning Models in Genomics; Are We There Yet?” Computational and Structural Biotechnology Journal, V. 18, 2020, pp. 1466-1473. doi: 10.1016/j.csbj.2020.06.017
18. Miglani, A., and Kumar, N., “Deep Learning Models for Traffic Flow Prediction in Autonomous Vehicles: A Review, Solutions, and Challenges,” Vehicular Communications, V. 20, Dec. 2019, Article No. 100184. doi: 10.1016/j.vehcom.2019.100184
19. Figueiredo, E.; Moldovan, I.; Santos, A.; Campos, P.; and Costa, J. C. W. A., “Finite Element-Based Machine-Learning Approach to Detect Damage in Bridges under Operational and Environmental Variations,” Journal of Bridge Engineering, ASCE, V. 24, No. 7, July 2019, p. 04019061. doi: 10.1061/(ASCE)BE.1943-5592.0001432
20. Sanchez, L. F. M., and Terra, M., “Using Machine Learning for Condition Assessment of Concrete Infrastructure,” Concrete International, V. 41, No. 11, Nov. 2019, pp. 35-39.
21. Pantoja, M.; Behrouzi, A.; and Fabris, D., “An Introduction to Deep Learning,” Concrete International, V. 40, No. 9, Sept. 2018, pp. 35-41.
22. Mangalathu, S., and Jeon, J.-S., “Machine Learning-Based Failure Mode Recognition of Circular Reinforced Concrete Bridge Columns: Comparative Study,” Journal of Structural Engineering, ASCE, V. 145, No. 10, Oct. 2019, p. 04019104. doi: 10.1061/(ASCE)ST.1943-541X.0002402
23. Bermúdez, J. L., Cognitive Science: An Introduction to the Science of the Mind, Cambridge University Press, Cambridge, UK, 2020.
24. Zhang, Q.; Yang, L. T.; Chen, Z.; and Li, P., “A Survey on Deep Learning for Big Data,” Information Fusion, V. 42, July 2018, pp. 146-157. doi: 10.1016/j.inffus.2017.10.006
25. Krizhevsky, A.; Sutskever, I.; and Hinton, G. E., “ImageNet Classification with Deep Convolutional Neural Networks,” Advances in Neural Information Processing Systems 25 (NIPS 2012), F. Pereira, C. J. Burges, L. Bottou, and K. Q. Weinberger, eds., 2012, 9 pp. doi: 10.1145/306538610.1145/3065386
26. LeCun, Y.; Bengio, Y.; and Hinton, G., “Deep Learning,” Nature, V. 521, No. 7553, 2015, pp. 436-444. doi: 10.1038/nature14539
27. Sadr, H.; Pedram, M. M.; and Teshnehlab, M., “A Robust Sentiment Analysis Method Based on Sequential Combination of Convolutional and Recursive Neural Networks,” Neural Processing Letters, V. 50, No. 3, Dec. 2019, pp. 2745-2761. doi: 10.1007/s11063-019-10049-1
28. Solhmirzaei, R.; Salehi, H.; Kodur, V.; and Naser, M. Z., “Machine Learning Framework for Predicting Failure Mode and Shear Capacity of Ultra High Performance Concrete Beams,” Engineering Structures, V. 224, Dec. 2020, Article No. 111221. doi: 10.1016/j.engstruct.2020.111221
29. Prayogo, D.; Cheng, M.-Y.; Wu, Y.-W.; and Tran, D.-H., “Combining Machine Learning Models via Adaptive Ensemble Weighting for Prediction of Shear Capacity of Reinforced-Concrete Deep Beams,” Engineering with Computers, V. 36, No. 3, July 2020, pp. 1135-1153.
30. Flah, M.; Suleiman, A. R.; and Nehdi, M. L., “Classification and Quantification of Cracks in Concrete Structures Using Deep Learning Image-Based Techniques,” Cement and Concrete Composites, V. 114, Nov. 2020, Article No. 103781. doi: 10.1016/j.cemconcomp.2020.103781
31. Salehi, H., and Burgueño, R., “Emerging Artificial Intelligence Methods in Structural Engineering,” Engineering Structures, V. 171, Sept. 2018, pp. 170-189. doi: 10.1016/j.engstruct.2018.05.084
32. Ye, X. W.; Jin, T.; and Yun, C. B., “A Review on Deep Learning-Based Structural Health Monitoring of Civil Infrastructures,” Smart Structures and Systems, V. 24, No. 5, 2019, pp. 567-585.
33. Hsieh, Y.-A., and Tsai, Y. J., “Machine Learning for Crack Detection: Review and Model Performance Comparison,” Journal of Computing in Civil Engineering, ASCE, V. 34, No. 5, Sept. 2020, p. 04020038. doi: 10.1061/(ASCE)CP.1943-5487.0000918
34. Rawat, W., and Wang, Z., “Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review,” Neural Computation, V. 29, No. 9, Sept. 2017, pp. 2352-2449. doi: 10.1162/neco_a_00990
35. Zhu, Z.; German, S.; and Brilakis, I., “Visual Retrieval of Concrete Crack Properties for Automated Post-Earthquake Structural Safety Evaluation,” Automation in Construction, V. 20, No. 7, Nov. 2011, pp. 874-883. doi: 10.1016/j.autcon.2011.03.004
36. Kim, Y. J., and Wang, J., “Development of Ultra-High-Performance Concrete with Various Silica Admixtures,” ACI Materials Journal, V. 116, No. 2, Mar. 2019, pp. 33-44. doi: 10.14359/51714450
37. Wang, J., and Kim, Y. J., “Functional Characteristics of Ultra-High-Performance Concrete Comprising Various Fibers,” ACI Materials Journal, V. 117, No. 5, Sept. 2020, pp. 179-191. doi: 10.14359/51725978
38. ASTM C39/C39M-15, “Standard Test Method for Compressive Strength of Cylindrical Concrete Specimens,” ASTM International, West Conshohocken, PA, 2015, 7 pp.
39. ASTM C1609/C1609M-12, “Standard Test Method for Flexural Performance of Fiber-Reinforced Concrete (Using Beam with Third-Point Loading),” ASTM International, West Conshohocken, PA, 2012, 9 pp.
40. Gulli, A., and Pal, S., Deep Learning with Keras, Packt Publishing Ltd., Birmingham, UK, 2017.
41. Manaswi, N. K., “Understanding and Working with Keras,” Deep Learning with Applications Using Python: Chatbots and Face, Object, and Speech Recognition With TensorFlow and Keras, Apress Media, New York City, NY, 2018, pp. 31-43.
42. Alarie, S.; Audet, C.; Gheribi, A. E.; Kokkolaras, M.; and Le Digabel, S., “Two Decades of Blackbox Optimization Applications,” EURO Journal on Computational Optimization, V. 9, 2021, Article No. 100011. doi: 10.1016/j.ejco.2021.100011
43. Ray, S., “A Quick Review of Machine Learning Algorithms,” Proceedings, 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), Faridabad, India, 2019, pp. 35-39.
44. Ho, Y., and Wookey, S., “The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabeling,” IEEE Access, V. 8, 2020, pp. 4806-4813. doi: 10.1109/ACCESS.2019.2962617
45. Kingma, D. P., and Ba, J. L., “ADAM: A Method for Stochastic Optimization,” Proceedings, 3rd International Conference on Learning Representations (ICLR 2015), San Diego, CA, 2015, 15 pp.
46. Simonyan, K., and Zisserman, A., “Very Deep Convolutional Networks for Large-Scale Image Recognition,” Proceedings, 3rd International Conference on Learning Representations (ICLR 2015), San Diego, CA, 2015, 14 pp.
47. Roy, S. K.; Krishna, G.; Dubey, S. R.; and Chaudhuri, B. B., “HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification,” IEEE Geoscience and Remote Sensing Letters, V. 17, No. 2, 2020, pp. 277-281. doi: 10.1109/LGRS.2019.2918719
48. Glorot, X., and Bengio, Y., “Understanding the Difficulty of Training Deep Feedforward Neural Networks,” Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS), Y. W. Teh and M. Titterington, eds., Sardinia, Italy, 2010, pp. 249-256.
49. Dumoulin, V. and Visin, F., “A Guide to Convolution Arithmetic for Deep Learning,” 2018, 31 pp.
50. Radiuk, P. M., “Impact of Training Set Batch Size on the Performance of Convolutional Neural Networks for Diverse Datasets,” Information Technology and Management Science, V. 20, No. 1, Dec. 2017, pp. 20-24.
51. Ioffe, S., and Szegedy, C., “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” Proceedings of the 32nd International Conference on Machine Learning (ICML 2015), F. Bach and D. Blei, eds., Lille, France, 2015, pp. 448-456.
52. Güçlütürk, Y.; Güçlü, U.; van Lier, R.; and van Gerven, M. A. J., “Convolutional Sketch Inversion,” Computer Vision – ECCV 2016 Workshops: Amsterdam, the Netherlands: Proceedings, Part I, G. Hua and H. Jégou, eds., Lecture Notes in Computer Science, V. 9913, Springer, Cham, Switzerland, 2016, pp. 810-824. doi: 10.1007/978-3-319-46604-0_56
53. Samui, P.; Roy, S. S.; and Balas, V. E., eds., Handbook of Neural Computation, Academic Press, Cambridge, MA, 2017.
54. Ibrahim, Z.; Isa, D.; Idrus, Z.; Kasiran, Z.; and Roslan, R., “Evaluation of Pooling Layers in Convolutional Neural Network for Script Recognition,” Soft Computing in Data Science: Proceedings of the 5th International Conference (SCDS 2019), M. W. Berry, B. W. Yap, A. Mohamed, and M. Köppen, eds., Iizuka, Japan, 2019, pp. 121-129.
55. Mohamed, K. S., Neuromorphic Computing and Beyond: Parallel, Approximation, Near Memory, and Quantum, Springer, Cham, Switzerland, 2020.
56. Dong, C.; Loy, C. C.; and Tang, X., “Accelerating the Super-Resolution Convolutional Neural Network,” Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, the Netherlands: Proceedings, Part II, B. Leibe, J. Matas, N. Sebe, and M. Welling, eds., Lecture Notes in Computer Science, V. 9906, Springer, Cham, Switzerland, 2016, pp. 391-407.
57. Baldi, P., and Sadowski, P., “Understanding Dropout,” Advances in Neural Information Processing Systems 26: 27th Annual Conference, C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger, eds., Lake Tahoe, NV, 2013, pp. 2814-2822.
58. Nwankpa, C. E.; Ijomah, W.; Gachagan, A.; and Marshall, S., “Activation Functions: Comparison of Trends in Practice and Research for Deep Learning,” 2018, 20 pp.
59. Waldherr, A., and Wettstein, M., “Bridging the Gaps: Using Agent-Based Modeling to Reconcile Data and Theory in Computational Communication Science,” International Journal of Communication, V. 13, 2019, pp. 3976-3999.
60. Wilensky, U., and Rand, W., An Introduction to Agent-Based Modeling: Modeling Natural, Social, and Engineered Complex Systems with NetLogo, MIT Press, Cambridge, MA, 2015.
61. Yamaguchi, T., and Hashimoto, S., “Fast Crack Detection Method for Large-Size Concrete Surface Images Using Percolation-Based Image Processing,” Machine Vision and Applications, V. 21, No. 5, Aug. 2010, pp. 797-809. doi: 10.1007/s00138-009-0189-8
62. Stauffer, D., and Aharony, A., Introduction to Percolation Theory, second edition, Taylor & Francis, London, UK, 2018.
63. Leal da Silva, W. R., and de Lucena, D. S., “Concrete Cracks Detection Based on Deep Learning Image Classification,” Proceedings, V. 2, No. 8, 2018, Article No. 489. doi: 10.3390/ICEM18-05387
64. Jia, S.; Gao, H.; and Hang, X., “Tomato Pests and Diseases Classification Model Based on Optimized Convolution Neural Network,” Journal of Physics: Conference Series, V. 1437, No. 1, 2020, Article No. 012052. doi: 10.1088/1742-6596/1437/1/012052
65. Akkus, Z.; Ali, I.; Sedlář, J.; Agrawal, J. P.; Parney, I. F.; Giannini, C. C.; and Erickson, B. J., “Predicting Deletion of Chromosomal Arms 1p/19q in Low-Grade Gliomas from MR Images Using Machine Intelligence,” Journal of Digital Imaging, V. 30, No. 4, Aug. 2017, pp. 469-476. doi: 10.1007/s10278-017-9984-3
66. Deepak, S., and Ameer, P. M., “Brain Tumor Classification Using Deep CNN Features via Transfer Learning,” Computers in Biology and Medicine, V. 111, Aug. 2019, Article No. 103345. doi: 10.1016/j.compbiomed.2019.103345
67. Ferreira, T., and Rasband, W., “ImageJ User Guide,” National Institutes of Health, Bethesda, MD, 2012, 198 pp.
68. Shah, S. P.; Swartz, S. E.; and Ouyang, C., Fracture Mechanics of Concrete: Applications of Fracture Mechanics to Concrete, Rock and Other Quasi-Brittle Materials, John Wiley & Sons, Inc., New York, NY, 1995, 588 pp.
69. Mandelbrot, B. B., The Fractal Geometry of Nature, Henry Holt & Company, New York, NY, 1983.
70. Farhidzadeh, A.; Dehghan-Niri, E.; Moustafa, A.; Salamone, S.; and Whittaker, A., “Damage Assessment of Reinforced Concrete Structures Using Fractal Analysis of Residual Crack Patterns,” Experimental Mechanics, V. 53, No. 9, Nov. 2013, pp. 1607-1619. doi: 10.1007/s11340-013-976