Surface cracks in reinforced concrete (RC) bridge structural elements pose significant concerns regarding durability, strength, and serviceability. Micro-cracks, if left unchecked, can propagate into macro-cracks due to several factors leading to structural health deteriorations and increased maintenance costs. Generative Adversarial Networks (GANs), which leverage Convolutional Neural Networks (CNNs), provide a powerful alternative by learning from unstructured image datasets and generating realistic visual outputs. This study presents a novel GAN-based mechanism referred to as CrackGAN for predicting the propagation patterns of cracks in RC bridge elements. The model synthesizes realistic crack growth patterns and allows for predictive visualization of their evolution. Validation of predicted results were validated by comparing them with real time crack propagation recorded in laboratory tests on RC beams and slabs. The results were evaluated using Structural Similarity Index Measure (SSIM) and Learned Perceptual Image Patch Similarity (LPIPS), demonstrating strong agreement between predicted and experimentally observed crack propagation.
AnitescuCAtroshchenkoEAlajlanN, et al. (2019) Artificial neural network methods for the solution of second order boundary value problems. Computers, Materials & Continua59(1): 345–359. https://doi.org/10.32604/cmc.2019.06641
2.
BayarGBilirT (2019) A novel study for the estimation of crack propagation in concrete using machine learning algorithms. Construction and Building Materials215: 670–685. https://doi.org/10.1016/j.conbuildmat.2019.04.227
3.
BianchiEHebdonM, (2021). Forecasting infrastructure deterioration with inverse GANs. In: Applications of machine learning 2021, SPIE, Vol. 11843, p. 1184304.
4.
ChakrabortyAAnitescuCZhuangX, et al. (2022) Domain adaptation based transfer learning approach for solving PDEs on complex geometries. Engineering with Computers38(5): 4569–4588. https://doi.org/10.1007/s00366-022-01661-2
GaoXTongB (2023) MRA-UNet: balancing speed and accuracy in road crack segmentation network. Signal, Image and Video Processing17(5): 2093–2100. https://doi.org/10.1007/s11760-022-02423-9
7.
GoodfellowI.J.Pouget-AbadieJ.MirzaM.XuB.Warde-FarleyD.OzairS.CourvilleA.BengioY., 2014. Generative adversarial nets. Advances in neural information processing systems, 27. 1406.2661. arXiv.
8.
GoswamiSAnitescuCChakrabortyS, et al. (2020) Transfer learning enhanced physics informed neural network for phase-field modeling of fracture. Theoretical and Applied Fracture Mechanics106: 102447. https://doi.org/10.1016/j.tafmec.2019.102447
9.
HanXZhaoZChenL, et al. (2022) Structural damage-causing concrete cracking detection based on a deep-learning method. Construction and Building Materials337: 127562. https://doi.org/10.1016/j.conbuildmat.2022.127562
10.
HasanSAsadRBArifFKhanA-R. Enhancing structural health monitoring: Conditional GAN-based crack detection in concrete and asphalt surfaces. Advances in Structural Engineering. 2025. https://doi.org/10.1177/13694332251381215
11.
HoTTKimTKimWJ, et al. (2021) A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects. Scientific Reports11(1): 34. https://doi.org/10.1038/s41598-020-79336-5
12.
HoTTKimGTKimT, et al. (2022) Classification of rotator cuff tears in ultrasound images using deep learning models. Medical, & Biological Engineering & Computing60(5): 1269–1278. https://doi.org/10.1007/s11517-022-02502-6
13.
HsiehYATsaiYJ (2020) Machine learning for crack detection: review and model performance comparison. Journal of Computing in Civil Engineering34(5): 04020038. https://doi.org/10.1061/(asce)cp.1943-5487.0000918
IsolaPZhuJYZhouT, et al. (2016) Image-to-image translation with conditional adversarial networks:1611.07004. arXiv.
16.
JiaoPYeXZhangC, et al. (2024) Vision‐based real‐time marine and offshore structural health monitoring system using underwater robots. Computer-Aided Civil and Infrastructure Engineering39(2): 281–299. https://doi.org/10.1111/mice.12993
17.
KimHAhnEShinM, et al. (2019) Crack and noncrack classification from concrete surface images using machine learning. Structural Health Monitoring18(3): 725–738. https://doi.org/10.1177/1475921718768747
18.
KochCGeorgievaKKasireddyV, et al. (2015) A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure. Advanced Engineering Informatics29(2): 196–210. https://doi.org/10.1016/j.aei.2015.01.008
19.
LaxmanKCRossAAiL, et al. (2023) Determination of vehicle loads on bridges by acoustic emission and an improved ensemble artificial neural network. Construction and Building Materials364: 129844.
20.
LinSWangY (2020) Crack-depth estimation in concrete elements using ultrasonic shear-horizontal waves. Journal of Performance of Constructed Facilities34(4): 04020064. https://doi.org/10.1061/(asce)cf.1943-5509.0001473
21.
LongXYZhaoSKJiangC, et al. (2021) Deep learning-based planar crack damage evaluation using convolutional neural networks. Engineering Fracture Mechanics246: 107604. https://doi.org/10.1016/j.engfracmech.2021.107604
ParkSSTranVTDoanNP, et al., (2021). Evaluation of damage level for ground settlement using the convolutional neural network. In CIGOS 2021, Emerging Technologies and Applications for Green Infrastructure: Proceedings of the 6th International Conference on Geotechnics, Civil Engineering and Structures, Singapore, 2021, October, pp. 1261-1268. Springer Nature Singapore.
24.
PharesBMWasherGARolanderDD, et al. (2004) Routine highway bridge inspection condition documentation accuracy and reliability. Journal of Bridge Engineering9(4): 403–413. https://doi.org/10.1061/(asce)1084-0702(2004)9:4(403)
25.
RamzanBMalikMSMartarelliM, et al. (2021) Pixel frequency based railroad surface flaw detection using active infrared thermography for structural health monitoring. Case Studies in Thermal Engineering27: 101234. https://doi.org/10.1016/j.csite.2021.101234
26.
RaoASNguyenTPalaniswamiM, et al. (2021) Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure. Structural Health Monitoring20(4): 2124–2142. https://doi.org/10.1177/1475921720965445
27.
SowdenAM (ed) (1990) The Maintenance of Brick and Stone Masonry Structures. Taylor & Francis.
28.
TanXBaoY (2021) Measuring crack width using a distributed fiber optic sensor based on optical frequency domain reflectometry. Measurement172: 108945. https://doi.org/10.1016/j.measurement.2020.108945
29.
TanXFanLHuangY, et al. (2021) Detection, visualization, quantification, and warning of pipe corrosion using distributed fiber optic sensors. Automation in Construction132: 103953. https://doi.org/10.1016/j.autcon.2021.103953
30.
TianJWuXTanX, et al. (2022) Experimental study and analysis model of flexural synergistic effect of reinforced concrete beams strengthened with ECC. Construction and Building Materials352: 128987. https://doi.org/10.1016/j.conbuildmat.2022.128987
31.
ValençaJPuenteIJúlioENBS, et al. (2017) Assessment of cracks on concrete bridges using image processing supported by laser scanning survey. Construction and Building Materials146: 668–678. https://doi.org/10.1016/j.conbuildmat.2017.04.096
32.
WangZBovikACSheikhHR, et al. (2004) Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing13(4): 600–612. https://doi.org/10.1109/tip.2003.819861
33.
ZhangRIsolaPEfrosAA, et al. (2018) The unreasonable effectiveness of deep features as a perceptual metric In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18-23,USA, pp. 586–595.
34.
ZhuJYParkTIsolaP, et al. (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks In: Proceedings of the IEEE International Conference on Computer Vision, July 21-26,USA, pp. 2223–2232.
35.
ZouQZhangZLiQ, et al. (2018) Deepcrack: learning hierarchical convolutional features for crack detection. IEEE Transactions on Image Processing28(3): 1498–1512. https://doi.org/10.1109/tip.2018.2878966
