Concrete multi-crack identification and location using back-propagation neural network and digital image correlation

Abstract

This study investigates the effectiveness of using a lightweight back-propagation (BP) neural network combined with digital image correlation (DIC) for the identification and localization of multi-crack on concrete surfaces. First, three-point bending tests were conducted on plain concrete specimens to obtain single-crack propagation data, thereby verifying the capability of the BP neural network in identifying and localizing single cracks. The optimal BP neural network structure for micro-crack identification was determined to consist of two hidden layers with three neurons in each layer. Subsequently, four-point bending tests were performed on reinforced concrete beams to collect experimental data involving the simultaneous propagation of multiple cracks, which were used to evaluate the BP neural network’s performance in multi-crack identification and localization. By integrating wavelet packet analysis and energy variation rate, the optimal BP neural network successfully identified and localized multiple cracks. Compared with convolutional neural networks, the proposed method is more convenient and lightweight, does not require a large number of high-quality crack labels, and demonstrates superior performance in recognizing global cracks.

Graphical abstract

Keywords

concrete / DIC / BP neural network / micro-crack identification / crack location / wavelet packet

References

[1] Liebold F , Wagner F , Giese J , Grzesiak S , de Sousa C , Beckmann B , Pahn M , Marx S , Curbach M , Maas H G . Damage analysis and quality control of carbon-reinforced concrete beams based on in situ computed tomography tests. Buildings, 2023, 13(10): 2669

[2] Rucka M , Wojtczak E , Knak M , Kurpińska M . Characterization of fracture process in polyolefin fibre-reinforced concrete using ultrasonic waves and digital image correlation. Construction and Building Materials, 2021, 280: 122522

[3] Zhang C G , Shu J P , Zhang H , Ning Y J , Yu Y T . Estimation of load-carrying capacity of cracked RC beams using 3D digital twin model integrated with point clouds and images. Engineering Structures, 2024, 310: 118126

[4] Yang L Y , Xie H Z , Fang S Z , Huang C , Yang A Y , Chao Y J . Experimental study on mechanical properties and damage mechanism of basalt fiber reinforced concrete under uniaxial compression. Structures, 2021, 31: 330–340

[5] Spencer B F , Hoskere V , Narazaki Y . Advances in computer vision-based civil infrastructure inspection and monitoring. Engineering, 2019, 5(2): 199–222

[6] Ding W , Shu J P , Debono C J , Prakash V , Seychell D , Borg R P . Quantitative assessment of cracks in concrete structures using active-learning-integrated transformer and unmanned robotic platform. Automation in Construction, 2024, 168: 105829

[7] Zhang P , Wang C , Gao Z , Wang F . A review on fracture properties of steel fiber reinforced concrete. Journal of Building Engineering, 2023, 67: 105975

[8] Han Z Y , Li D Y , Li X B . Dynamic mechanical properties and wave propagation of composite rock-mortar specimens based on SHPB tests. International Journal of Mining Science and Technology, 2022, 32(4): 793–806

[9] Zieliński P , Klimczak M , Tekieli M , Strzępek M . An evaluation of the fracture properties of asphalt concrete mixes using the semi-circular bending method and digital image correlation. Materials, 2025, 18(5): 967

[10] Liu Y , Dai F . A review of experimental and theoretical research on the deformation and failure behavior of rocks subjected to cyclic loading. Journal of Rock Mechanics and Geotechnical Engineering, 2021, 13(5): 1203–1230

[11] Fan X Q , Liu S , Ge F . Fracture properties of early-age concrete based on digital image correlation technique. Engineering Fracture Mechanics, 2025, 315: 110847

[12] Goszczyńska B , Trąmpczyński W , Tworzewska J . Analysis of crack width development in reinforced concrete beams. Materials, 2021, 14(11): 3043

[13] Chakraborty S , Subramaniam K V L . Evaluation of cracking and cohesive fracture response in recycled aggregate concrete. Materials and Structures, 2023, 56(7): 130

[14] Herbers M , Richter B , Gebauer D , Classen M , Marx S . Crack monitoring on concrete structures: comparison of various distributed fiber optic sensors with digital image correlation method. Structural Concrete, 2023, 24(5): 6123–6140

[15] Markin S , Mechtcherine V . Quantification of plastic shrinkage and plastic shrinkage cracking of the 3D printable concretes using 2D digital image correlation. Cement and Concrete Composites, 2023, 139: 105050

[16] Avadh K , Jiradilok P , Bolander J E , Nagai K . Direct observation of the local bond behavior between corroded reinforcing bars and concrete using digital image correlation. Cement and Concrete Composites, 2021, 123: 104180

[17] Ma Y F , Yang J , Su X C , Peng A Y , Wang L , Huang K . Crack propagation characterization of concrete under non-uniform corrosion of steel strand using digital image correlation. Construction and Building Materials, 2024, 455: 139166

[18] Minhajur Rahman M , Zhao X D , D’Antino T , Focacci F , Carloni C . Digital image correlation and cracked hinge model applied to notched beams reinforced with GFRP bars. Engineering Fracture Mechanics, 2024, 301: 109965

[19] Xu X , Chi L Y , Yang J , Lv N . Investigation on the deformation and failure characteristics of concrete in dynamic splitting tests. Materials, 2022, 15(5): 1681

[20] Zhou K Y , Lei D , He J T , Zhang P , Bai P X , Zhu F P . Single micro-damage identification and evaluation in concrete using digital image correlation technology and wavelet analysis. Construction and Building Materials, 2021, 267: 120951

[21] Gehri N , Mata-Falcón J , Kaufmann W . Refined extraction of crack characteristics in large-scale concrete experiments based on digital image correlation. Engineering Structures, 2022, 251: 113486

[22] Pekgöz M , Günaydın O , Güçlüer K . An investigation of concrete stress-strain behavior by the image analysis method. Journal of Construction, 2021, 20(2): 308–320

[23] Ren H S , Qian Z D , Huang W , Bo W , Chen T J , Cao H B . Evaluation of fracture behavior in asphalt concrete through the combination of semi-circular bending test and digital image correlation technology. Construction and Building Materials, 2024, 451: 138854

[24] Shang W , Ning X B , Liu J H , Liu J Z . Failure analysis and evaluation for cracked concrete beam reinforced with CFRP. Theoretical and Applied Fracture Mechanics, 2024, 129: 104222

[25] Lu J , Zhang Y F , Duan L B , Huo Y J , Liu H . Dynamic behavior of CFRP strengthen RC beams based on digital image correlation technology. Engineering Fracture Mechanics, 2022, 271: 108597

[26] Rucka M , Zielińska M . Autonomous ultrasonic imaging and crack localisation in concrete beams during the fracture process. Mechanical Systems and Signal Processing, 2025, 237: 113105

[27] Shams G , Rivard P , Moradian O . Tensile strength and failure behavior of rock-mortar interfaces: direct and indirect measurements. Journal of Rock Mechanics and Geotechnical Engineering, 2024, 16(1): 41–55

[28] Chu P , Xie H P , Hu J J , Li M H , Ren L , Li C B . Anisotropic fracture behavior and corresponding fracture process zone of laminated shale through three-point bending tests. Journal of Rock Mechanics and Geotechnical Engineering, 2025, 17(2): 757–774

[29] Cui S , Xu X F , Chen Z , Zeng G , Ouyang Q X , Li G H . Effect of different sizing agent-treated basalt fibers on bending and cracking performance of reinforced BFRC beams. Construction and Building Materials, 2023, 365: 130037

[30] Gao H B , Sun H N , Wang Z K , Han X Y , Li X R . Bending performance of alkali-activated concrete beams based on digital image correlation method. Materials, 2025, 18(7): 1616

[31] Zhang D , Wang W T , Li V C . micro-crack characterization of loaded Engineered Cementitious Composites via optical scans and photogrammetric analyses. Construction and Building Materials, 2022, 318: 126000

[32] Zhang Y L , Su R K L . Experimental investigation of process of corrosion-induced cover delamination using digital image correlation. Construction and Building Materials, 2021, 312: 125287

[33] Nitka M , Rucka M . 3D DEM modelling of acoustic emission in concrete: insights into elastic waves initiated by micro-cracks. Ultrasonics, 2025, 150: 107599

[34] Wang S Y , Zhuang M L , Xue X . Experimental and numerical investigations on crack intersection and propagation of concrete structures. International Journal of Concrete Structures and Materials, 2022, 16(1): 67

[35] Yan X F , Zhang R , Guo L . Investigation of mixed-mode fracture of UHPC using a hybrid digital image correlation and peridynamics approach. Optics and Lasers in Engineering, 2022, 151: 106918

[36] Yuan Y , Wang L X , Wu Z R , Mou W S , Feng X T , Liu J Z , Wang X H , Yang X . Full-field deformation-aided compressive failure evaluation of seawater concrete using digital image correlation technique. Journal of Marine Science and Engineering, 2022, 10(4): 518

[37] Yu L , Liu Y M , Liu Y G . Advanced monitoring of damage behavior and 3D visualization of fiber distribution in assessing crack resistance mechanisms in steel fiber-reinforced concrete. Journal of Building Engineering, 2024, 97: 110980

[38] Zhou S P , Jiang Z H , Ou Q Y , Liu J K , Wang C L . Analysis on flexural toughness of steel fiber reinforced concrete based on acoustic emission and digital image correlation techniques. Construction and Building Materials, 2025, 492: 143039

[39] Zhang Y L , Su R K L . Experimental study of corrosion-caused corner cracking using digital image correlation. Materials and Structures, 2022, 55(4): 121

[40] Zhang W , Huang J K , Lin J W , Lin B Q , Yang X Z , Huan Y Q . Experimental and numerical investigation of mechanical behavior of segmental joint of shield tunneling strengthened by prestressed CFRP plates. Structures, 2024, 70: 107634

[41] Cha Y J , Ali R , Lewis J , Büyükӧztürk O . Deep learning-based structural health monitoring. Automation in Construction, 2024, 161: 105328

[42] Feng Q , Xie X Y , Wang P H , Qiao H X , Zhang Y S , Ma Y X . Prediction of durability of reinforced concrete based on hybrid-Bp neural network. Construction and Building Materials, 2024, 425: 136091

[43] Gopalakrishnan K , Khaitan S K , Choudhary A , Agrawal A . Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection. Construction and Building Materials, 2017, 157: 322–330

[44] Belloni V , Sjölander A , Ravanelli R , Crespi M , Nascetti A . Crack Monitoring from Motion (CMfM): Crack detection and measurement using cameras with non-fixed positions. Automation in Construction, 2023, 156: 105072

[45] Zhu Z H , Al-Qadi I L . Automated crack propagation measurement on asphalt concrete specimens using an optical flow-based deep neural network. International Journal of Pavement Engineering, 2023, 24(1): 2186407

[46] Zhu K Y , Liu Y Z , Ren X C , Pan B . Panoramic deformation measurement and crack identification in concrete with deep-learning-based multi-camera DIC. Measurement, 2025, 256: 118133

[47] Mishra M , Lourenço P B . Artificial intelligence-assisted visual inspection for cultural heritage: State-of-the-art review. Journal of Cultural Heritage, 2024, 66: 536–550

[48] Li L , Sun H X , Zhang Y , Yu B . Surface cracking and fractal characteristics of bending fractured polypropylene fiber-reinforced geopolymer mortar. Fractal and Fractional, 2021, 5(4): 142

[49] Samaniego E , Anitescu C , Goswami S , Nguyen-Thanh V M , Guo H , Hamdia K , Zhuang X , Rabczuk T . An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications. Computer Methods in Applied Mechanics and Engineering, 2020, 362: 112790

[50] Sun J , Liu Y H , Wang Y Z , Yao Z H , Zheng X P . BINN: A deep learning approach for computational mechanics problems based on boundary integral equations. Computer Methods in Applied Mechanics and Engineering, 2023, 410: 116012

[51] Wang Y Z , Sun J , Rabczuk T , Liu Y H . DCEM: A deep complementary energy method for linear elasticity. International Journal for Numerical Methods in Engineering, 2024, 125(24): e7585

[52] Laqsum S A , Zhu H , Haruna S I , Ibrahim Y E , Amer M , Al-Shawafi A , Ahmed O S . Impact and failure analysis of U-shaped concrete containing polyurethane materials: Deep learning and digital imaging correlation-based approach. Polymers, 2025, 17(9): 1245

[53] Słoński M , Tekieli M . 2D digital image correlation and region-based convolutional neural network in monitoring and evaluation of surface cracks in concrete structural elements. Materials, 2020, 13(16): 3527

[54] Wang Y ZBai J SLin Z YWang Q MAnitescu CSun JEshaghi M SGu Y TFeng X QZhuang X Y, et al. Artificial intelligence for partial differential equations in computational mechanics: A review. 2024, arXiv: 2410.19843

[55] Słoński M . Assessment of cracking development in concrete precast crane beams using optical and deep learning methods. Materials, 2025, 18(4): 731

[56] Wang Y Z , Zhuang X Y , Rabczuk T , Liu Y H. . AI for PDEs in solid mechanics: A review.. Advances in Mechanics, 2025, 55(2): 231–287

[57] Wang J Y , Lei D , Zhou K Y , He J T , Zhu F P , Bai P X . Crack identification in concrete, using digital image correlation and neural network. Frontiers of Structural and Civil Engineering, 2024, 18(4): 536–550

[58] Wang X R , Liu X F , Wang E Y , Liu S X , Shan T C , Labuz J F . micro-cracking characterization in tensile failure of hard coal: an experimental and numerical approach. Rock Mechanics and Rock Engineering, 2024, 57(8): 6441–6460

[59] Wang Z Y , Niu F J , Du W Y , Wang Y R . Durability evaluation of modified basalt fiber reinforced concrete in high altitude cold regions: based on AE, DIC and deep learning prediction. Case Studies in Construction Materials, 2025, 22: e04837

[60] Zhou K Y , Lei D , He J T , Zhang P , Bai P X , Zhu F P . Real-time localization of micro-damage in concrete beams using DIC technology and wavelet packet analysis. Cement and Concrete Composites, 2021, 123: 104198

[61] Bai J S , Lin Z Y , Wang Y Z , Wen J C , Liu Y H , Rabczuk T , Gu Y T , Feng X Q . Energy-based physics-informed neural network for frictionless contact problems under large deformation. Computer Methods in Applied Mechanics and Engineering, 2025, 437: 117787

[62] Wang Y Z , Sun J , Li W , Lu Z Y , Liu Y H . CENN: conservative energy method based on neural networks with subdomains for solving variational problems involving heterogeneous and complex geometries. Computer Methods in Applied Mechanics and Engineering, 2022, 400: 115491

[63] Wang Y Z , Bai J S , Eshaghi M S , Anitescu C , Zhuang X Y , Rabczuk T , Liu Y H . Transfer learning in physics-informed neurals networks: full fine-tuning, lightweight fine-tuning, and low-rank adaptation. International Journal of Mechanical System Dynamics, 2025, 5(2): 212–235

[64] Bai J S , Liu G R , Rabczuk T , Wang Y Z , Feng X Q , Gu Y T . A robust radial point interpolation method empowered with neural network solvers (RPIM-NNS) for nonlinear solid mechanics. Computer Methods in Applied Mechanics and Engineering, 2024, 429: 117159

[65] Eshaghi M S , Anitescu C , Thombre M , Wang Y Z , Zhuang X Y , Rabczuk T . Variational Physics-Informed Neural Operator (VINO) for solving partial differential equations. Computer Methods in Applied Mechanics and Engineering, 2025, 437: 117785

[66] Wang Y Z , Sun J , Bai J S , Anitescu C , Eshaghi M S , Zhuang X Y , Rabczuk T , Liu Y H . Kolmogorov–Arnold-informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov–Arnold Networks. Computer Methods in Applied Mechanics and Engineering, 2025, 433: 117518

RIGHTS & PERMISSIONS

Higher Education Press