Smart Structures and Systems

  • 제33권4호
  • /
  • Pages.301-311
  • /
  • 2024
  • /
  • 1738-1584(pISSN)
  • /
  • 1738-1991(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Crack growth prediction on a concrete structure using deep ConvLSTM

  • Man-Sung Kang (Department of Architectural Engineering, Sejong University) ;
  • Yun-Kyu An (Department of Architectural Engineering, Sejong University)
  • 투고 : 2023.10.27
  • 심사 : 2024.04.25
  • 발행 : 2024.04.25
⟨ 이전 논문 다음 논문 ⟩

초록

This paper proposes a deep convolutional long short-term memory (ConvLSTM)-based crack growth prediction technique for predictive maintenance of structures. Since cracks are one of the critical damage types in a structure, their regular inspection has been mandatory for structural safety and serviceability. To effectively establish the structural maintenance plan using the inspection results, crack propagation or growth prediction is essential. However, conventional crack prediction techniques based on mathematical models are not typically suitable for tracking complex nonlinear crack propagation mechanism on civil structures under harsh environmental conditions. To address the technical issue, a field data-driven crack growth prediction technique using ConvLSTM is newly proposed in this study. The proposed technique consists of the four steps: (1) time-series crack image acquisition, (2) target image stabilization, (3) deep learning-based crack detection and quantification and (4) crack growth prediction. The performance of the proposed technique is experimentally validated using a concrete mock-up specimen by applying step-wise bending loads to generate crack growth. The validation test results reveal the prediction accuracy of 94% on average compared with the ground truth obtained by field measurement.

키워드

과제정보

This work was supported by the faculty research fund of Sejong University in 2024 (20240311).

참고문헌

  1. Alahi, A., Ortiz, R. and Vandergheynst, P. (2012), "FREAK: fast retina keypoint", In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, June.
  2. Bae, H. and An, Y.K. (2024), "Computer vision-based statistical crack quantification for concrete structures", Meas., 211, 112632. https://doi.org/10.1016/j.measurement.2023.112632
  3. Bae, H., Jang, K. and An, Y.K. (2021), "Deep super resolution crack network (SrcNet) for improving computer vision-based automated crack detectability in in situ bridges", Struct. Health Monit., 20(4), 1428-1442. https://doi.org/10.1177/147592172091722
  4. Chang, H., Shen, M., Yang, X. and Hou, J.X. (2020), "Uncertainty modeling of fatigue crack growth and probabilistic life prediction for welded joints of nuclear stainless steel", Materials, 13, 3192. https://doi.org/10.3390/ma13143192
  5. Ding, W., Yang, H., Yu, K. and Shu, J.P. (2023), "Crack detection and quantification for concrete structure using UAV and transformer", Automat. Constr., 152, 104929. https://doi.org/10.1016/j.autcon.2023.104929
  6. Geiger, A., Lenz, P., Stiller, C. and Urtasun, R. (2013), "Vision meets robotics: the KITTI dataset", Int. J. Robot Res., 32, 1231-1237. https://doi.org/10.1177/027836491349129
  7. Griffith, A.A. (1921), "The phenomena of rupture and flow in solids", Philos. T. R. Soc. Lond., 221, 163-198. https://doi.org/10.1098/rsta.1921.0006
  8. Harris, C. and Stephens, M. (1988), "A combined corner and edge detector", Proceedings of the 4th Alvey Vision Conference, Manchester, UK, August.
  9. Holt, E. and Leivo, M. (2004), "Cracking risks associated with early age shrinkage", Cement Concrete Compos., 26, 521-530. https://doi.org/10.1016/S0958-9465(03)00068-4
  10. Ioffe, S. and Szegedy, C. (2015), "Batch normalization: accelerating deep network training by reducing internal covariate shift", Proceedings of the 32nd International Conference on Machine Learning, Lille, France, July.
  11. Ismail, M., Muhammad, B. and Ismail, M.E. (2010), "Compressive strength loss and reinforcement degradations of reinforced concrete structure due to long-term exposure", Const. Build Mater., 24, 898-902. https://doi.org/10.1016/j.conbuildmat.2009.12.003
  12. Jang, K., An, Y.K., Kim, B. and Cho, S. (2021), "Automated crack evaluation of a high-rise bridge pier using a ring-type climbing robot", Comput.-Aided Civ. Inf., 36, 14-29. https://doi.org/10.1111/mice.12550
  13. Jang, K., Jung, H. and An, Y.K. (2022), "Automated bridge crack evaluation through deep super resolution network-based hybrid image matching", Automat. Constr., 137, 104229. https://doi.org/10.1016/j.autcon.2022.104229
  14. Jang, K., Park, S., Jung, H., Yoo, H. and An, Y.K. (2024), "Deep learning-based 3D digital damage map of vertical-type tunnels using unmanned fusion data scanning", Comput.-Aided Civ. Inf. 162, 105397. https://doi.org/10.1016/j.autcon.2024.105397
  15. Koh, E., Jin, S.S. and Kim, R.E. (2022), "Physical interpretation of concrete crack images from feature estimation and classification", Smart Struct. Syst., Int. J., 30(4), 385-395. https://doi.org/10.12989/sss.2022.30.4.385
  16. Lai, J., Cai, J., Chen, Q.J., He, A. and Wei, M.Y. (2020), "Influence of crack width on chloride penetration in concrete subjected to alternating wetting-drying cycles", Mater., 13(17), 3801. https://doi.org/10.3390/ma13173801
  17. Lam, L., Lee, S.W. and Suen, C.Y. (1992), "Thinning methodologies-a comprehensive survey", IEEE T. Pattern Anal., 14, 869-885. https://doi.org/10.1109/34.161346
  18. Nair, V. and Hinton, G.E. (2010), "Rectified linear units improve restricted Boltzmann machines", Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel.
  19. Ni, F.T., Zhang, J. and Chen, Z.Q. (2019), "Pixel-level crack delineation in images with convolutional feature fusion", Struct. Control Health Monit., 26(1), e2286. https://doi.org/10.1002/stc.2286
  20. Otsu, N. (1979), "A threshold selection method from gray-level histograms", IEEE T. Syst. Man Cyb., 9, 62-66. https://doi.org/10.1109/TSMC.1979.4310076
  21. Paris, P. and Erdogan F. (1963), "A critical analysis of crack propagation laws", J. Fluid Eng., 85, 528-533. https://doi.org/10.1115/1.3656900
  22. Pierson, K., Rahman, A. and Spear, A.D. (2019), "Predicting microstructure-sensitive fatigue crack path in 3D using machine learning framework", Jom., 71(8), 2680-2694. https://doi.org/10.1007/s11837-019-03572-y
  23. Qi, Y., Yuan, C., Kong, Q., Xiong, B. and Li, P. (2021), "A deep learning-based vision enhancement method for UAV assisted visual inspection of concrete cracks", Smart Struct. Syst., Int. J., 27(6), 1031-1040. https://doi.org/10.12989/sss.2021.27.6.1031
  24. Raja, A., Chukka, S.T. and Jayaganthan, R. (2020), "Prediction of fatigue crack growth behaviour in ultrafine grained Al 2014 alloy using machine learning", Metals, 10(10), 1349. https://doi.org/10.3390/met10101349
  25. Rao, R.P.N. and Ballard, D.H. (1999), "Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects", Nat. Neurosci., 2, 79-87. https://doi.org/10.1038/4580
  26. Reagan, D., Sabato, A. and Niezrecki, C. (2018), "Feasibility of using digital image correlation for unmanned aerial vehicle structural health monitoring of bridges", Struct. Health Monit., 17(5), 1056-1072. https://doi.org/10.1177/1475921717735326
  27. Rovinelli, A., Sangid, M.D., Proudhon, H. and Ludwig, W. (2018), "Using machine learning and a data-driven approach to identify the small fatigue crack driving force in polycrystalline materials", Npj. Comp. Mater., 4(35). https://doi.org/10.1038/s41524-018-0094-7
  28. Safiuddin, M., Kaish, A.B.M., Woon, C.O. and Raman, S.N. (2018), "Early-age cracking in concrete: causes, consequences, remedial measures, and recommendations", Appl. Sci., 8, 1730. https://doi.org/10.3390/app8101730
  29. Special act on the safety control and maintenance of establishments, Land, Infrastructure and Transport, KLRI.
  30. Straka, Z., Svoboda, T. and Hoffmann, M. (2023), "PreCNet: next-frame video prediction based on predictive coding", IEEE T. Neur. Net. Lear., 2023, 1-15. https://doi.org/10.1109/TNNLS.2023.3240857
  31. Torr, P.H.S. and Zisserman, A. (2000), "MLEASC: a new robust estimator with application to estimating image geometry", Comp. Vis. Image Und., 78, 138-156. https://doi.org/10.1006/cviu.1999.0832
  32. Wang, X.Y. (2018), "Effects of crack and climate change on service life of concrete subjected to carbonation", Appl. Sci., 8, 572. https://doi.org/10.3390/app8040572
  33. Wang, B.X., Zhao, W.G., Du, Y.L., Zhang, G.Y. and Yang, Y. (2016), "Prediction of fatigue stress concentration factor using extreme learning machine", Comp. Mater. Sci., 125, 136-145. https://doi.org/10.1016/j.commatsci.2016.08.035
  34. Wu, P., Liu, A., Fu, J., Ye, X. and Zhao, Y. (2022), "Autonomous surface crack identification of concrete structures based on an improved one-stage object detection algorithm", Eng. Strut., 272, 114962. https://doi.org/10.1016/j.engstruct.2022.114962
  35. Xu, Y., Fan, Y.L. and Li, H. (2023), "Lightweight semantic segmentation of complex structural damage recognition for actual bridges", Struct. Health Monit., 22(5). https://doi.org/10.1177/14759217221147015
  36. Yu, F., Chen, H.F., Wang, X., Wian, W.Q., Chen, Y.Y., Liu, F.C., Madhavan, V. and Darrell, T. (2020), "BDD100K: a diverse driving dataset for heterogeneous multitask learning", In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, June.
  37. Yu, S., Yan, C., Liu, C.Y. and Pu, J.P. (2023), "Fatigue life evaluation of parallel steel-wire cables under the combined actions of corrosion and traffic load", Struct. Control Health Monit., 2023, https://doi.org/10.1155/2023/5806751