Structural Engineering and Mechanics

  • 제81권6호
  • /
  • Pages.665-675
  • /
  • 2022
  • /
  • 1225-4568(pISSN)
  • /
  • 1598-6217(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

A novel method for generation and prediction of crack propagation in gravity dams

  • Zhang, Kefan (College of Liberal Art and Science, National University of Defense Technology) ;
  • Lu, Fangyun (College of Liberal Art and Science, National University of Defense Technology) ;
  • Peng, Yong (College of Liberal Art and Science, National University of Defense Technology) ;
  • Li, Xiangyu (College of Liberal Art and Science, National University of Defense Technology)
  • 투고 : 2021.06.30
  • 심사 : 2021.12.13
  • 발행 : 2022.03.25
⟨ 이전 논문 다음 논문 ⟩

초록

The safety problems of giant hydraulic structures such as dams caused by terrorist attacks, earthquakes, and wars often have an important impact on a country's economy and people's livelihood. For the national defense department, timely and effective assessment of damage to or impending damage to dams and other structures is an important issue related to the safety of people's lives and property. In the field of damage assessment and vulnerability analysis, it is usually necessary to give the damage assessment results within a few minutes to determine the physical damage (crack length, crater size, etc.) and functional damage (decreased power generation capacity, dam stability descent, etc.), so that other defense and security departments can take corresponding measures to control potential other hazards. Although traditional numerical calculation methods can accurately calculate the crack length and crater size under certain combat conditions, it usually takes a long time and is not suitable for rapid damage assessment. In order to solve similar problems, this article combines simulation calculation methods with machine learning technology interdisciplinary. First, the common concrete gravity dam shape was selected as the simulation calculation object, and XFEM (Extended Finite Element Method) was used to simulate and calculate 19 cracks with different initial positions. Then, an LSTM (Long-Short Term Memory) machine learning model was established. 15 crack paths were selected as the training set and others were set for test. At last, the LSTM model was trained by the training set, and the prediction results on the crack path were compared with the test set. The results show that this method can be used to predict the crack propagation path rapidly and accurately. In general, this article explores the application of machine learning related technologies in the field of mechanics. It has broad application prospects in the fields of damage assessment and vulnerability analysis.

키워드

과제정보

The project was supported by the National Natural Science Foundations of China (11902355).

참고문헌

  1. Bayar, G. and Bilir, T. (2019), "A novel study for the estimation of crack propagation in concrete using machine learning algorithms", Constr. Build. Mater., 215, 670-685. https://doi.org/10.1016/j.conbuildmat.2019.04.227.
  2. Belytschko, T., Gracie, R. and Ventura, G. (2009), "A review of extended/generalized finite element methods for material modeling", Model. Simul. Mater. Sci., 17(4), 1-24. https://doi.org/10.1088/09650393/17/4/043001.
  3. Corps, U.A. (1995), Gravity Dam Design, Engineers O, USA.
  4. Dai, B., Gu, C. and Zhao, E. (2019), "Improved online sequential extreme learning machine for identifying crack behavior in concrete dam", Adv. Struct. Eng., 22(2), 402-412. https://doi.org/10.1177/1369433218788635.
  5. Ding, B.Y., Wang, G.B. and Huang, S.P. (1994), "A review on causes of cracking in domestic concrete dams and preventive measures", Water Resour. Hydrop. Eng., 4, 12-18. https://doi.org/CNKI:SUN:SJWJ.0.1994-04-002.
  6. Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K. and Darrell, T. (2015), "Long-term recurrent convolutional networks for visual recognition and description", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2625-2634.
  7. Dong, W., Song, S., Zhang, B. and Yang, D. (2019), "SIF-based fracture criterion of rock-concrete interface and its application to the prediction of cracking paths in gravity dam", Eng. Fract. Mech., 221, 106686. https://doi.org/10.1016/j.engfracmech.2019.106686.
  8. Ford, E., Maneparambil, K. and Rajan, S. (2021), "Machine learning-based accelerated property prediction of two-phase materials using microstructural descriptors and finite element analysis", Comput. Mater. Sci., 191(7), 110328. https://doi.org/10.1016/j.commatsci.2021.110328.
  9. Frechet and Maurice, M. (1906), "Sur quelques points du calcul fonctionnel", Rendiconti del Circolo Matematico di Palermo (1884-1940), 22(1), 1-72. https://doi.org/10.1007/BF03018603.
  10. Ganasan, R., Tan, C.G., Ibrahim, Z., Nazri, F.M., Sherif, M.M. and El-Shafie, A. (2021), "Development of crack width prediction models for RC beam-column joint subjected to lateral cyclic loading using machine learning", Appl. Sci., 11(16), 7700. https://doi.org/10.3390/app11167700.
  11. Gong, D.G., Qu, Z.Q. and Li, J.X. (2016), "Extended finite element simulation of hydraulic fracture based on ABAQUS platform", Rock Soil Mech., 37(5), 1512-1520. https://doi.org/10.16285/j.rsm.2016.05.036.
  12. Graves, A. (2012), Supervised Sequence Labelling with Recurrent Neural Networks, Springer, Germany.
  13. Hanson, J., Yang, Y.D. and Paliwal, K. (2017), "Improving protein disorder prediction by deep bidirectional long short-term memory recurrent neural networks", Bioinform., 33(5), 685-692. https://doi.org/10.1093/bioinformatics/btw678.
  14. Hochreiter, S. and Schmidhuber, J. (1997), "Long short-term memory", Neur. Comput., 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735.
  15. International Commission on Large Dams (1984), World Register of Dams, Washington, USA.
  16. Jekel, C.F., Venter, G. and Venter, M.P. (2019), "Similarity measures for identifying material parameters from hysteresis loops using inverse analysis", Int. J. Mater. Form., 12(3), 355-378. https://doi.org/10.1007/s12289-018-1421-8.
  17. Jin, H.L., Wang, B. and Wang, Y.P. (2018), "Experimental study on near-field shock wave propagation of underwater explosion of TNT with different charge shapes", Chin. J. Explos. Propel., 41(5), 461-500. https://doi.org/CNKI:SUN:BGXB.0.2018-05-009.
  18. Li, D.Z. (2009), "Numerical analysis of dynamic behavior of RC slabs under blast loading", Tran. Tianjin Univ., 1, 61-64. https://doi.org/10.1007/s12209-009-0012-7.
  19. Li, Y., Bao, T. and Shu, X. (2020), "A Hybrid model integrating principal component analysis, fuzzy C-means, and gaussian process regression for dam deformation prediction", Arab. J. Sci. Eng., Appl. Acoust., 46, 4293-4306. https://doi.org/10.1007/s13369-020-04923-7.
  20. Lin, J.Y. (2019), Hydraulic Structure, China Water and Power Press, Beijing, China.
  21. Ma, X.L., Tao, Z.M. and Wang, Y.H. (2015), "Long short-term memory neural network for traffic speed prediction using remote microwave sensor data", Transp. Res. Part C: Emerg. Technol., 54, 187-197. https://doi.org/10.1016/j.trc.2015.03.014.
  22. Masoud, A. and Zhang, C.W. (2021), "Dynamic vulnerability assessment and damage prediction of RC columns subjected to severe impulsive loading", Struct. Eng. Mech., 77(4), 441-461. https://doi.org/10.12989/sem.2021.77.4.441.
  23. Mo, S.N., Dolbow, J. and Belytschko, T. (1999), "A finite element method for crack growth without remeshing", Int. J. Numer. Meth. Eng., 46(1), 131-150. https://doi.org/10.1002/(SICI)1097-0207(19990910)46:13.0.CO;2-J.
  24. Muir, C., Swaminathan, B., Almansour, A.S., Sevener, K., Smith, C., Presby, M., ... & Daly, S. (2021), "Damage mechanism identification in composites via machine learning and acoustic emission", Comput. Mater., 7(1), 1-15. https://doi.org/10.1038/s41524021-00565-x.
  25. Qiu, L., Shen, Z. and Fuheng, M.A. (2019), "Application of MLR-Legendre polynomials model in concrete dam crack opening prediction", Hydro-Sci. Eng., 2, 111-119. https://doi.org/10.16198/j.cnki.1009-640X.2019.02.016.
  26. Rafiei, M.H., Khushefati, W.H., Demirboga, R. and Adeli, H. (2021), "Neural network, machine learning, and evolutionary approaches for concrete material characterization", Appl. Sci., 113(6), 781-789. https://doi.org/10.14359/51689360.
  27. Shojaee, S., Ghelichi, M. and Iz, A.P. (2013), "Combination of isogeometric analysis and extended finite element in linear crack analysis", Struct. Eng. Mech., 48(1), 125-150. https://doi.org/10.12989/sem.2013.48.1.125.
  28. Shu, X. and Min, L.U. (2019), "Dam crack prediction based on GA-BP neural network model", Henan Sci. Technol., 22(1), 79-81. https://doi.org/CNKI:SUN:HNKJ.0.2019-22-030.
  29. Songlin, Z.H.A.N.G., Dongliang, M.A. and Deyu, W.A.N.G. (2021), "Method for plate crack damage detection based on long short-term memory neural network", Appl. Sci., 55(5), 527-535. https://doi.org/10.16183/j.cnki.jsjtu.2020.095.
  30. Srivastav (2015), "Unsupervised learning of video representations using lstms", International Conference on Machine Learning, Lile, France, July.
  31. Stazi, F.L., Budyn, E. and Chessa, J. (2003), "An extended finite element method with higher-order elements for curved cracks", Comput. Mech., 31(1-2), 38-48. https://doi.org/10.1007/s00466-002-0391-2.
  32. Szelg, M. (2020), "Application of an automated digital image-processing method for quantitative assessment of cracking patterns in a lime cement matrix", Sensor., 20(14), 38-59. https://doi.org/10.3390/s20143859.
  33. Tahmina, T.N., Md, M.R. and Dookie, K. (2021), "Damage index based seismic risk generalization for concrete gravity dams considering FFDI", Struct. Eng. Mech., 78(1), 53-66. https://doi.org/10.12989/sem.2021.78.1.053.
  34. Vinyals, O., Toshev, A., Bengio, S. and Erhan, D. (2015), "Show and tell: A neural image caption generator", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3156-3164.
  35. Wang, L., Guo, S.G. and Jiang, Y. (2019), "A method of landing operation evaluation based on curve similarity", J. Transp. Inform. Saf., 37(6), 63-69. https://doi.org/10.3963/j.issn.1674-4861.2019.06.008.
  36. Wang, X., Wu, J. and Liu, C. (2018), "Exploring LSTM based recurrent neural network for failure time series prediction", J. Beijing Univ. Aeronaut. Astronaut, 44(4), 772-784. https://doi.org/10.13700/j.bh.1001-5965.2017.0285.
  37. Xu, Q., Deng, T. and Dong, W. (2009), "Numerical analysis of complete crack propagation process in concrete gravity dams based on crack propagation criterion", J. Arch. Civil Eng., 26(3), 49-54. https://doi.org/10.3321/j.issn:1673-2049.2009.03.008.
  38. Yangtze River Survey, Planning, Design and Research Institute (1995), Design Code for Concrete Gravity Dam SL 319-2018, China.
  39. You, J., Jin, K. and Jiang, Y. (2016), "Prediction of dam cracks based on AFSA-Grey neural network", Yellow River, 39(11), 136-139. https://doi.org/10.3969/j.issn.1000-1379.2016.11.033.
  40. Zhang, C., Long, Y. and Zhou, Y. (2008), "A comparative study for concrete fracture analysis using smeared and discrete crack model", Eng. Mech., 25(3), 80-84. https://doi.org/10.1016/S18725791(08)60058-5.
  41. Zhang, Q., Barri, K., Babanajad, S.K. and Alavi, A.H. (2020), "Real-time detection of cracks on concrete bridge decks using deep learning in the frequency domain", Eng. Fract.Mech., 7(12), 1786-1796. https://doi.org/10.1016/j.eng.2020.07.026.
  42. Zhang, X., Zou, Z. and Wang, K. (2018), "A new rail crack detection method using LSTM network for actual application based on AE technology", Appl. Acoust., 142, 78-86. https://doi.org/10.1016/j.apacoust.2018.08.020.
  43. Zhuang, Z. (2012), Extended Finite Element Method, Tsinghua University Press, Beijing, China.