Computers and Concrete

  • 제32권6호
  • /
  • Pages.625-637
  • /
  • 2023
  • /
  • 1598-8198(pISSN)
  • /
  • 1598-818X(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Numerical data-driven machine learning model to predict the strength reduction of fire damaged RC columns

  • HyunKyoung Kim (Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology) ;
  • Hyo-Gyoung Kwak (Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology) ;
  • Ju-Young Hwang (Department of Civil Engineering, Dong-Eui University)
  • 투고 : 2023.05.24
  • 심사 : 2023.08.31
  • 발행 : 2023.12.25
⟨ 이전 논문 다음 논문 ⟩

초록

The application of ML approaches in determining the resisting capacity of fire damaged RC columns is introduced in this paper, on the basis of analysis data driven ML modeling. Considering the characteristics of the structural behavior of fire damaged RC columns, the representative five approaches of Kernel SVM, ANN, RF, XGB and LGBM are adopted and applied. Additional partial monotonic constraints are adopted in modelling, to ensure the monotone decrease of resisting capacity in RC column with fire exposure time. Furthermore, additional suggestions are also added to mitigate the heterogeneous composition of the training data. Since the use of ML approaches will significantly reduce the computation time in determining the resisting capacity of fire damaged RC columns, which requires many complex solution procedures from the heat transfer analysis to the rigorous nonlinear analyses and their repetition with time, the introduced ML approach can more effectively be used in large complex structures with many RC members. Because of the very small amount of experimental data, the training data are analytically determined from a heat transfer analysis and a subsequent nonlinear finite element (FE) analysis, and their accuracy was previously verified through a correlation study between the numerical results and experimental data. The results obtained from the application of ML approaches show that the resisting capacity of fire damaged RC columns can effectively be predicted by ML approaches.

키워드

과제정보

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2023R1A2C2005101).

참고문헌

  1. ACI (2017), 318 Building Code Requirements for Structural Concrete ACI 318-95, American Concrete Institute, Farmington Hills, MI, USA.
  2. Akiba, T., Sano, S., Yanase, T., Ohta, T. and Koyama, M. (2019), "Optuna: A next-generation hyperparameter optimization framework", Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA, August.
  3. Anderberg, Y. and Thelandersson, S. (1976), Stress and Deformation Characteristics of Concrete: Experimental Investigation and Material Behaviour Model, Lund Institute of Technology, Lund, Sweden.
  4. ANSI/AISC 360-16 (2010), ANSI/AISC 360-10: Specification for Structural Steel Buildings, American Institute of Steel Construction, Chicago, IL, USA.
  5. Baharudin, M.E. (2017), "Modelling the structural response of reinforced concrete slabs exposed to fire: Validation , sensitivity and consequences for analysis and design" , Ph.D. Dissertation, University of Edinburg, Edinburgh, UK.
  6. Banerji, S., Kodur, V. and Solhmirzaei, R. (2020), "Experimental behavior of ultra high performance fiber reinforced concrete beams under fire conditions", Eng. Struct., 208, 110316. https://doi.org/10.1016/j.engstruct.2020.110316.
  7. Biau, G. and Scornet, E. (2016), "A random forest guided tour", Test, 25(2), 197-227. https://doi.org/10.1007/s11749-016-0481-7.
  8. Bratina, S., Saje, M. and Planinc, I. (2007), "The effects of different strain contributions on the response of RC beams in fire", Eng. Struct., 29(3), 418-430. https://doi.org/10.1016/j.engstruct.2006.05.008.
  9. British Standard Institution (2004), Eurocode 1994-1-1: Design of Composite Steel and Concrete Structures - Part 1-1: Gerenal Rules and Rules for Buildings, European Committee for Standardization, European Committee for Standardization, Brussels, Belgium..
  10. British Standard Institution (2004), Eurocode 1994-1-2: Design of Concrete Structures - Part 1-2: Gerenal Rules - Structural Fire Design, European Committee for Standardization, Brussels, Belgium.
  11. Cai, B., Pan, G. and Fu, F. (2020), "Prediction of the postfire flexural capacity of RC beam using GA-BPNN machine learning", J. Perform. Constr. Facil., 34(6), 04020105. https://doi.org/10.1061/(asce)cf.1943-5509.0001514.
  12. Carbonneau, R., Laframboise, K. and Vahidov, R. (2008), "Application of machine learning techniques for supply chain demand forecasting", Eur. J. Operat. Res., 184(3), 1140-1154. https://doi.org/10.1016/j.ejor.2006.12.004.
  13. Castelli, M., Vanneschi, L. and Silva, S. (2013), "Prediction of high performance concrete strength using Genetic Programming with geometric semantic genetic operators", Expert Syst. Appl., 40(17), 6856-6862. https://doi.org/10.1016/j.eswa.2013.06.037.
  14. Chang, C.M., Lin, T.K. and Chang, C.W. (2018), "Applications of neural network models for structural health monitoring based on derived modal properties", Measure., 129, 457-470. https://doi.org/10.1016/j.measurement.2018.07.051.
  15. Chang, Y.F., Chen, Y.H., Sheu, M.S. and Yao, G.C. (2006), "Residual stress-strain relationship for concrete after exposure to high temperatures", Cement Concrete Res., 36(10), 1999-2005. https://doi.org/10.1016/j.cemconres.2006.05.029.
  16. Chaudhary, R.K., Roy, T. and Matsagar, V. (2020), "Member and structural fragility of reinforced concrete structure under fire", J. Struct. Fire Eng., 11(4), 409-435. https://doi.org/10.1108/JSFE-02-2019-0015.
  17. Chen, T. and Guestrin, C. (2016), "XGBoost: A scalable tree boosting system", Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August.
  18. Ding, F.X., Li, Z., Cheng, S.S. and Yu, Z.W. (2018), "Stress redistribution of simply supported reinforced concrete beams under fire conditions", J. Central South Univ., 25(9), 2093-2106. https://doi.org/10.1007/s11771-018-3899-0.
  19. Galatzer-Levy, I.R., Karstoft, K.I., Statnikov, A. and Shalev, A.Y. (2014), "Quantitative forecasting of PTSD from early trauma responses: A machine learning application", J. Psychiatr. Res., 59, 68-76. https://doi.org/10.1016/j.jpsychires.2014.08.017.
  20. Ghafari, E., Bandarabadi, M., Costa, H. and Julio, E. (2015), "Prediction of fresh and hardened state properties of UHPC: Comparative study of statistical mixture design and an artificial neural network model", J. Mater. Civil Eng., 27(11), 04015017. https://doi.org/10.1061/(asce)mt.1943-5533.0001270.
  21. Han, L.H. and Huo, J.S. (2002), "Concrete-filled hollow structural steel columns after exposure to ISO-834 fire standard", J. Struct. Eng., 129(1), 68-78. https://doi.org/10.1061/(ASCE)0733-9445(2003)129:1(68)
  22. Harmathy, T. (1967), "A comprehensive creep model", J. Basic Eng., 89, 496-502. https://doi.org/10.1115/1.3609648.
  23. Huang, Z., Asce, M., Burgess, I.W. and Plank, R.J. (2009), "Three-dimensional analysis of reinforced concrete beam-column structures in fire", J. Struct. Eng., 135(10), 1201-1212. https://doi.org/10.1061/ASCE0733-94452009135:101201.
  24. Hwang, J.Y. and Kwak, H.G. (2018), "Evaluation of post-fire residual resistance of RC columns considering non-mechanical deformations", Fire Saf. J., 100, 128-139. https://doi.org/10.1016/j.firesaf.2018.08.003.
  25. Jiao, P., Roy, M., Barri, K., Zhu, R., Ray, I. and Alavi, A.H. (2019), "High-performance fiber reinforced concrete as a repairing material to normal concrete structures: Experiments, numerical simulations and a machine learning-based prediction model", Constr. Build. Mater., 223, 1167-1181. https://doi.org/10.1016/j.conbuildmat.2019.07.312.
  26. KDS (2021), KDS 14 20 50, Ministry of Land, Infrastructure and Transport, Sejong City, Korea.
  27. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q. and Liu, T.Y. (2017), "Lightgbm: A highly efficient gradient boosting decision tree", Adv. Neural Informat. Process. Syst., 2017, 3147-3155.
  28. Kim, B. and Cho, S. (2018), "Automated vision-based detection of cracks on concrete surfaces using a deep learning technique", Sensors, 18(10), 3452. https://doi.org/10.3390/s18103452.
  29. Kodur, V.K.R., Cheng, F.P., Wang, T.C. and Sultan, M.A. (2003), "Effect of strength and fiber reinforcement on fire resistance of high-strength concrete columns", J. Struct. Eng., 129(2), 253-259. https://doi.org/10.1061/(ASCE)0733-9445(2003)129:2(253).
  30. Kumar, S. (2011), Neural Networks: A Classroom Approach, McGraw-Hill Education India, Uttar Pradesh, India.
  31. LaMalva, K. and Hopkin, D. (2021), SFPES: International Handbook of Structural Fire Engineering, Springer International Publishing, Cham, Switzerland.
  32. Lewis, R.J. (2000), "An Introduction to Classification and Regression Tree ( CART ) Analysis", Annual Meeting of the Society for Academic Emergency Medicine in San Francisco, California, San Francisco, CA, USA, May.
  33. Lie, T.T. and Lin, T.D. (1985), Fire Performance of Reinforced Concrete Columns, ASTM International, West Conshohocken, PA, USA.
  34. Ly, H.B. (2020), "Erratum: Computational hybrid machine learning based prediction of shear capacity for steel fiber reinforced concrete beams" Sustainab., 12(17), 2709. https://doi.org/10.3390/su12177029.
  35. Mangalathu, S., Jang, H., Hwang, S.H. and Jeon, J.S. (2020), "Data-driven machine-learning-based seismic failure mode identification of reinforced concrete shear walls", Eng. Struct., 208, 110331. https://doi.org/10.1016/j.engstruct.2020.110331.
  36. Martinez-Martinez, F., Ruperez-Moreno, M.J., Martinez-Sober, M., Solves-Llorens, J.A., Lorente, D., Serrano-Lopez, A.J. and Martin-Guerrero, J.D. (2017), "A finite element-based machine learning approach for modeling the mechanical behavior of the breast tissues under compression in real-time", Comput. Biol. Med., 90, 116-124. https://doi.org/10.1016/j.compbiomed.2017.09.019.
  37. Ogunleye, A. and Wang, Q.G. (2020), "XGBoost model for chronic kidney disease diagnosis", IEEE/ACM Trans. Comput. Biol. Bioinformat., 17(6), 2131-2140. https://doi.org/10.1109/TCBB.2019.2911071.
  38. Olalusi, O.B. and Awoyera, P.O. (2021), "Shear capacity prediction of slender reinforced concrete structures with steel fibers using machine learning", Eng. Struct., 227, 111470. https://doi.org/10.1016/j.engstruct.2020.111470.
  39. Ozbolt, J., Bosnjak, J., Periskic, G. and Sharma, A. (2014), "3D numerical analysis of reinforced concrete beams exposed to elevated temperature", Eng. Struct., 58, 166. https://doi.org/10.1016/j.engstruct.2012.11.030.
  40. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G. and Chintala, S. (2019), "PyTorch: An imperative style, high-performance deep learning library", Adv. Neural Informat. Process. Syst., 2019, 32.
  41. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O. and Duchesnay, E. (2011), "Scikit-learn: Machine learning in Python", J. Mach. Learn. Res., 12, 2825-2830.
  42. Pyl, L., Schueremans, L., Dierckx, W. and Georgieva, I. (2012), "Fire safety analysis of a 3D frame structure based on a full-scale fire test", Thin Wall. Struct., 61, 204-212. https://doi.org/10.1016/j.tws.2012.03.023.
  43. Rafiei, M.H., Khushefati, W.H., Demirboga, R. and Adeli, H. (2016), "Neural network, machine learning, and evolutionary approaches for concrete material characterization", ACI Mater. J., 113(6), 781-789. https://doi.org/10.14359/51689360.
  44. Ray, S. (2019), "A quick review of machine learning algorithms", Proceedings of the International Conference on Machine Learning, Big Data, Cloud and Parallel Computing: Trends, Prespectives and Prospects, COMITCon2019, Faridabad, India, February.
  45. Rezaiee-Pajand, M. and Karimipour, A. (2021), "Crack spacing prediction of fibre-reinforced concrete beams with lap-spliced bars by machine learning models", Iran. J. Sci. Technol. Trans. Civil Eng., 45(2), 833-850. https://doi.org/10.1007/s40996-020-00441-6.
  46. Soman, K.P. (2009), Machine Learning with SVM and Other Kernel Methods, PHI Learning Pvt. Ltd., New Delhi, Delhi, India.
  47. Stanwick, S. (2003), A Cool Mist, NRC Publications Archive Archives des Publications du CNRC, National Research Council Canada, Ottawa, Ontario, Canada.
  48. Suwondo, R., Cunningham, L., Gillie, M. and Bailey, C. (2021), "Analysis of the robustness of a steel frame structure with composite floors subject to multiple fire scenarios", Adv. Struct. Eng., 24(10), 2076-2089. https://doi.org/10.1177/1369433221992494.