Computers and Concrete

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Improved ensemble machine learning framework for seismic fragility analysis of concrete shear wall system

  • Sangwoo Lee (Department of Civil Engineering, Kyung Hee University) ;
  • Shinyoung Kwag (Department of Civil and Environmental Engineering, Hanbat National University) ;
  • Bu-seog Ju (Department of Civil Engineering, Kyung Hee University)
  • Received : 2022.09.16
  • Accepted : 2023.05.18
  • Published : 2023.09.25
⟨ Previous Next ⟩

Abstract

The seismic safety of the shear wall structure can be assessed through seismic fragility analysis, which requires high computational costs in estimating seismic demands. Accordingly, machine learning methods have been applied to such fragility analyses in recent years to reduce the numerical analysis cost, but it still remains a challenging task. Therefore, this study uses the ensemble machine learning method to present an improved framework for developing a more accurate seismic demand model than the existing ones. To this end, a rank-based selection method that enables determining an excellent model among several single machine learning models is presented. In addition, an index that can evaluate the degree of overfitting/underfitting of each model for the selection of an excellent single model is suggested. Furthermore, based on the selected single machine learning model, we propose a method to derive a more accurate ensemble model based on the bagging method. As a result, the seismic demand model for which the proposed framework is applied shows about 3-17% better prediction performance than the existing single machine learning models. Finally, the seismic fragility obtained from the proposed framework shows better accuracy than the existing fragility methods.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. RS-2022-00144328). This work was also supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. 2021R1A2C1010278).

References

  1. Abraik, E. and Youssef, M.A. (2018), "Seismic fragility assessment of superelastic shape memory alloy reinforced concrete shear walls", J. Build. Eng., 19, 142-153. https://doi.org/10.1016/j.jobe.2018.05.009.
  2. ACI 349-13 (2013), Code Requirements for Nuclear Safety-Related Concrete Structures and Commentary, American Concrete Institute (ACI), Farmington Hills, MI, USA.
  3. Alpaydin, E. (2020), Introduction to Machine Learning, MIT press, Cambridge, MA, USA.
  4. Armaghani, D.J., Mohamad, E.T., Narayanasamy, M.S., Narita, N. and Yagiz, S. (2017), "Development of hybrid intelligent models for predicting TBM penetration rate in hard rock condition", Tunnel. Undergr. Sp. Technol., 63, 29-43. https://doi.org/10.1016/j.tust.2016.12.009.
  5. Asteris, P.G., Skentou, A.D., Bardhan, A., Samui, P. and Pilakoutas, K. (2021), "Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models", Cement Concrete Res., 145, 106449. https://doi.org/10.1016/j.cemconres.2021.106449.
  6. Baba, M. (2013), "Fukushima accident: What happened?", Radiat. Measure., 55, 17-21. https://doi.org/10.1016/j.radmeas.2013.01.013.
  7. Baker, J.W. (2015), "Efficient analytical fragility function fitting using dynamic structural analysis", Earthq. Spectra, 31(1), 579-599. https://doi.org/10.1193/021113EQS025M.
  8. Barbachyn, S.M., Devine, R.D., Thrall, A.P. and Kurama, Y.C. (2020), "Behavior of nuclear RC shear walls designed for similar lateral strengths using normal-strength versus high-strength materials", J. Struct. Eng., 146(11), 04020252. https://doi.org/10.1061/%28ASCE%29ST.1943-541X.0002818.
  9. Breiman, L. (1996), "Bagging predictors", Mach. Learn., 24(2), 123-140. https://doi.org/10.1007/BF00058655.
  10. Burges, C.J. (1998), "A tutorial on support vector machines for pattern recognition", Data Min. Knowl. Discov., 2(2), 121-167. https://doi.org/10.1023/A:1009715923555.
  11. Calderon, S., Vargas, L., Sandoval, C., Araya-Letelier, G. and Milani, G. (2022), "Shear design equation and updated fragility functions for partially grouted reinforced masonry shear walls", J. Build. Eng., 50, 104097. https://doi.org/10.1016/j.jobe.2022.104097.
  12. Cornell, C.A., Jalayer, F., Hamburger, R.O. and Foutch, D.A. (2002), "Probabilistic basis for 2000 SAC federal emergency management agency steel moment frame guidelines", J. Struct. Eng., 128(4), 526-533. https://doi.org/10.1061/(ASCE)0733-9445(2002)128:4(526).
  13. Eem, S., Choi, I.K., Cha, S.L. and Kwag, S. (2021), "Seismic response correlation coefficient for the structures, systems and components of the Korean nuclear power plant for seismic probabilistic safety assessment", Annal. Nucl. Energy, 150, 07759. https://doi.org/10.1016/j.anucene.2020.107759.
  14. EPRI (2013), "Seismic probabilistic risk assessment implementation guide", Technical Report 3002000709; Electric Power Research Institute, Washington D.C., USA.
  15. EPRI (2018), "Seismic fragility and seismic margin guidance for seismic probabilistic risk assessments", Technical Report 3002012994; Electric Power Research Institute, Washington D.C., USA.
  16. Ghosh, J., Padgett, J.E. and Duenas-Osorio, L. (2013), "Surrogate modeling and failure surface visualization for efficient seismic vulnerability assessment of highway bridges", Probab. Eng. Mech., 34, 189-199. https://doi.org/10.1016/j.probengmech.2013.09.003.
  17. Gidaris, I., Taflanidis, A.A. and Mavroeidis, G.P. (2015), "Kriging metamodeling in seismic risk assessment based on stochastic ground motion models", Earthq. Eng. Struct. Dyn., 44(14), 2377-2399. https://doi.org/10.1002/eqe.2586.
  18. Goodfellow, I., Bengio, Y. and Courville, A. (2016), "6.5 back-propagation and other differentiation algorithms", Deep Learning, MIT Press, Cambridge, MA, USA.
  19. Gulec, C.K. (2009), Performance-Based Assessment and Design of Squat Reinforced Concrete Shear Walls, State University of New York at Buffalo, Buffalo, NY, USA.
  20. Gulec, C.K., Whittaker, A.S. and Hooper, J. D. (2010), "Fragility functions for low aspect ratio reinforced concrete walls", Eng. Struct., 32(9), 2894-2901. https://doi.org/10.1016/j.engstruct.2010.05.008.
  21. Hidalgo, P.A., Ledezma, C.A. and Jordan, R.M. (2002), "Seismic behavior of squat reinforced concrete shear walls", Earthq. Spectra, 18(2), 287-308. https://doi.org/10.1193/1.1490353.
  22. Ile, N. and Reynouard, J.M. (2000), "Nonlinear analysis of reinforced concrete shear wall under earthquake loading", J. Earthq. Eng., 4(2), 183-213. https://doi.org/10.1142/S1363246900000102.
  23. Izumo, J. (1989), "Analytical models for RC panel elements subjected to in-plane forces", Concrete Lib. JSCE, 12, 155-181.
  24. Jalayer, F. (2003), "Direct probabilistic seismic analysis: Implementing non-linear dynamic assessments", Doctoral Dissertation, Stanford University, Stanford, CA, USA.
  25. Kardani, N., Bardhan, A., Kim, D., Samui, P. and Zhou, A. (2021), "Modelling the energy performance of residential buildings using advanced computational frameworks based on RVM, GMDH, ANFIS-BBO and ANFIS-IPSO", J. Build. Eng., 35, 02105. https://doi.org/10.1016/j.jobe.2020.102105.
  26. Kwag, S. and Gupta, A. (2018), "Computationally efficient fragility assessment using equivalent elastic limit state and Bayesian updating", Comput. Struct., 197, 1-11. https://doi.org/10.1016/j.compstruc.2017.11.011.
  27. Kwag, S., Gupta, A. and Dinh, N. (2018), "Probabilistic risk assessment based model validation method using Bayesian network", Reliab. Eng. Syst. Saf., 169, 380-393. https://doi.org/10.1016/j.ress.2017.09.013.
  28. Kwag, S., Ju, B. and Jung, W. (2018), "Beneficial and detrimental effects of soil-structure interaction on probabilistic seismic hazard and risk of nuclear power plant", Adv. Civil Eng., 2018, 1-18. https://doi.org/10.1155/2018/2698319.
  29. Kwag, S., Oh, J., Lee, J.M. and Ryu, J.S. (2017), "Bayesian-based seismic margin assessment approach: Application to research reactor", Earthq. Struct., 12(6), 653-663. https://doi.org/10.12989/eas.2017.12.6.653.
  30. Kwag, S., Ryu, Y. and Ju, B.S. (2020), "Efficient seismic fragility analysis for large-scale piping system utilizing Bayesian approach", Appl. Sci., 10(4), 1515. https://doi.org/10.3390/app10041515.
  31. Lee, J. and Fenves, G.L. (1998), "Plastic-damage model for cyclic loading of concrete structures", J. Eng. Mech., 124(8), 892-900. https://doi.org/10.1061/(ASCE)0733-9399(1998)124:8(892).
  32. Lee, S., Gupta, A. and Proestos, G.T. (2022), "Performance based characterization and quantification of uncertainty in damage plasticity model for seismic fragility assessment of concrete structures", ASCE-ASME J. Risk Uncertain. Eng. Syst. Part A: Civil Eng., 9(1), 04022060. https://doi.org/10.1061/AJRUA6.RUENG-913.
  33. Lubliner, J., Oliver, J., Oller, S. and Onate, E. (1989), "A plastic-damage model for concrete", Int. J. Solid. Struct., 25(3), 299-326. https://doi.org/10.1016/0020-7683(89)90050-4.
  34. Maekawa, K. and Okamura, H. (1983), "The deformational behavior and constitutive equation of concrete using the elasto-plastic and fracture model", J. Fac. Eng. Univ. Tokyo Ser. B, 37(2), 253-328.
  35. Mangalathu, S. and Jeon, J.S. (2019), "Stripe-based fragility analysis of multispan concrete bridge classes using machine learning techniques", Earthq. Eng. Struct. Dyn., 48(11), 1238-1255. https://doi.org/10.1002/eqe.3183.
  36. Mangalathu, S., Heo, G. and Jeon, J.S. (2018b), "Artificial neural network based multi-dimensional fragility development of skewed concrete bridge classes", Eng. Struct., 162, 166-176. https://doi.org/10.1016/j.engstruct.2018.01.053.
  37. 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.
  38. Mangalathu, S., Jeon, J.S. and DesRoches, R. (2018a), "Critical uncertainty parameters influencing seismic performance of bridges using Lasso regression", Earthq. Eng. Struct. Dyn., 47(3), 784-801. https://doi.org/10.1002/eqe.2991.
  39. Morita, R., Saito, K. and Yuyama, A. (2021), "Development and analysis of seismic experience database of structures, systems and components in nuclear power plants based on investigation reports and maintenance records", Nucl. Eng. Des., 375, 11078. https://doi.org/10.1016/j.nucengdes.2021.111078.
  40. Palermo, D., Vecchio, F.J. and Solanki, H. (2002), "Behavior of three-dimensional reinforced concrete shear walls", ACI Struct. J., 99(1), 81-89.
  41. Raschka, S. (2018), "Model evaluation, model selection, and algorithm selection in machine learning", arXiv preprint arXiv, 1811, 12808. https://doi.org/10.48550/arXiv.1811.12808.
  42. Shinozuka, M., Feng, M.Q., Lee, J. and Naganuma. T. (2000), "Statistical analysis of fragility curves", ASCE J. Eng. Mech., 126(12), 1224-1231. https://doi.org/10.7916/D80S0073.
  43. Sohn, J., Choi, I. and Kim, J. (2022), "Development of limit states for seismic fragility assessment of piloti-type structures verified with observed damage data", Eng. Struct., 251, 113562. https://doi.org/10.1016/j.engstruct.2021.113562.
  44. Straub, D. and Der Kiureghian, A. (2008), "Improved seismic fragility modeling from empirical data", Struct. Saf., 30(4), 320-336. https://doi.org/10.1016/j.strusafe.2007.05.004.
  45. Syed, S. and Gupta, A. (2015a), "Seismic fragility of RC shear walls in nuclear power plant part 1: Characterization of uncertainty in concrete constitutive model", Nucl. Eng. Des., 295, 576-586. https://doi.org/10.1016/j.nucengdes.2015.09.037.
  46. Syed, S. and Gupta, A. (2015b), "Seismic fragility of RC shear walls in nuclear power plant part 2: Influence of uncertainty in material parameters on fragility of concrete shear walls", Nucl. Eng. Des., 295, 587-596. https://doi.org/10.1016/j.nucengdes.2015.09.038.
  47. Tadinada, S.K. and Gupta, A. (2017), "Structural fragility of T-joint connections in large-scale piping systems using equivalent elastic time-history simulations", Struct. Saf., 65, 49-59. https://doi.org/10.1016/j.strusafe.2016.12.003.
  48. Tibshirani, R. (1997), "The lasso method for variable selection in the Cox model", Stat. Med., 16(4), 385-395. https://doi.org/10.1002/(SICI)1097-0258(19970228)16:4<385::AID-SIM380>3.0.CO;2-3.
  49. US NRC (2014), Design Response Spectra for Seismic Design of Nuclear Power Plants, Regulatory Guide 1.60, US Nuclear Regulatory Commission, Rockville, MD, USA.
  50. Vamvatsikos, D. and Cornell, C.A. (2002), "Incremental dynamic analysis", Earthq. Eng. Struct. Dyn., 31(3), 491-514. https://doi.org/10.1002/eqe.141.
  51. Wang, J.J., Liu, C., Nie, X., Ding, R. and Zhu, Y.J. (2022), "Biaxial constitutive models for simulation of low-aspect-ratio reinforced concrete shear walls", J. Eng. Mech., 148(2), 4021157. https://doi.org/10.1061/%28ASCE%29EM.1943-7889.0002030.
  52. Wei, F., Chen, H. and Xie, Y. (2022), "Experimental study on seismic behavior of reinforced concrete shear walls with low shear span ratio", J. Build. Eng., 45, 103602. https://doi.org/10.1016/j.jobe.2021.103602.
  53. Xu, J., Nie, J., Braverman, J. and Hofmayer, C. (2007), "Assessment of analysis methods for seismic shear wall capacity using JNES/NUPEC multi-axial cyclic and shaking table test data", NUREG/CR-6925, Nuclear Regulatory Commission, Rockville, MD, USA.
  54. Yan, Y., Huang, H. and Sun, L. (2022), "Multivariate structural seismic fragility analysis and comparative study based on moment estimation surrogate model and Gaussian copula function", Eng. Struct., 262, 114324. https://doi.org/10.1016/j.engstruct.2022.114324.
  55. Yazdi, A.J., Haukaas, T., Yang, T. and Gardoni, P. (2016), "Multivariate fragility models for earthquake engineering", Earthq. Spectra, 32(1), 441-461. https://doi.org/10.1193/061314EQS085M.
  56. Yoshida, K., Uchida, N., Hiarahara, S., Nakayama, T., Matsuzawa, T., Okada, T., Matsumoto, Y. and Hasegawa, A. (2020), "2019 M6. 7 Yamagata-Oki earthquake in the stress shadow of 2011 Tohoku-Oki earthquake: Was it caused by the reduction in fault strength?", Tectonophys., 793, 228609. https://doi.org/10.1016/j.tecto.2020.228609.