Earthquakes and Structures

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

An improved multiple-vertical-line-element model for RC shear walls using ANN

  • Xiaolei Han (State Key Laboratory of Subtropical Building and Urban Science, South China University of Technology) ;
  • Lei Zhang (State Key Laboratory of Subtropical Building and Urban Science, South China University of Technology) ;
  • Yankun Qiu (School of Civil Engineering & Transportation, South China University of Technology) ;
  • Jing Ji (State Key Laboratory of Subtropical Building and Urban Science, South China University of Technology)
  • Received : 2022.01.02
  • Accepted : 2023.10.07
  • Published : 2023.11.25
⟨ Previous Next ⟩

Abstract

The parameters of the multiple-vertical-line-element model (MVLEM) of reinforced concrete (RC) shear walls are often empirically determined, which causes large simulation errors. To improve the simulation accuracy of the MVLEM for RC shear walls, this paper proposed a novel method to determine the MVLEM parameters using the artificial neural network (ANN). First, a comprehensive database containing 193 shear wall specimens with complete parameter information was established. And the shear walls were simulated using the classic MVLEM. The average simulation errors of the lateral force and drift of the peak and ultimate points on the skeleton curves were approximately 18%. Second, the MVLEM parameters were manually optimized to minimize the simulation error and the optimal MVLEM parameters were used as the label data of the training of the ANN. Then, the trained ANN was used to generate the MVLEM parameters of the collected shear walls. The results show that the simulation error of the predicted MVLEM was reduced to less than 13% from the original 18%. Particularly, the responses generated by the predicted MVLEM are more identical to the experimental results for the testing set, which contains both flexure-control and shear-control shear wall specimens. It indicates that establishing MVLEM for RC shear walls using ANN is feasible and promising, and that the predicted MVLEM substantially improves the simulation accuracy.

Keywords

Acknowledgement

This work was supported by the Natural Science Foundation of Guangdong Province (Grant No. 2017A030313274) and the Guangzhou Municipal Science and Technology Program (Grant No. 201904010221). Thanks to Dr. Cui Jidong for the collected database.

References

  1. Adeli, H. (2001), "Neural networks in civil engineering: 1989-2000", Comput. Aid. Civil Inf., 16(2), 126-142. https://doi.org/10.1111/0885-9507.00219.
  2. Asteris, P.G., Armaghani, D.J., Hatzigeorgiou, G.D., Karayannis, C.G. and Pilakoutasdeli, K. (2019), "Predicting the shear strength of reinforced concrete beams using artificial neural networks", Comput. Concrete, 24(5), 469-488. http://doi.org/10.12989/cac.2019.24.5.469.
  3. Ayat, H., Kellouche, Y., Ghrici, M. and Boukhatem, B. (2018), "Compressive strength prediction of limestone filler concrete using artificial neural networks", Adv. Comput. Des., 3(3), 289-302. https://doi.org/10.12989/acd.2018.3.3.289.
  4. Ayoub, A. and Filippou, F.C. (1999), "Mixed formulation of bondslip problems under cyclic loads", J. Struct. Eng., 125(6), 661-671. https://doi.org/10.1061/(ASCE)0733-9445(1999)125:6(661).
  5. Barkhordari, M.S. and Massone L.M. (2022), "Failure mode detection of reinforced concrete shear walls using ensemble deep neural networks", Int. J. Concrete Struct. Mater., 16, 33. https://doi.org/10.1186/s40069-022-00522-y.
  6. Barkhordari, M.S. and Massone L.M. (2023), "Ensemble techniques and hybrid intelligence algorithms for shear strength prediction of squat reinforced concrete walls", Adv. Comput. Des., 8(1), 37-59. https://doi.org/10.12989/acd.2023.8.1.037.
  7. Barkhordari, M.S. and Tehranizadeh, M. (2021), "Response estimation of reinforced concrete shear walls using artificial neural network and simulated annealing algorithm", Struct., 34, 1155-1168. https://doi.org/10.1016/j.istruc.2021.08.053.
  8. Caruana, R., Lawrence, S. and Giles, L. (2000), "Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping", International Conference on Neural Information Processing Systems, Denver, CO, USA, January.
  9. Chen, X.W. (2011), "Research on deformation limit state of shear-wall structure's components and development of the computing platform", Ph.D. Dissertation, South China University of Technology, Guangzhou, China.
  10. Colotti, V. (1993), "Shear behavior of RC structural wall", J. Struct. Eng., 119(3), 728-746. https://doi.org/10.1061/(ASCE)0733-9445(1993)119:3(728).
  11. Cui, J.D. (2017), "Research and experimental verification of deformation index limits of RC beams, columns and shear walls", Ph.D. Dissertation, South China University of Technology, Guangzhou, China.
  12. Derecho, A., Takayanagi, T. and Corley, W. (1979), Analysis of Inelastic Shear Deformation Effects in Reinforced Concrete Structural Wall Systems, Portland Cement Association, Chicago, IL, USA.
  13. FEMA 356 (2000), Prestandard and Commentary for the Seismic Rehabilitation of Building, Federal Emergency Management Agency, Washington, D.C., USA.
  14. Huang, Y., Hong, L.L., Wan, X.W. and Hu X.F. (2019), "Plastic hinge length of reinforced concrete shear wall", Earthq. Eng. Eng. Dyn., 39(2), 79-88. https://doi.org/10.1680/macr.14.00298.
  15. Ilkhani, M., Naderpour, H. and Kheyroddin, A. (2019), "A proposed novel approach for torsional strength prediction of RC beams", J. Build. Eng., 25, 200810. https://doi.org/10.1016/j.jobe.2019.100810.
  16. Ioffe, S. and Szegedy, C. (2015), "Batch normalization: Accelerating deep network training by reducing internal covariate shift", arXiv preprint arXiv:1502.03167.
  17. Junemann, R., Delallera, J., Hube, M., Cifuentes, L. and Kausel, E. (2015), "A statistical analysis of reinforced concrete wall buildings damaged during the 2010, Chile earthquake", Eng. Struct., 82, 168-185. https://doi.org/10.1016/j.engstruct.2014.10.014.
  18. Kabeyasawa, T., Shiohara, H., Otani, S. and Aoyama, H. (1983), "Analysis of the full-scale seven-story reinforced concrete test structure", J. Fac. Eng., Univ. Tokyo Ser. B, 37(2), 431-478.
  19. Kazaz, I. (2013), "Analytical study on plastic hinge length of structural walls", J. Struct. Eng., 139(11), 1938-1950. https://doi.org/10.1061/(ASCE)ST.1943-541X.0000770.
  20. Kingma, D.P. and Ba, J. (2014), "Adam: A method for stochastic optimization", arXiv preprint arXiv:1412.6980.
  21. Kolozvari, K., Orakcal, K. and Wallace, J.W. (2015), "Modeling of cyclic shear-flexure interaction in reinforced concrete structural walls I: Theory", J. Struct. Eng., 141(5), 1-10. https://doi.org/10.1061/(ASCE)ST.1943-541X.0001059.
  22. Kolozvari, K., Orakcal, K. and Wallace, J.W. (2015), "Shear-flexure interaction modeling for reinforced concrete structural walls and columns under reversed cyclic loading", Peer Report 2015/12, Pacific Earthquake Engineering Research Center, Berkeley, CA, USA.
  23. Kocer, M., Ozturk, M. and Arslan, M.H. (2019), "Determination of moment, shear and ductility capacities of spiral columns using an artificial neural network", J. Build. Eng., 26, 100878. https://doi.org/10.1016/j.jobe.2019.100878.
  24. Marini, A. and Spacone, E. (2006), "Analysis of reinforced concrete elements including shear effects", ACI Struct. J., 103(5), 645-655.
  25. Massone, L.M. and Wallace, J.W. (2004) "Load-deformation Responses of Slender Reinforced Concrete Walls", Struct. J., 101(1), 103-113.
  26. Massone, L.M., Orakcal, K. and Wallace, J. (2006), "Shear-flexure interaction for structural walls", ACI Spec. Publ., 236(7), 127-150.
  27. Menegotto, M. and Pinto, P.E. (1973), "Method of analysis for cyclically loaded R.C. plane frames including changes in geometry and non-elastic behaviour of elements under combined normal force and bending", Symposium on the Resistance and Ultimate Deformability of Structures Acted on by Well Defined Repeated Loads, International Association for Bridge and Structural Engineering, Zurich, Switzerland.
  28. Orakcal, K., Massone, L.M. and Wallace, J.W. (2006), "Analytical modeling of reinforced concrete walls for predicting flexural and coupled-shear-flexural responses", PEER Report 2006/07, Pacific Earthquake Engineering Research Center, Berkeley, CA, USA.
  29. Park, R. and Pauly, T. (1975), Reinforced Concrete Structures, John Wiley & Sons, Hoboken, NJ, USA.
  30. Parker, Z., Poe, S. and Vrbsky, S.V. (2013), "Comparing NoSQL MongoDB to an SQL DB", Proceedings of the 51st ACM Southeast Conference, Savannah, GA, USA, April.
  31. Saha, P., Prasad, M.L.V. and Kumar, P.R. (2017), "Predicting strength of SCC using artificial neural network and multivariable regression analysis", Comput. Concrete, 20(1), 31-38. https://doi.org/10.12989/cac.2017.20.1.031.
  32. Scott, B.D., Park, R. and Priestley, M.J.N. (1982), "Stress-strain behavior of concrete confined by overlapping hoops at low and high strain rates", J. Am. Concrete Inst., 79(1), 13-27.
  33. Song, C., Pujol, S. and Lepage, A. (2012), "The collapse of the Alto Rio building during the 27 February 2010, Maule, Chile earthquake", Earthq. Spectra, 28(1), 301-334. https://doi.org/10.1193/1.4000036.
  34. Vasquez, J.A., Delallera, J.C. and Hube, M.A. (2016), "A regularized fiber element model for reinforced concrete shear walls", Earthq. Eng. Struct. D., 45(13), 2063-2083. https://doi.org/10.1002/eqe.2731.
  35. Vulcano, A. and Bertero, V.V. (1986), "Nonlinear analysis of RC structural walls", Proceedings of the 8th European Conference on Earthquake Engineering, Lisbon, Portugal, September.
  36. Vulcano, A., Bertero, V.V. and Colotti, V. (1988), "Analytical modeling of RC structural walls", Proceedings of 9th World Conference on Earthquake Engineering, Tokyo-Kyoto, Japan, August.
  37. Wood, S.L., Wight, J.K. and Moehle, J.P. (1987), "The 1985 Chile earthquake: Observations on earthquake-resistant construction in Vina del Mar", Report No. UILU-ENG-87-2002 NSF-ENG-87015, University of Illinois at Urbana-Champaign, Urbana, IL, USA.
  38. Zhou, Q., Zhu, F., Yang, X., Wang, F.L., Chi, B. and Zhang, Z.M. (2017), "Shear capacity estimation of fully grouted reinforced concrete masonry walls using neural network and adaptive neuro-fuzzy inference system models", Constr. Build. Mater., 153, 937-947. https://doi.org/10.1016/j.conbuildmat.2017.07.171.