Multiple Target Machine Learning Prediction of Capacity Curves of Reinforced Concrete Shear Walls

Document Type : Regular Article

Authors

1 Ph.D. Candidate, Civil, Construction and Environmental Engineering, Iowa State University, Iowa, United States

2 Associate Professor, Civil, Construction and Environmental Engineering, Iowa State University, Iowa, United States

Abstract

Reinforced concrete (RC) shear wall is one of the most widely adopted earthquake-resisting structural elements. Accurate prediction of capacity curves of RC shear walls has been of significant importance since it can convey important information about progressive damage states, the degree of energy absorption, and the maximum strength. Decades-long experimental efforts of the research community established a systematic database of capacity curves, but it is still in its infancy to productively utilize the accumulated data. In the hope of adding a new dimension to earthquake engineering, this study provides a machine learning (ML) approach to predict capacity curves of the RC shear wall based on a multi-target prediction model and fundamental statistics. This paper harnesses bootstrapping for uncertainty quantification and affirms the robustness of the proposed method against erroneous data. Results and validations using more than 200 rectangular RC shear walls show a promising performance and suggest future research directions toward data- and ML-driven earthquake engineering.

Keywords

Main Subjects


[1]     Aaleti S, Brueggen BL, Johnson B, French CE, Sritharan S. Cyclic Response of Reinforced Concrete Walls with Different Anchorage Details: Experimental Investigation. J Struct Eng 2013;139:1181–91. https://doi.org/10.1061/(ASCE)ST.1943-541X.0000732.
[2]     Dazio A, Beyer K, Bachmann H. Quasi-static cyclic tests and plastic hinge analysis of RC structural walls. Eng Struct 2009;31:1556–71. https://doi.org/10.1016/j.engstruct.2009.02.018.
[3]     Lefas ID, Kotsovos MD, Ambraseys NN. Behavior of Reinforced Concrete Structural Walls: Strength, Deformation Characteristics, and Failure Mechanism. ACI Struct J 1990;87:23–31. https://doi.org/10.14359/2911.
[4]     Salonikios TN, Kappos AJ, Tegos IA, Penelis GG. Cyclic load behavior of low-slenderness reinforced concrete walls: design basis and test results. ACI Struct J 1999;96:649–60.
[5]     Rafiq M., Bugmann G, Easterbrook D. Neural network design for engineering applications. Comput Struct 2001;79:1541–52. https://doi.org/10.1016/S0045-7949(01)00039-6.
[6]     Reich Y. Machine learning techniques for civil engineering problems. Comput Civ Infrastruct Eng 1997;12:295–310.
[7]     Chou J, Ngo N, Pham A. Shear Strength Prediction in Reinforced Concrete Deep Beams Using Nature-Inspired Metaheuristic Support Vector Regression. J Comput Civ Eng 2016;30:04015002. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000466.
[8]     Pal M, Deswal S. Support vector regression based shear strength modelling of deep beams. Comput Struct 2011;89:1430–9. https://doi.org/10.1016/j.compstruc.2011.03.005.
[9]     Aguilar V, Sandoval C, Adam JM, Garzón-Roca J, Valdebenito G. Prediction of the shear strength of reinforced masonry walls using a large experimental database and artificial neural networks. Struct Infrastruct Eng 2016;12:1661–74. https://doi.org/10.1080/15732479.2016.1157824.
[10]   Chou J-S, Pham A-D. Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength. Constr Build Mater 2013;49:554–63. https://doi.org/10.1016/j.conbuildmat.2013.08.078.
[11]   van Gent MRA, van den Boogaard HFP. Neural network modelling of forces on vertical structures. Coast Eng Proc 1998:2096–123. https://doi.org/http://dx.doi.org/10.9753/icce.v26.%25p.
[12]   Johari A, Habibagahi G, Ghahramani A. Prediction of Soil–Water Characteristic Curve Using Genetic Programming. J Geotech Geoenvironmental Eng 2006;132:661–5. https://doi.org/10.1061/(ASCE)1090-0241(2006)132:5(661).
[13]   Saha S, Gu F, Luo X, Lytton RL. Prediction of Soil-Water Characteristic Curve Using Artificial Neural Network Approach. PanAm Unsaturated Soils 2017, Reston, VA: American Society of Civil Engineers; 2018, p. 124–34. https://doi.org/10.1061/9780784481684.014.
[14]   Struyf J, Zenko B, Blockeel H, Vens C. Clus: user’s manual. 2010.
[15]   ┼Żenko B. Learning predictive clustering rules. Int Work Knowl Discov Inductive Databases 2005;32:234–50.
[16]   Blockeel H, De Raedt L, Ramon J. Top-down induction of clustering trees. Proc 15th Int Conf Mach Learn 1998:55–63. https://doi.org/10.1.1.50.3353.
[17]   Prajapati P, Thakkar A. Improving the performance of predictive clustering tree algorithm for hierarchical multi-label classification. Proc. Int. Conf. Emerg. Res. Comput. Information, Commun. Appl., 2014.
[18]   Jianhua Lin. Divergence measures based on the shannon entropy. IEEE Trans Inf Theory 1991;37:145–51.
[19]   Karegowda AG, Manjunath AS, Ratio G, Evaluation CF. Comparative study of attribute selection using gain ratio. Int J Inf Technol Knowl Knowl Manag 2010;2:271–7.
[20]   Opitz D, Maclin R. Popular Ensemble Methods: An Empirical Study. J Artif Intell Res 1999;11:169–98. https://doi.org/10.1613/jair.614.
[21]   Rokach L. Ensemble-based classifiers. Artif Intell Rev 2010;33:1–39. https://doi.org/10.1007/s10462-009-9124-7.
[22]   Tille Y. Statistical Analysis of Designed Experiments. vol. 53. New York: Springer-Verlag; 2002. https://doi.org/10.1007/b98966.
[23]   Bbeiman LEO, Breiman L. Bagging predictors. Mach Learn 1996;24:123–40.
[24]   Quinlan JR. Bagging, boosting, and C4.5. AAAI/IAAI, 1996, p. 725–30.
[25]   Kocev D, Vens C, Strufy J, Dzeroski S. Ensembles of multi-objective decision trees. Mach Learn ECML 2007 2007:624–31.
[26]   Aho T, Zenko B, Dzeroski S. Rule Ensembles for Multi-target Regression. 2009 Ninth IEEE Int. Conf. Data Min., IEEE; 2009, p. 21–30. https://doi.org/10.1109/ICDM.2009.16.
[27]   Friedman JH, Popescu BE. Predictive learning via rule ensembles. Ann Appl Stat 2008;2:916–54. https://doi.org/10.1214/07-AOAS148.
[28]   Struyf J. Clus download 2013.
[29]   Yang Y, Cho IH. Shear wall database 2019.
[30]   Cho IH. Virtual Earthquake Engineering Laboratory Capturing Nonlinear Shear, Localized Damage and Progressive Buckling of Bar. Earthq Spectra 2013;29:103–26. https://doi.org/10.1193/1.4000095.
[31]   Cho IH, Hall JF. Parallelized Implicit Nonlinear FEA Program for Real Scale RC Structures under Cyclic Loading. J Comput Civ Eng 2012;26:356–65. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000138.
[32]   Cho IH, Porter KA. Multilayered grouping parallel algorithm for multiple-level multiscale analyses. Int J Numer Methods Eng 2014;100:914–32. https://doi.org/10.1002/nme.4791.
[33]   Thomsen JH, Wallace JW. Displacement-Based Design of Slender Reinforced Concrete Structural Walls—Experimental Verification. J Struct Eng 2004;130:618–30. https://doi.org/10.1061/(ASCE)0733-9445(2004)130:4(618).
[34]   Song I, Cho I, Tessitore T, Gurcsik T, Ceylan H. Data-Driven Prediction of Runway Incursions with Uncertainty Quantification. J Comput Civ Eng 2018;32:04018004. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000733.
[35]   Efron B, Stein C. The Jackknife Estimate of Variance. Ann Stat 1981;9:586–96. https://doi.org/10.1214/aos/1176345462.
[36]   Tongji Univeristy. Database on static tests of structural members and joint assemblies. 2008.
[37]   Song I, Yang Y, Im J, Tong T, Ceylan H, Cho IH. Impacts of Fractional Hot-Deck Imputation on Learning and Prediction of Engineering Data. IEEE Trans Knowl Data Eng 2020;32:2363–73. https://doi.org/10.1109/TKDE.2019.2922638.