Evolutionary Polynomial Regression Algorithm Enhanced with a Robust Formulation: Application to Shear Strength Prediction of RC Beams without Stirrups
Publication: Journal of Computing in Civil Engineering
Volume 35, Issue 6
Abstract
Many classes of engineering problems focus on the process of calibrating mathematical models using observed data. The enormous progress of scientific computation and data-mining techniques has allowed the search for accurate mathematical models from experimental data using algorithms. Among them, the evolutionary polynomial regression (EPR) is an artificial intelligence (AI) technique that merges genetic algorithms (GAs) and regression techniques such as ordinary least square (OLS). This paper presents a robust and well-conditioned EPR technique to remove potential outliers and leverage points included in any biased data set. This hybrid approach combines bisquare, Huber, and Cauchy robust multivariate techniques with GAs and the Akaike weight-based method to assess the optimal polynomial model while limiting the impact of the data bias. The robust techniques will define the parameters, the GAs will determine the exponents, and the Akaike weight-based method will evaluate the relative importance of each observed variable of the proposed model. As a case study, a shear strength data set of RC beams without stirrups is used to compare the standard EPR algorithm with the new proposed hybrid methodology. Furthermore, the optimal robust model is compared with different benchmark formulations to highlight its accuracy and consistency. The proposed hybrid technique can be adopted as a mathematical tool for many engineering problems, providing an unbiased prediction of the observed variable. Furthermore, the shear strength equation that provides the best compromise between accuracy and complexity allows its potential use in many engineering practices and building codes.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All data that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The research leading to these results has received funding from the European Research Council under the Grant Agreement No. ERC_IDEal reSCUE_637842 of the project IDEAL RESCUE (Integrated Design and Control of Sustainable Communities During Emergencies).
References
Acharya, D. N., and K. O. Kemp. 1965. “Significance of dowel forces on the shear failure of rectangular reinforced concrete beams without web reinforcement.” J. Proc. 62 (10): 1265–1280.
ACI (American Concrete Institute). 2008. Building code requirements for structural concrete (ACI 318-08) and commentary. ACI 318-08. Farmington Hills, MI: ACI.
Agdas, D., D. J. Warne, J. Osio-Norgaard, and F. J. Masters. 2018. “Utility of genetic algorithms for solving large-scale construction time-cost trade-off problems.” J. Comput. Civil Eng. 32 (1): 04017072. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000718.
Ahangar-Asr, A., A. Faramarzi, N. Mottaghifard, and A. A. Javadi. 2011. “Modeling of permeability and compaction characteristics of soils using evolutionary polynomial regression.” Comput. Geosci. 37 (11): 1860–1869. https://doi.org/10.1016/j.cageo.2011.04.015.
Akaike, H. 1983. “Information measures and model selection.” In Proc., Int. Statistical Institute 44th Session, 277–291. Hague, Netherlands: International Statistical Institute.
Altarabsheh, A., A. Kandil, and M. Ventresca. 2018. “New multiobjective optimization approach to rehabilitate and maintain sewer networks based on whole lifecycle behavior.” J. Comput. Civ. Eng. 32 (1): 04017069. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000715.
Altomare, C., D. B. Laucelli, H. Mase, and X. Gironella. 2020. “Determination of semi-empirical models for mean wave overtopping using an evolutionary polynomial paradigm.” J. Mar. Sci. Eng. 8 (8): 570. https://doi.org/10.3390/jmse8080570.
Andersen, R. 2008. Modern methods for robust regression. Los Angeles: SAGE.
Angelakos, D., E. C. Bentz, and M. P. Collins. 2001. “Effect of concrete strength and minimum stirrups on shear strength of large members.” Struct. J. 98 (3): 291–300.
Back, T. 1996. Evolutionary algorithms in theory and practice: Evolution strategies, evolutionary programming, genetic algorithms. Oxford, UK: Oxford University Press.
Bazant, Z. P., and M. T. Kazemi. 1991. “Size effect on diagonal shear failure of beams without stirrups.” ACI Struct. J. 88 (3): 268–276.
BSI (British Standards Institution). 2004. Eurocode 2: Design of concrete structures. Part 1-1: General rules and rules for buildings. EC2. London: BSI.
Cherkassky, V. 2002. “Model complexity control and statistical learning theory.” Nat. Comput. 1 (1): 109–133. https://doi.org/10.1023/A:1015007927558.
Choi, K.-K., A. G. Sherif, M. M. R. Taha, and L. Chung. 2009. “Shear strength of slender reinforced concrete beams without web reinforcement: A model using fuzzy set theory.” Eng. Struct. 31 (3): 768–777. https://doi.org/10.1016/j.engstruct.2008.11.013.
Collins, M. P., E. C. Bentz, E. G. Sherwood, and L. Xie. 2008. “An adequate theory for the shear strength of reinforced concrete structures.” Mag. Concr. Res. 60 (9): 635–650. https://doi.org/10.1680/macr.2008.60.9.635.
Cressie, N. 1985. “Fitting variogram models by weighted least squares.” J. Int. Assoc. Math. Geol. 17 (5): 563–586. https://doi.org/10.1007/BF01032109.
Davidson, J. W., D. Savic, and G. A. Walters. 1999. “Method for the identification of explicit polynomial formulae for the friction in turbulent pipe flow.” J. Hydroinf. 1 (2): 115–126. https://doi.org/10.2166/hydro.1999.0010.
Eiben, A. E., and J. E. Smith. 2003. Introduction to evolutionary computing. New York: Springer.
Fiore, A., L. Berardi, and G. C. Marano. 2012. “Predicting torsional strength of RC beams by using evolutionary polynomial regression.” Adv. Eng. Software 47 (1): 178–187. https://doi.org/10.1016/j.advengsoft.2011.11.001.
Fiore, A., G. Quaranta, G. C. Marano, and G. Monti. 2016. “Evolutionary polynomial regression–based statistical determination of the shear capacity equation for reinforced concrete beams without stirrups.” J. Comput. Civ. Eng. 30 (1): 04014111. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000450.
Fox, J., and G. Monette. 2002. An R and S-Plus companion to applied regression. Los Angeles: SAGE.
Gandomi, A. H., D. Mohammadzadeh, J. L. Pérez-Ordóñez, and A. H. Alavi. 2014. “Linear genetic programming for shear strength prediction of reinforced concrete beams without stirrups.” Appl. Soft Comput. 19 (Jun): 112–120. https://doi.org/10.1016/j.asoc.2014.02.007.
Giustolisi, O., and D. A. Savic. 2006. “A symbolic data-driven technique based on evolutionary polynomial regression.” J. Hydroinf. 8 (3): 207–222. https://doi.org/10.2166/hydro.2006.020b.
Giustolisi, O., and V. Simeone. 2006. “Optimal design of artificial neural networks by a multi-objective strategy: Groundwater level predictions.” Hydrol. Sci. J. 51 (3): 502–523. https://doi.org/10.1623/hysj.51.3.502.
Gross, A. M. 1977. “Confidence intervals for bisquare regression estimates.” J. Am. Stat. Assoc. 72 (358): 341–354. https://doi.org/10.1080/01621459.1977.10481001.
Han, J., J. Pei, and M. Kamber. 2011. Data mining: Concepts and techniques. New York: Elsevier.
Holland, J. H. 1984. “Genetic algorithms and adaptation.” In Adaptive control of ill-defined systems, 317–333. New York: Springer.
Huber, P. J. 1964. “Robust statistics: A review.” Ann. Math. Stat. 43 (4): 1041–1067.
Ishibuchi, H., and T. Yamamoto. 2003. “Effects of three-objective genetic rule selection on the generalization ability of fuzzy rule-based systems.” In Proc., Int. Conf. on Evolutionary Multi-Criterion Optimization, 608–622. New York: Springer.
Koller, M., and M. Mächler. 2020. “Definitions of -functions available in robustbase.” Accessed June 1, 2021. https://cran.r-project.org/web/packages/robustbase/vignettes/psi_functions.pdf.
Li, G. 1985. “Robust regression.” In Vol. 281 of Exploring data tables, trends, and shapes, U340. Hoboken, NJ: Wiley.
Ljung, L. 2010. “Perspectives on system identification.” Ann. Rev. Control 34 (1): 1–12. https://doi.org/10.1016/j.arcontrol.2009.12.001.
Long, J., K. Xueyuan, H. Haihong, Q. Zhinian, and W. Yehong. 2005. “Study on the overfitting of the artificial neural network forecasting model.” Acta Meteorologica Sin. 19 (2): 216–225.
Marano, G. C., G. Quaranta, and R. Greco. 2009. “Multi-objective optimization by genetic algorithm of structural systems subject to random vibrations.” Struct. Multidiscip. Optim. 39 (4): 385–399. https://doi.org/10.1007/s00158-008-0330-8.
Marasco, S., and G. P. Cimellaro. 2021. “A new evolutionary polynomial regression technique to assess the fundamental periods of irregular buildings.” Earthquake Eng. Struct. Dyn. 50 (8): 2195–2211. https://doi.org/10.1002/eqe.3441.
Mohsenijam, A., M.-F. F. Siu, and M. Lu. 2017. “Modified stepwise regression approach to streamlining predictive analytics for construction engineering applications.” J. Comput. Civ. Eng. 31 (3): 04016066. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000636.
Monti, G., G. Quaranta, and G. C. Marano. 2010. “Genetic-algorithm-based strategies for dynamic identification of nonlinear systems with noise-corrupted response.” J. Comput. Civ. Eng. 24 (2): 173–187. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000024.
Mphonde, A. G., and G. C. Frantz. 1984. “Shear tests of high-and low-strength concrete beams without stirrups.” J. Proc. 81 (4): 350–357.
Oreta, A. W. C. 2004. “Simulating size effect on shear strength of RC beams without stirrups using neural networks.” Eng. Struct. 26 (5): 681–691. https://doi.org/10.1016/j.engstruct.2004.01.009.
Polat, E. 2020. “The effects of different weight functions on partial robust M-regression performance: A simulation study.” Commun. Stat. - Simul. Comput. 49 (4): 1089–1104. https://doi.org/10.1080/03610918.2019.1586926.
Quarteroni, A. 2009. “Mathematical models in science and engineering.” Not. AMS 56 (1): 10–19.
Rajagopalan, K., and P. M. Ferguson. 1968. “Exploratory shear tests emphasizing percentage of longitudinal steel.” J. Proc. 65 (8): 634–638.
Rebeiz, K. S. 1999. “Shear strength prediction for concrete members.” J. Struct. Eng. 125 (3): 301–308. https://doi.org/10.1061/(ASCE)0733-9445(1999)125:3(301).
Rousseeuw, P. J., and A. M. Leroy. 2005. Robust regression and outlier detection. New York: Wiley.
Taylor, R. 1960. “Some shear tests on reinforced concrete beams without shear reinforcement.” Mag. Concr. Res. 12 (36): 145–154. https://doi.org/10.1680/macr.1960.12.36.145.
Tompos, E. J., and R. J. Frosch. 2002. “Influence of beam size, longitudinal reinforcement, and stirrup effectiveness on concrete shear strength.” Struct. J. 99 (5): 559–567.
Yegnanarayana, B. 2009. Artificial neural networks. New Delhi, India: PHI Learning.
Zararis, P. D., and G. C. Papadakis. 2001. “Diagonal shear failure and size effect in RC beams without web reinforcement.” J. Struct. Eng. 127 (7): 733–742. https://doi.org/10.1061/(ASCE)0733-9445(2001)127:7(733).
Zillner, S., J. A. Gomez, A. G. Robles, E. Curry, C. Södergård, N. Boujemaa, A. Metzger, Z. Sabeur, M. Kaltenböck, and T. Hahn. 2018. Data-driven artificial intelligence for european economic competitiveness and societal progress: BDVA position statement, November 2018. Bruxelles, Belgium: Big Data Value Aisbl.
Zitzler, E., and L. Thiele. 1999. “Multiobjective evolutionary algorithms: A comparative case study and the strength Pareto approach.” IEEE Trans. Evol. Comput. 3 (4): 257–271. https://doi.org/10.1109/4235.797969.
Information & Authors
Information
Published In
Journal of Computing in Civil Engineering
Volume 35 • Issue 6 • November 2021
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Sep 28, 2020
Accepted: May 1, 2021
Published online: Jul 26, 2021
Published in print: Nov 1, 2021
Discussion open until: Dec 26, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- M. Z. Naser, Integrating Machine Learning Models into Building Codes and Standards: Establishing Equivalence through Engineering Intuition and Causal Logic, Journal of Structural Engineering, 10.1061/JSENDH.STENG-12934, 150, 5, (2024).
- Beibei Xiong, Devid Falliano, Luciana Restuccia, Fabio Di Trapani, Cristoforo Demartino, Giuseppe Carlo Marano, Mortar with Substituted Recycled PET Powder: Experimental Characterization and Data-Driven Strength Predictive Models, Journal of Materials in Civil Engineering, 10.1061/JMCEE7.MTENG-16065, 35, 9, (2023).
- Ruan G.S. Gomes, Guilherme J.C. Gomes, Jasper A. Vrugt, A hybrid multi-step sensitivity-driven evolutionary polynomial regression enables robust model structure selection, Engineering Applications of Artificial Intelligence, 10.1016/j.engappai.2022.105421, 116, (105421), (2022).
- Sebastiano Marasco, Giuseppe Carlo Marano, Gian Paolo Cimellaro, Evolutionary polynomial regression algorithm combined with robust bayesian regression, Advances in Engineering Software, 10.1016/j.advengsoft.2022.103101, 167, (103101), (2022).