Abstract
This paper presents an innovative machine learning approach for the formulation of load carrying capacity of castellated steel beams (CSB). New design equations were developed to predict the load carrying capacity of CSB using linear genetic programming (LGP), and an integrated search algorithm of genetic programming and simulated annealing, called GSA. The load capacity was formulated in terms of the geometrical and mechanical properties of the castellated beams. An extensive trial study was carried out to select the most relevant input variables for the LGP and GSA models. A comprehensive database was gathered from the literature to develop the models. The generalization capabilities of the models were verified via several criteria. The sensitivity of the failure load of CSB to the influencing variables was examined and discussed. The employed machine learning systems were found to be effective methods for evaluating the failure load of CSB. The prediction performance of the optimal LGP model was found to be better than that of the GSA model.
Similar content being viewed by others
References
Zirakian T, Showkati H (2006) Distortional buckling of castellated beams. J Const Steel Res 65:863–871
Amayreh L, Saka MP (2005) Failure load prediction of castellated beams using artificial neural networks. Asian J Civ Eng 6(1–2):35–54
Gandomi AH, Tabatabaie SM, Moradian MH, Radfar A, Alavi AH (2011) A new prediction model for load capacity of castellated steel beams. J Constr Steel Res 67(7):1096–1105
Kerdal D, Nethercot DA (1984) Failure modes for castellated beams. J Constr Steel Res 4:295–315
Knowles PR (1991) Castellated beams. Proc Inst Civ Eng Part 1 90:521–536
Mitchell T (1997) Does machine learning really work? AI Mag 18(3):11–20
Alavi AH, Gandomi AH (2011) Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing. Comput Struct 89(23–24):2176–2194
El-Shafie A, Abdelazim T, Noureldin A (2010) Neural network modeling of time-dependent creep deformations in masonry structures. Neural Comput Appl 19:583–594
Chakraverty S, Gupta P, Sharma S (2010) Neural network-based simulation for response identification of two-storey shear building subject to earthquake motion. Neural Comput Appl 19:367–375
Kraslawski A, Pedrycz W, Nyström L (1999) Fuzzy neural network as instance generator for case-based reasoning system: an example of selection of heat exchange equipment in mixing. Neural Comput Appl 8(2):106–113
Cao M, Qiao P (2008) Neural network committee-based sensitivity analysis strategy for geotechnical engineering problems. Neural Comput Appl 17:509–519
Alavi AH, Gandomi AH, Mollahasani A, Heshmati AAR, Rashed A (2010) Modeling of maximum dry density and optimum moisture content of stabilized soil using artificial neural networks. J Plant Nutr Soil Sci 173(3):368–379
Gholizadeh S, Pirmoz A, Attarnejad R (2011) Assessment of load carrying capacity of castellated steel beams by neural networks. J Constr Steel Res 67:770–779
Simpson AR, Priest SD (1993) The application of genetic algorithms to optimisation problems in geotechnics. Comput Geotech 15(1):1–19
Dehuri S, Cho SB (2010) A hybrid genetic based functional link artificial neural network with a statistical comparison of classifiers over multiple datasets. Neur Comput Appl 19(2):317–328
Paul RJ, Chanev TS (1997) Optimising a complex discrete event simulation model using a genetic algorithm. Neur Comput Appl 6(4):229–237
Zhou ZH, Chen SF (2002) Evolving fault-tolerant neural networks. Neur Comput Appl 11(3–4):156–160
Koza JR (1992) Genetic programming: on the programming of computers by means of natural selection. MIT Press, Cambridge
Gandomi AH, Alavi AH, Mirzahosseini MR, Moqhadas Nejad F (2011) Nonlinear genetic-based models for prediction of flow number of asphalt mixtures. J Mater Civ Eng ASCE 23(3):248–263
Gandomi AH, Alavi AH (2012) A new multi-gene genetic programming approach to nonlinear system modeling. Part II: geotechnical and earthquake engineering problems. Neur Comput Appl 21:189–201
Gandomi AH, Alavi AH (2011) Multi-stage genetic programming: a new strategy to nonlinear system modeling. Inf Sci 181(23):5227–5239
Gandomi AH, Alavi AH (2012) A new multi-gene genetic programming approach to nonlinear system modeling. Part I: materials and structural engineering problems. Neur Comput Appl 21:171–187
Brameier M, Banzhaf W (2007) Linear genetic programming. Springer, New York
Brameier M, Banzhaf W (2001) A comparison of linear genetic programming and neural networks in medical data mining. IEEE Trans Evol Comput 5(1):17–26
Alavi AH, Gandomi AH (2011) A robust data mining approach for formulation of geotechnical engineering systems. Eng Comput 28(3):242–274
Alavi AH, Gandomi AH (2012) Energy-based models for assessment of soil liquefaction. Geosci Front 3(4):541–555
Metropolis N, Rosenbluth AW, Rosenbluth MN, Teller AH, Teller E (1953) Equation of state calculations by fast computing mechanics. J Chem Phys 21(6):1087–1092
Folino G, Pizzuti C, Spezzano G (2000) Genetic programming and simulated annealing: a hybrid method to evolve decision trees. In: Proceedings of EuroGP’2000, 1802, pp 294–303
Deschaine LM, Zafran FA, Patel JJ, Amick D, Pettit R, Francone FD, Nordin P, Dilkes E, Fausett LV (2000) Solving the unsolved using machine learning, data mining and knowledge discovery to model a complex production process. In: Proceedings of advanced technology simulation conference, Washington
Alavi AH, Ameri M, Gandomi AH, Mirzahosseini MR (2011) Formulation of flow number of asphalt mixes using a hybrid computational method. Constr Build Mater 25(3):1338–1355
Aminian P, Javid MR, Asghari A, Gandomi AH, Arab Esmaeili M (2011) A robust predictive model for base shear of steel frame structures using a hybrid genetic programming and simulated annealing method. Neural Comput Appl (in press) doi: 10.1007/s00521-011-0689-0
Hall M, Smith L (1996) Practical feature subset selection for machine learning. In: Proceedings of the Australian computer science conference (University of Western Australia). University of Waikato, Hamilton
Tesink S (2007) Improving intrusion detection systems through machine learning. ILK Research Group, Technical Report Series no. 07–02
Gandomi AH, Alavi AH, Yun GJ (2011) Nonlinear modeling of shear strength of SFRCB beams using linear genetic programming. Struct Eng Mech 38(1):1–25
Poli R, Langdon WB, McPhe NF, Koza JR (2007) Genetic programming: an introductory tutorial and a survey of techniques and applications. Technical Report [CES-475], University of Essex, Colchester
Francone FD, Deschaine LM (2004) Extending the boundaries of design optimization by integrating fast optimization techniques with machine-code-based, linear genetic programming. Inf Sci 161:99–120
Okubo T, Nethercot DA (1985) Web post strength in castellated beams. Proc Inst Civ Eng Part 2 79:533–557
Das SK, Basudhar PK (2008) Prediction of residual friction angle of clays using artificial neural network. Eng Geol 100(3–4):l142–l145
Zaarour W, Redwood R (1996) Web buckling in thin castellated beams. J Struct Eng ASCE 122:860–866
Redwood R, Demirdjian S (1998) Castellated beam web buckling in shear. J Struct Eng ASCE 124:1202–1207
Banzhaf W, Nordin P, Keller R, Francone F (1998) Genetic programming—an introduction. On the automatic evolution of computer programs and its application. Dpunkt/Morgan Kaufmann, Heidelberg
Deschaine LM (2000) Using genetic programming to develop a C/C++ simulation model of a waste incinerator. Science Applications International Corp, Draft Technical Report
Francone FD (2004) Discipulus lite™ software owner’s manual. Machine Learning Technologies Inc, Littleton
Smith GN (1986) Probability and statistics in civil engineering. Collins, London
Frank IE, Todeschini R (1994) The data analysis handbook. Elsevier, Amsterdam
Golbraikh A, Tropsha A (2002) Beware of q2. J Mole Graph Model 20:269–276
Roy PP, Roy K (2008) On some aspects of variable selection for partial least squares regression models. QSAR Comb Sci 27:302–313
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix 1: The BEST LGP solution for the prediction of the load carrying capacity of CSB
The optimum LGP program can be compiled in any C++ environment. (Note: v[0], …, v[3], respectively, represent d g, h, t w × F yw, and e. f[0] is the output parameter.)
{ |
double f[8]; |
double tmp = 0; |
f[1] = f[2] = f[3] = f[4] = f[5] = f[6] = f[7] = 0; |
f[0] = v[0]; |
l0: f[0]/ = v[3]; |
l1: tmp = f[1]; f[1] = f[0]; f[0] = tmp; |
l2: f[0]+ =f[1]; |
l3: f[0] = sqrt(f[0]); |
l4: tmp = f[1]; f[1] = f[0]; f[0] = tmp; |
l5: f[0]− = 8; |
l6: f[0]− = 4; |
l7: f[0]* = 3; |
l8: f[0]* = f[1]; |
f[1]/ = f[0]; |
l9: f[0]− = 9; |
l10: f[0]+ = v[0]; |
l11: f[0]− = v[1]; |
l12: f[0]/ = 5; |
l13: f[0]+ = v[2]; |
l14: f[0]/ = 9; |
l15: f[0]* = f[0]; |
f[0]− = f[1]; |
l16: f[0]− = v[1]; |
l17: f[0]− = v[1]; |
l18: f[0]− = 5; |
l19: f[0]+ = v[0]; |
l20: f[0]− = v[1]; |
l21: f[0]/ = 5; |
l22: |
l23: |
return f[0]; |
} |
Appendix 2: The best GSA solution for the prediction of the load carrying capacity of CSB
The optimum GSA program can be compiled in any C++ environment.
{ |
double f[8]; |
double tmp = 0; |
f[1] = f[2] = f[3] = f[4] = f[5] = f[6] = f[7] = 0; |
f[0] = v[0]; |
l0: f[0]− = v[1]; |
l1: f[0]+ = 4; |
l2: f[0]+ = v[2]; |
l3: f[0]− = v[1]; |
l4: f[0]+ = v[2]; |
l5: f[0]* = f[0]; |
tmp = f[1]; f[1] = f[0]; f[0] = tmp; |
l6: f[0]− = 8; |
l7: f[0]− = 5; |
l8: f[0]+ = 1; |
l9: f[0]* = 7; |
l10: f[1]/ = f[0]; |
f[0]− = f[1]; |
l11: f[0]− = v[3]; |
l12: f[0]+ = v[2]; |
l13: f[0]/ = 5; |
l14: f[0]/ = 5; |
l15: |
l16: |
return f[0]; |
} |
Rights and permissions
About this article
Cite this article
Aminian, P., Niroomand, H., Gandomi, A.H. et al. New design equations for assessment of load carrying capacity of castellated steel beams: a machine learning approach. Neural Comput & Applic 23, 119–131 (2013). https://doi.org/10.1007/s00521-012-1138-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-012-1138-4