Soft Computing Metamodels for the Failure Prediction of T-stub Bolted Connections
In structural and mechanical fields, there is a growing trend to replace expensive numerical simulations with more cost-effective approximations. In this context, the use of metamodels represents an attractive option. Without significant loss of accuracy, metamodelling techniques can drastically reduce the computational burden required by simulations. This paper proposes a method for developing soft computing metamodels to predict the failure of steel bolted connections. The setting parameters of the metamodels are tuned by an optimisation based on genetic algorithms during the training process. The method also includes the selection of the most relevant input features to reduce the models’ complexity. In total, two well-known metamodelling techniques are evaluated to compare their performances on accuracy and parsimony. This case studies the T-stub bolted connection, which allows us to validate the proposed models. The results show soft computing’s metamodelling capacity to accurately predict the T-stub response, while reducing the number of variables and with negligible computation cost.
KeywordsMetamodelling Multilayer Perceptron Support Vector Regression Genetic Algorithms Finite Element Method T-stub connection
Unable to display preview. Download preview PDF.
- 1.ABAQUS v.6.11. Analysis User’s ManualGoogle Scholar
- 2.Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
- 6.European Committee for Standardization: EN 1993-1-8 Eurocode 3. Design of steel structures part 1-8. Design of jointsGoogle Scholar
- 7.Faella, C., Piluso, V., Rizzano, G.: Structural Steel Semirigid Connections: Theory, Design, and Software. New Directions in Civil Engineering. Taylor & Francis (1999)Google Scholar
- 11.R Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2013)Google Scholar
- 13.Sanz-García, A., Fernández-Ceniceros, J., Fernández-Martínez, R., Martínez-de Pisón, F.J.: Methodology based on genetic optimisation to develop overall parsimony models for predicting temperature settings on an annealing furnace. Ironmaking & Steelmaking, 1–12 (November 2012)Google Scholar
- 14.Sanz-García, A., Fernández-Ceniceros, J., Antoñanzas-Torres, F., Martínez-de-Pisón-Ascacibar, F.J.: Parsimonious support vector machines modelling for set points in industrial processes based on genetic algorithm optimization. In: Herrero, A., Baruque, B., Klett, F., Abraham, A., Snasel, V., de Carvalho, A.C.P.L.F., Bringas, P.G., Zelinka, I., Quintian, H., Corchado, E. (eds.) International Joint Conference SOCO’13-CISIS’13-ICEUTE’13. AISC, vol. 239, pp. 1–10. Springer, Heidelberg (2014)Google Scholar
- 15.Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer-Verlag New York, Inc., New York (1995)Google Scholar