Advertisement

Multilayer-Perceptron Network Ensemble Modeling with Genetic Algorithms for the Capacity of Bolted Lap Joint

  • Julio Fernández-Ceniceros
  • Andrés Sanz-García
  • Fernando Antoñanzas-Torres
  • F. Javier Martínez-de-Pisón-Ascacibar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7208)

Abstract

The assessment of failure force in bolted lap joints is a critical parameter in the design of steel structures. This kind of bolted joint shows a highly nonlinear behaviour so traditional analytical models are not very reliable. By contrast, other classical technique like finite element analysis provides a powerful tool to solve nonlinearities but usually with a high computational cost. In this article, we propose a data-driven approach based on multilayer-perceptron network ensemble model for failure force prediction, using a data set generated via finite element simulations of different bolted lap joints. Numeric ensemble methods combine multiple predictors to obtain a single output through average. Moreover, a procedure based on genetic algorithms is used to optimize the ensemble parameters. Results show greater generalization capacity than single prediction model. The resulting ensemble includes the advantages of finite element method whereas reduces the complexity and requires less computation.

Keywords

Genetic Algorithms Multilayer-perceptron Network Ensemble Model Finite Element Method Bolted Connection Lap Joint 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Annicchiarico, W., Cerrolaza, M.: Structural shape optimization 3d nite-element models based on genetic algorithms and geometric modeling. Finite Elements in Analysis and Design 37, 403–415 (2001)zbMATHCrossRefGoogle Scholar
  2. 2.
    Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
  3. 3.
    Breiman, L.: Bagging predictors. Machine Learning 24, 123–140 (1996)MathSciNetzbMATHGoogle Scholar
  4. 4.
    Bursi, O.S., Jaspart, J.P.: Benchmarks for finite element modelling of bolted steel connections. Journal of Constructional Steel Research 43(1-3), 17–42 (1997)CrossRefGoogle Scholar
  5. 5.
    Corchado, E., Abraham, A., Carvalho, A.: Hybrid intelligent algorithms and applications. Information Sciences 180(14), 2633–2634 (2010)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Corchado, E., Graña, M., Wozniak, M.: New trends and applications on hybrid artificial intelligence systems. Neurocomputing 75(1), 61–63 (2012)CrossRefGoogle Scholar
  7. 7.
    European Committee for Standardization: EN 10025-2: 2004. Non-alloy structural steels: grades, mechanical properties and nearest equivalent gradesGoogle Scholar
  8. 8.
    European Committee for Standardization: EN 1993-1-8 Eurocode 3. Design of steel structures part 1-8. Design of jointsGoogle Scholar
  9. 9.
    Fernández, J., Pernía, A., de Pisón, F.M., Lostado, R.: Prediction models for calculating bolted connections using data mining techniques and the finite element method. Engineering Structures 32(10), 3018–3027 (2010)CrossRefGoogle Scholar
  10. 10.
    Friedman, J.H., Popescu, B.E.: Importance sampled learning ensembles. Tech. rep., Stanford University, Department of Statistics (2003)Google Scholar
  11. 11.
    Garcia-Pedrajas, N., Hervas-Martinez, C., Ortiz-Boyer, D.: Cooperative coevolution of artificial neural network ensembles for pattern classification 9(3), 271–302 (2005)Google Scholar
  12. 12.
    Hansen, L.K., Salamon, P.: Neural network ensembles 12(10), 993–1001 (1990)Google Scholar
  13. 13.
    Hornik, K., Stinchcombe, M.B., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2(5), 359–366 (1989)CrossRefGoogle Scholar
  14. 14.
    Jones, M.T.: Artificial Intelligence: A Systems Approach. Infinity Science Press, LLC (2008)Google Scholar
  15. 15.
    Ju, S.-H., Fan, C.-Y., Wu, G.H.: Three-dimensional finite elements of steel bolted connections. Engineering Structures 26(3), 403–413 (2004)CrossRefGoogle Scholar
  16. 16.
    Kim, T.S., Kuwamura, H., Cho, T.J.: A parametric study on ultimate strength of single shear bolted connections with curling. Thin-Walled Structures 46(1), 38–53 (2008)CrossRefGoogle Scholar
  17. 17.
    Loureiro, A., Gutiérrez, R., Reinosa, J., Moreno, A.: Axial stiffness prediction of non-preloaded t-stubs: An analytical frame approach. Journal of Constructional Steel Research 66(12), 1516–1522 (2010)CrossRefGoogle Scholar
  18. 18.
    Ovaska, S.J., Kamiya, A., Chen, Y.: Fusion of soft computing and hard computing: computational structures and characteristic features 36(3), 439–448 (2006)Google Scholar
  19. 19.
    Salih, E.L., Gardner, L., Nethercot, D.A.: Numerical investigation of net section failure in stainless steel bolted connections. Journal of Constructional Steel Research 66(12), 1455–1466 (2010)CrossRefGoogle Scholar
  20. 20.
    Yang, Y.-Y., Mahfouf, M., Pnoutsos, G.: Development of a parsimonious ga-nn ensemble model with a case study for charpy impact energy prediction. Advances in Engineering Software 42, 435–443 (2011)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Julio Fernández-Ceniceros
    • 1
  • Andrés Sanz-García
    • 1
  • Fernando Antoñanzas-Torres
    • 1
  • F. Javier Martínez-de-Pisón-Ascacibar
    • 1
  1. 1.EDMANS Research GroupUniversity of La RiojaLogroñoSpain

Personalised recommendations