Neural network prediction of load capacity for eccentrically loaded reinforced concrete columns

Magdalena Jakubek

doi:10.24423/cames.84

Magdalena Jakubek Institute for Computational Civil Engineering, Cracow University of Technology, Kraków

DOI: http://dx.doi.org/10.24423/cames.84

Abstract

This paper presents neural networks prediction of load capacity for eccentrically loaded reinforced concrete (RC) columns. The direct modelling of the load capacity of RC columns by means of the finite element method presents several difficulties, mainly in geometry representation and handling of several nonlinearities. Properly trained neural network can provide a useful surrogate model for such columns. The paper discusses architecture and training methods of the both multi-layer perceptron (MLP) and fuzzy weights neural networks (FWNN) for this application. It also presents the performance analysis of the networks trained on data from three independent databases available in the literature.

Keywords

concrete reinforced columns, load capacity, neural networks, fuzzification,

References

[1] M. Jakubek. Application of artificial neural networks to selected problems of experimental mechanics of materials and structures, (in Polish). Ph.D. thesis, Cracow University of Technology, 2008.
[2] K. Chudyba. The influence of material and geometric characteristics on the compressive load capacity of reinforced concrete columns, (in Polish). Ph.D. thesis, Cracow University of Technology, 1999.
[3] W.B. Cranston. Analysis and design of reinforced concrete columns. Research report 20, Cement and Concrete Association, 1972.
[4] http://www.ce.washington.edu/ peera1/, 2007.
[5] Concrete and reinforced concrete structures. Static calculations and design Polish Standards PN-B-03264:2002, Polish Normalisation Committee, Warszawa, 2002.
[6] M. Bradford. Short-time and time dependent design rules for slender RC columns of circular sections. Magazine of Concrete Research, 159: 74–79, 1992.
[7] Design of concrete structures. Part 1: General rules and rules for buildings. Technical report ENV 1992-1-1, 1991.
[8] A. Lapko, B.C. Jansen. Reinforced concrete structures – design algorithms and recommendations. Arkady, Warszawa, 2006.
[9] M. Jakubek. Fuzzy weight neural network in the analysis of concrete specimens and R/C column buckling tests. Computer Assisted Mechanics and Engineering Sciences, 18(4): 243:254, 2011.