ANN constitutive material model in the shakedown analysis of an aluminum structure
Abstract
The paper presents the application of artificial neural networks (ANN) for description of the Ramberg- Osgood (RO) material model, representing the non linear strain-stress relationship of ε (σ). A neural model of material (NMM) is a feed-forward layered neural network (FLNN) whose parameters were determined using the penalized least squares (PLS) method. A FLNN performing the inverse problem: σ(ε), using pseudo empirical patterns, was developed. Two models of NMM were developed, i.e. a standard model (SNN) and a model based on Bayesian inference (BNN). The properties of the models were compared on the example of a reference truss structure. The computations were performed by means of the hybrid FEM/NMM program, in which NMM developed previously described the current model of the material, and made it possible to explicitly build a tangent operator Et = dσ/dε. The neural model of material was applied to the analysis of the shakedown of load carrying capacity of an aluminum truss.
Keywords
artificial neural network, inverse problem, material modeling, finite element method, hybrid program, shakedown analysis,References
[1] J. Lemaitre, J.L. Chaboche. Mechanics of solid materials. University Press, Cambridge, 1994.[2] T. Furukawa, T. Sugata, S. Yoshimura, M. Hoffman. An automated system for simulation and parameter identification of inelastic constitutive models. Comput. Methods Appl. Mech. Eng., 191: 2235–2260, 2002.
[3] M. Lefik, B.A. Schrefler. Artificial neural network for parameter identifications for an elasto-plastic model of superconducting cable under cyclic loading. Comp & Struct., 80: 1699–1713, 2002.
[4] G. Bolzon, V. Buliak, G. Maier, B. Miller. Assessment of elastic-plastic material parameters comparatively by three procedures based on indentation test and inverse analysis. Inverse Problems in Science and Eng., 19: 815–837, 2011.
[5] J. Ghaboussi, D.A. Pecknold, M. Zhang, R.M. Haj-Ali. Autoprogressive training of neural network constitutive models. Int. J. Num. Meth. Eng., 42: 105–126, 1998.
[6] E. Pabisek. Identification of an equivalent model for granular soils by FEM/NMM/p-EMP hybrid system. Computer Assisted Mech. Eng. Sci., 18: 283–290, 2011.
[7] PN-EN 1999-1-1:2011, Design of aluminum structures. Part 1-1: General rules [in Polish: Projektowanie konstrukcji aluminiowych. Część 1-1: Reguły ogólne].
[8] T. Akazawa, M. Nakashima, O. Sakaguchi. Simple model for simulating hysteretic behavior involving significant strain hardening. 11th World Conf. on Earthquake Eng., 264, 1996.
[9] I.T. Nabney. Netlab: algorithms for pattern recognition, London, Springer, 2006.
[10] Neural network toolbox for use with MATLAB. The MathWorks. Inc., 2006.
[11] C.M. Bishop. Neural networks for pattern recognition. Oxford, Oxford University Press, 1995.
[12] Y.M. Hashash, S. Jung, J. Ghaboussi. Numerical implementation of a neural network based material model in finite element analysis. Int. J. Num. Meth. Eng., 59: 989–1005, 2004.
[13] A.P. Perez-Foguet, A. Rodriguez-Ferran, A. Huerta. Numerical differentiation for local and global tangent operators in computational plasticity. Comput. Methods Appl. Mech. Engrg., 189: 277–296, 2000.
[14] Z. Waszczyszyn, E. Pabisek. Elastoplastic analysis of plane steel frames by a new superelement. Archives of Civ. Eng., 48: 159–181, 2002.
[15] 20 Meter Water Tower. U.S. Army Corps of Engineers, Engineering and Construction Division. US ARMY Engineer District, Afghanistan. APO AE, 09356, 2009.
