Hybrid MES/SSN analysis of the elastic-plastic truss under cyclic loading

• Autorzy: Potrzeszcz-Sut B.

Warianty tytułu

PL

Analiza hybrydowa MES/SSN sprężysto-plastycznej konstrukcji kratowej poddanej obciążeniu cyklicznemu

• Języki publikacji: EN PL

Abstrakty

EN

The paper presents the application of a hybrid program that integrates finite element method (FEM) and artificial neural network (ANN) for nonlinear analysis of plane truss. ANN, used for the solving the inverse problem has been formulated in ‘off line’ mode. Learning and testing of ANN were carried out using pseudo empirical data. The network formed thereby constitutes the neural material model (NMM), describes the Ramberg-Osgood nonlinear physical relationship. NMM makes it possible to determine the stress and tangential module during cyclic loading of the structure. Numerical tests indicate that the developed FEM/ANN program may be applied to analyse other boundary problems in the uniaxial stress state.

Słowa kluczowe

EN

nonlinear numerical analysis; inverse problem; Ramberg-Osgood material model; artificial neural network; neural material model

PL

nieliniowa analiza numeryczna; problem odwrotny; model materiału Ramberg-Osgood; sztuczne sieci neuronowe; neuronowy model materiału

• Wydawca: Wydawnictwo Politechniki Świętokrzyskiej
• Czasopismo: Structure and Environment
• Rocznik: 2014
• Tom: Vol. 6, no. 4
• Strony: 12--16
• Opis fizyczny: Bibliogr. 8 poz., rys., wykr.

Twórcy

autor

Potrzeszcz-Sut B.

• Kielce University of Technology

Bibliografia

• [1] Hashash Y.M., Jung S., Ghaboussi J.: Numerical implementation of a neural network based material model in finite element analysis, Int. J. Num. Meth. Eng., 59 (2004), pp. 989-1005.
• [2] Furukawa T., Yagawa G.: Implicit constitutive modelling for viscoplasticity using neural networks, Intern. J. for Numerical Methods in Eng, 43 (1998) 43, pp. 195-219.
• [3] Waszczyszyn Z., Pabisek E.: Hybrid NN/FEM analysis of the elastoplastic plane stress problem, Comp. Assisted Mech. Eng. Sci., 6(1999), pp. 177-118.
• [4] Ramberg W., Osgood W.R: Description of stress-strain curves by three parameters, Technical Note No. 902, National Committee for Aeronautics, Washington DC, 1943.
• [5] Pabisek E.: Hybrid systems integrating FEM and ANN for the analysis of selected problems of structural and materials mechanics, Cracow University of Technology, Series Civil Engineering, Monograph, 369, Cracow (in Polish), 2008.
• [6] Akazawa T., Nakashima M., Sakaguchi O.: Simple model for simulating hysteretic behavior involving significant strain hardening, Eleventh World Conference on Earthquake Engineering, Paper No. 264, 1996.
• [7] Ghaboussi J., Pecknold D.A., Zhang M., Haj-Ali R.: Autoprogressive training of neural network constitutive models, Int. J. Num. Mrth. Eng., 42 (1998), pp. 105-126.
• [8] Bishop C.M.: Neural networks for pattern recognition. Oxford: Clarendon Press, 1995.