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

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.