Accurate cyclic plastic analysis using a neural network material model

The computer simulation is replacing mechanical experiments in many cases due to its cost-effectiveness and improved accuracy. Nevertheless, its application fields are still limited to elastic analysis, as there exists a significant amount of model error in present inelastic material models. In this paper, we first propose a material model using neural networks, which has the ability to describe plasticity and cyclic plasticity. The proposed model was first created with the material data of 2 1/4Cr-1 Mo steel, and the results show that the model can represent the actual cyclic plastic material behavior within a 2% error. The model is then implemented in a commercially available finite element analysis package and the cyclic plastic deformation behavior of a test specimen of the material is predicted within a 3% error. (C) 2003 Elsevier Ltd. All rights reserved.