Abstract The subject of investigation in this paper is the modeling of adiabatic thermally expanded hyperelasticity. Through the use of neural networks Cauchy stresses were predicted from logarithmic strains and the derivatives of the neural network outputs with respect to the strains were used to compute the material stiffness matrix. Firstly, a neural network based model for incompressible behaviour was developed, tested and compared with available literature to ensure the validity of the approach. Ogden’s model was used as a base with which results were compared to. Afterwards the model was expanded to accommodate thermoelastic behaviour and the results were compared to the expanded Ogden’s model for thermoelasticity.
展开▼
