Optimization of material composition of nonhomogeneous plate for thermal stress relaxation making use of neural network. Analysis taking into account the relative heat transfer at boundary surfaces when subjected to unsteady heat supply

In this study, a neural network is applied to optimization problems of material compositions for a nonhomogeneous plate with arbitrarily distributed and continuously varied material properties such as Functionally Graded Material. Unsteady temperature distribution for such nonhomogeneous plate is evaluated by taking into account the bounds of the number of the layers. Furthermore, the thermal stress components for an infinitely long nonhomogeneous plate are formulated under the mechanical condition of being traction free. As a numerical example, the plate composed of zirconium oxide and titanium alloy is considered. And, as the optimization problem of minimizing the thermal stress distribution, the numerical calculations are carried out making use of neural network, and the optimum material composition is determined taking into account the effect of temperature-dependency of material properties. Furthermore, the results obtained by neural network and ordinary nonlinear programming method are compared. (author)