Neural network optimization of material composition of a functionally graded material plate at arbitrary temperature range and temperature rise (Q1291890)

The authors apply a neural network model to the optimization of material compositions for a functionally graded material plate with arbitrarily distributed and continuously varied in the thickness direction material properties. The unsteady temperature distribution is evaluated by taking into account the bounds on the number of layers. The authors obtain thermal stresses for an infinite plate under traction-free conditions. The optimal material composition is determined for temperature-dependent material properties, and the results obtained by the neural network method are compared with the results from the nonlinear programming method.