Modeling of 2D Functionally Graded Circular Plates with Artificial Neural Network

Authors : Munise Didem DEMİRBAŞ, Didem ÇAKIR

Pages : 97-110

Doi:10.47897/bilmes.840471

View : 40 | Download : 18

Publication Date : 2020-12-31

Article Type : Research Paper

Abstract :The thermo-mechanical properties of the functionally graded material insert ignore into journalissuearticles values(FGM); depend on the volumetric distribution that determines the material character, which is very important in order to overcome different operating conditions and stress levels. Three different training algorithms are used in an Artificial Neural Network insert ignore into journalissuearticles values(ANN); to determine the equivalent stress levels of a hollow disc that is functionally graded in two directions. The data set was created by choosing the most important four different equivalent stress values insert ignore into journalissuearticles values(σ_insert ignore into journalissuearticles values(eqv max max); ,σ_insert ignore into journalissuearticles values(eqv max min); ,σ_insert ignore into journalissuearticles values(eqv min max); ,σ_insert ignore into journalissuearticles values(eqv min min);); that determine the material structure in thermo-mechanical analysis. Performance estimation was performed in three different training algorithms insert ignore into journalissuearticles values(Gradient Descent Backpropagation, Gradient Descent with Momentum Backpropagation, BFGS Quasi-Newton Backpropagation Algorithm);. In this study, termomechanical behaviour was numerically determined by using finite difference method at different compositional gradient upper values to train ANN.
Keywords : Two Directional Functionally Graded Circular Plates, Finite difference method, Thermal stress analysis, Artificial neural network, Training algorithms

ORIGINAL ARTICLE URL