Analysis of functionally graded disks using neural networks and finite element software

Abstract

This paper investigates the thermomechanical analysis of disks using deep neural networks and finite element software. The structural components are made from functionally graded materials and are subjected to combined mechanical and thermal loading. The neural network is trained using a dataset obtained through simulations performed by programming a commercially available finite element software Abaqus. Both the programs of the finite element software and the neural network-based solver application are written in Python programming language.