UPDF AI

Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture

S. Niaki,E. Haghighat,2 Auteurs,R. Vaziri

2020 · DOI: 10.1016/j.cma.2021.113959
arXiv.org · 253 citations

TLDR

A Physics-Informed Neural Network (PINN) is presented to simulate the thermochemical evolution of a composite material on a tool undergoing cure in an autoclave by optimizing the parameters of a deep neural network using a physics-based loss function.