Constitutive model characterization and discovery using physics-informed deep learning

no code implementations • 18 Mar 2022 • Ehsan Haghighat, Sahar Abouali, Reza Vaziri

Additionally, in their discretized form, they are computationally very efficient, often resulting in a simple algebraic relation, and therefore they have been extensively used within large-scale explicit and implicit finite element models.

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

1 code implementation • 27 Nov 2020 • Sina Amini Niaki, Ehsan Haghighat, Trevor Campbell, Anoush Poursartip, Reza Vaziri

We present a Physics-Informed Neural Network (PINN) to simulate the thermochemical evolution of a composite material on a tool undergoing cure in an autoclave.

Transfer Learning