DeepPhysics: a physics aware deep learning framework for real-time simulation

no code implementations • 17 Sep 2021 • Alban Odot, Ryadh Haferssas, Stéphane Cotin

In this paper, we propose a solution to simulate hyper-elastic materials using a data-driven approach, where a neural network is trained to learn the non-linear relationship between boundary conditions and the resulting displacement field.

Cantilever Beam