Accurately Solving Physical Systems with Graph Learning

06/06/2020
by   Han Shao, et al.
0

Iterative solvers are widely used to accurately simulate physical systems. These solvers require initial guesses to generate a sequence of improving approximate solutions. In this contribution, we introduce a novel method to accelerate iterative solvers for physical systems with graph networks (GNs) by predicting the initial guesses to reduce the number of iterations. Unlike existing methods that aim to learn physical systems in an end-to-end manner, our approach guarantees long-term stability and therefore leads to more accurate solutions. Furthermore, our method improves the run time performance of traditional iterative solvers. To explore our method we make use of position-based dynamics (PBD) as a common solver for physical systems and evaluate it by simulating the dynamics of elastic rods. Our approach is able to generalize across different initial conditions, discretizations, and realistic material properties. Finally, we demonstrate that our method also performs well when taking discontinuous effects into account such as collisions between individual rods. A video showing dynamic results of our graph learning assisted simulations of elastic rods can be found on the project website available at http://computationalsciences.org/publications/shao-2020-physical-systems-graph-learning.html .

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/28/2022

Learning to Simulate Unseen Physical Systems with Graph Neural Networks

Simulation of the dynamics of physical systems is essential to the devel...
research
01/21/2020

Learning to Control PDEs with Differentiable Physics

Predicting outcomes and planning interactions with the physical world ar...
research
05/01/2018

Falsification of Cyber-Physical Systems Using Deep Reinforcement Learning

With the rapid development of software and distributed computing, Cyber-...
research
03/22/2020

Interpretable machine learning models: a physics-based view

To understand changes in physical systems and facilitate decisions, expl...
research
02/23/2023

Grounding Graph Network Simulators using Physical Sensor Observations

Physical simulations that accurately model reality are crucial for many ...
research
06/23/2020

Learning Physical Constraints with Neural Projections

We propose a new family of neural networks to predict the behaviors of p...
research
04/28/2020

VIGN: Variational Integrator Graph Networks

Rich, physically-informed inductive biases play an imperative role in ac...

Please sign up or login with your details

Forgot password? Click here to reset