Learning Physics-Consistent Particle Interactions

02/01/2022
by   Zhichao Han, et al.
0

Interacting particle systems play a key role in science and engineering. Access to the governing particle interaction law is fundamental for a complete understanding of such systems. However, the inherent system complexity keeps the particle interaction hidden in many cases. Machine learning methods have the potential to learn the behavior of interacting particle systems by combining experiments with data analysis methods. However, most existing algorithms focus on learning the kinetics at the particle level. Learning pairwise interaction, e.g., pairwise force or pairwise potential energy, remains an open challenge. Here, we propose an algorithm that adapts the Graph Networks framework, which contains an edge part to learn the pairwise interaction and a node part to model the dynamics at particle level. Different from existing approaches that use neural networks in both parts, we design a deterministic operator in the node part. The designed physics operator on the nodes restricts the output space of the edge neural network to be exactly the pairwise interaction. We test the proposed methodology on multiple datasets and demonstrate that it achieves considerably better performance in inferring correctly the pairwise interactions while also being consistent with the underlying physics on all the datasets than existing purely data-driven models. The developed methodology can support a better understanding and discovery of the underlying particle interaction laws, and hence guide the design of materials with targeted properties.

READ FULL TEXT

page 4

page 6

page 7

page 8

research
04/30/2023

Collective Relational Inference for learning physics-consistent heterogeneous particle interactions

Interacting particle systems are ubiquitous in nature and engineering. R...
research
03/03/2022

NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields

Deep learning has shown great potential for modeling the physical dynami...
research
06/04/2021

Data-driven discovery of interacting particle systems using Gaussian processes

Interacting particle or agent systems that display a rich variety of col...
research
07/25/2023

A model for efficient dynamical ranking in networks

We present a physics-inspired method for inferring dynamic rankings in d...
research
04/13/2019

Combining Physical Simulators and Object-Based Networks for Control

Physics engines play an important role in robot planning and control; ho...
research
05/08/2020

Parsimonious neural networks learn classical mechanics, its underlying symmetries, and an accurate time integrator

Machine learning is playing an increasing role in the physical sciences ...
research
04/27/2020

Neural Network and Particle Filtering: A Hybrid Framework for Crack Propagation Prediction

Crack detection, length estimation, and Remaining Useful Life (RUL) pred...

Please sign up or login with your details

Forgot password? Click here to reset