Learning 3D Granular Flow Simulations

TL;DR

This paper introduces a Graph Neural Networks approach to accurately model complex 3D granular flow simulations generated by discrete element methods, focusing on real-world applications like rotating drums and hoppers.

Contribution

The paper presents a novel GNN-based framework for modeling 3D granular flows, incorporating boundary conditions and interactions, advancing data-driven physical process modeling.

Findings

GNN models closely replicate LIGGGHTS simulation trajectories.

The approach effectively captures particle flow dynamics and mixing entropy.

Results demonstrate potential for data-driven simulation in granular physics.

Abstract

Recently, the application of machine learning models has gained momentum in natural sciences and engineering, which is a natural fit due to the abundance of data in these fields. However, the modeling of physical processes from simulation data without first principle solutions remains difficult. Here, we present a Graph Neural Networks approach towards accurate modeling of complex 3D granular flow simulation processes created by the discrete element method LIGGGHTS and concentrate on simulations of physical systems found in real world applications like rotating drums and hoppers. We discuss how to implement Graph Neural Networks that deal with 3D objects, boundary conditions, particle - particle, and particle - boundary interactions such that an accurate modeling of relevant physical quantities is made possible. Finally, we compare the machine learning based trajectories to LIGGGHTS trajectories in terms of particle flows and mixing entropies.