Scalability of Graph Neural Network in Accurate Prediction of Frictional Contact Network in Suspensions

TL;DR

This paper presents a scalable Graph Neural Network model that accurately predicts frictional contact networks in dense suspensions, enabling faster and cost-effective analysis of shear thickening behavior in large systems.

Contribution

The study introduces a GNN model capable of predicting FCNs in dense suspensions, demonstrating robustness and scalability across various conditions and system sizes.

Findings

GNN accurately predicts FCNs in simulations.

Model generalizes to different stress levels and system sizes.

Provides faster, lower-cost predictions compared to traditional methods.

Abstract

Dense suspensions often exhibit shear thickening, characterized by a dramatic increase in viscosity under large external forcing. This behavior has recently been linked to the formation of a system-spanning frictional contact network (FCN), which contributes to increased resistance during deformation. However, identifying these frictional contacts poses experimental challenges and is computationally expensive. This study introduces a Graph Neural Network (GNN) model designed to accurately predict FCNs in two dimensional simulations of dense shear thickening suspensions. The results demonstrate the robustness and scalability of the GNN model across various stress levels $(\sigma)$, packing fractions$(\phi)$, system sizes, particle size ratios$(\Delta)$, and amount of smaller particles. The model is further able to predict both the occurrence and structure of the FCN. The presented model is accurate and interpolates and extrapolates to conditions far from its control parameters. This machine learning approach provides an accurate, lower cost, and faster predictions of suspension properties compared to conventional methods, while it is trained using only small systems. Ultimately, the findings in this study pave the way for predicting frictional contact networks in real-life large-scale polydisperse suspensions, for which theoretical models are largely limited owing to computational challenges.