The prediction of contact force networks in granular materials based on graph neural networks

Abstract

The contact force network, usually organised inhomogeneously by the inter-particle forces on the bases of the contact network topologies, is essential to the rigidity and stability in amorphous solids. How to capture such a 'backbone' is crucial to the understanding of various anomalous properties or behaviors in those materials, which remains a central challenge presently in physics, engineering, or material science. Here we use a novel graph neural network to predict the contact force network in two-dimensional granular materials under uniaxial compression. With the edge classification model in the framework of the deep graph library, we show that the inter-particle contact forces can be accurately estimated purely from the knowledge of the static microstructures, which can be acquired from a discrete element method or directly visualized from experimental methods. By testing the granular packings with different structural disorders and pressure, we further demonstrate the robustness of the optimized graph neural network to changes in various model parameters. Our research tries to provide a new way of extracting the information about the inter-particle forces, which substantially improves the efficiency and reduces the costs compared to the traditional experiments.

Modulation of Auger recombination via facet engineering in CsPbBr3 perovskite nanocrystals

“…where a F denotes the dimensionless Fro ¨hlich coupling constant that describes the interaction of charge carriers with longitudinal optical (LO) phonons, o LO denotes the angular frequency of the typical LO-phonon mode (B20 meV), 40 h is the reduced Planck constant and e N (e s ) denotes the high-frequency (static) dielectric constant. Given that e N E e opt and e N { e s for the CPB perovskite system, 36,39 eqn (10) can be transformed to…”

Prediction of Tooth Profile Deviation for WEDM Rigid Gears Based on ISSA-LSSVM

“…Currently, the setting of WEDM process parameters mostly relies on the operator's experience, which is unable to adapt to the processing of variable working conditions and affects the processing quality of the workpiece. Prediction problems have been tackled using a range of algorithms in recent years, including neural networks, random forests, support vector machines (SVMs), and the least squares support vector machine (LSSVM) [18][19][20][21]. Neural networks, despite their complex structure, have poor generalization ability.…”