Estimating Contact Force Chains Using Artificial Neural Network

Mengmeng Wu,Jianfeng Wang

doi:10.3390/app11146278

Abstract

The inhomogeneous distribution of contact force chains (CFC) in quasi-statically sheared granular materials dominates their bulk mechanical properties. Although previous micromechanical investigations have gained significant insights into the statistical and spatial distribution of CFC, they still lack the capacity to quantitatively estimate CFC evolution in a sheared granular system. In this paper, an artificial neural network (ANN) based on discrete element method (DEM) simulation data is developed and applied to predict the anisotropy of CFC in an assembly of spherical grains undergoing a biaxial test. Five particle-scale features including particle size, coordination number, x- and y-velocity (i.e., x and y-components of the particle velocity), and spin, which all contain predictive information about the CFC, are used to establish the ANN. The results of the model prediction show that the combined features of particle size and coordination number have a dominating influence on the CFC’s estimation. An excellent model performance manifested in a close match between the rose diagrams of the CFC from the ANN predictions and DEM simulations is obtained with a mean accuracy of about 0.85. This study has shown that machine learning is a promising tool for studying the complex mechanical behaviors of granular materials.

Highlights

It is well known that granular materials such as sand, gravel and coal exhibit a wide range of complex mechanical behaviors which are caused by the highly convoluted nature of their topological packing structure, individual grain morphology, microstructure and physical properties, as well as the contact mechanics of a large assembly of interacting grains [1,2]
The interparticle contact[36], forcethe is evolution mathematically defined by the contact model adopted in the cannot be analytically model adopted in the discrete element method (DEM) modeling [36], the evolution of contact force chains (CFC) cannot be analytically model adopted in the
A multilayer feedforward artificial neural network (ANN) model based on a detailed set of 2D

Summary

Introduction

It is well known that granular materials such as sand, gravel and coal exhibit a wide range of complex mechanical behaviors which are caused by the highly convoluted nature of their topological packing structure, individual grain morphology, microstructure and physical properties, as well as the contact mechanics of a large assembly of interacting grains [1,2]. Over the last two decades, X-ray microcomputed tomography (micro-CT) has been increasingly used as a powerful tool for the investigation of the grain-scale mechanical behavior of granular materials [6,7,8,9,10,11,12,13,14]. This tool makes it possible to capture and characterize the interparticle contacts of granular materials and their evolutions under the triaxial shearing condition [15,16]. To gain new insight into the physical processes of granular materials, it is essential to estimate the interparticle contact forces in the shearing test

Objectives

Methods

Results

Discussion

Conclusion