CaltechAUTHORS
  A Caltech Library Service

Bridging length scales in granular materials using convolutional neural networks

Mital, Utkarsh and Andrade, José E. (2022) Bridging length scales in granular materials using convolutional neural networks. Computational Particle Mechanics, 9 (1). pp. 221-235. ISSN 2196-4378. doi:10.1007/s40571-021-00405-1. https://resolver.caltech.edu/CaltechAUTHORS:20210506-104707586

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210506-104707586

Abstract

Granular materials are complex systems whose macroscopic mechanics are governed by particles at the grain-scale. The need to understand their grain-scale behavior has motivated significant experimental and modeling efforts. Bridging the grain-scale with the continuum scale is important in order to develop constitutive theories based on grain-scale behavior, as well as for interpreting the results of grain-scale models and experiments from a macroscopic context. In this work, we present a new data-driven framework based on convolutional neural networks to bridge the grain-scale and continuum scale in granular materials. We use this framework to obtain a micromechanical model of stress and demonstrate that spatial correlations at the grain-scale are critical for bridging length scales. Our results suggest that it is possible to learn data-driven relationships between the grain-scale and macroscale even if we have limited knowledge about the physical state of a granular system. We also observed that it is possible to train a model to predict macroscopic stress using only a subset of the contact data for each time step. This points to the discovery of a new pattern in granular systems, whereby any spatially correlated subset of contact data is sufficient to model macroscopic stress, regardless of how much force they may be carrying. Finally, we demonstrated that our framework is robust with potential for generalizability in time.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1007/s40571-021-00405-1DOIArticle
https://rdcu.be/cj63aPublisherFree ReadCube access
ORCID:
AuthorORCID
Mital, Utkarsh0000-0001-9794-382X
Additional Information:© OWZ 2021. Received 17 December 2020; Revised 11 March 2021; Accepted 17 March 2021; Published 01 April 2021. Data Availability: Data were obtained from the work done by Marteau and Andrade [42]. The authors acknowledge funding support by Army Research Office, under Grant Number W911NF-17-1-0212. The authors declare that they have no conflict of interest.
Funders:
Funding AgencyGrant Number
Army Research Office (ARO)W911NF-17-1-0212
Subject Keywords:Granular Materials; Machine learning; Convolutional neural networks; Pattern discovery; Data-driven mechanics; Multiscale
Issue or Number:1
DOI:10.1007/s40571-021-00405-1
Record Number:CaltechAUTHORS:20210506-104707586
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210506-104707586
Official Citation:Mital, U., Andrade, J.E. Bridging length scales in granular materials using convolutional neural networks. Comp. Part. Mech. 9, 221–235 (2022). https://doi.org/10.1007/s40571-021-00405-1
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:108989
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:06 May 2021 17:58
Last Modified:15 Feb 2022 23:11

Repository Staff Only: item control page