No Cover Image

Journal article 173 views 68 downloads

Deep Learning Predicts Stress–Strain Relations of Granular Materials Based on Triaxial Testing Data

Tongming QU, Shaocheng Di, Yuntian Feng Orcid Logo, Min Wang, Tingting Zhao, Mengqi Wang

Computer Modeling in Engineering & Sciences, Volume: 128, Issue: 1, Pages: 129 - 144

Swansea University Authors: Tongming QU, Yuntian Feng Orcid Logo

  • 57281.pdf

    PDF | Version of Record

    This work is licensed under a Creative Commons Attribution 4.0 International License

    Download (1.24MB)

Abstract

This study presents an AI-based constitutive modelling framework wherein the prediction model directly learns from triaxial testing data by combining discrete element modelling (DEM) and deep learning. A constitutive learning strategy is proposed based on the generally accepted frame-indifference as...

Full description

Published in: Computer Modeling in Engineering & Sciences
ISSN: 1526-1506
Published: Computers, Materials and Continua (Tech Science Press) 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57281
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: This study presents an AI-based constitutive modelling framework wherein the prediction model directly learns from triaxial testing data by combining discrete element modelling (DEM) and deep learning. A constitutive learning strategy is proposed based on the generally accepted frame-indifference assumption in constructing material constitutive models. The low-dimensional principal stress-strain sequence pairs, measured from discrete element modelling of triaxial testing, are used to train recurrent neural networks, and then the predicted principal stress sequence is augmented to other high-dimensional or general stress tensor via coordinate transformation. Through detailed hyperparameter investigations, it is found that long short-term memory (LSTM) and gated recurrent unit (GRU) networks have similar prediction performance in constitutive modelling problems, and both satisfactorily predict the stress responses of granular materials subjected to a given unseen strain path. Furthermore, the unique merits and ongoing challenges of data-driven constitutive models for granular materials are discussed.
Keywords: Deep learning; granular materials; constitutive modelling; discrete element modelling; coordinate transformation; LSTM; GRU
College: College of Engineering
Issue: 1
Start Page: 129
End Page: 144