Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning

Qu, Tongming; Di, Shaocheng; Feng, Yuntian; Wang, Min; Zhao, Tingting; QU, Tongming

doi:10.1016/j.ijplas.2021.103046

Journal article 846 views 153 downloads

Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning

Tongming Qu, Shaocheng Di, Yuntian Feng

, Min Wang, Tingting Zhao, Tongming QU

International Journal of Plasticity, Volume: 144, Start page: 103046

Swansea University Authors: Yuntian Feng , Tongming QU

PDF | Accepted Manuscript

©2021 All rights reserved. All article content, except where otherwise noted, is licensed under a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND)
Download (1.32MB)

Check full text

DOI (Published version): 10.1016/j.ijplas.2021.103046

Abstract

The analytical description of path-dependent elastic-plastic responses of a granular system is highly complicated because of continuously evolving microstructures and strain localisation within the system undergoing deformation. This study offers an alternative to the current analytical paradigm by...

Full description

Published in:	International Journal of Plasticity
ISSN:	0749-6419
Published:	Elsevier BV 2021
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa57046
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2021-06-08T08:16:26Z
last_indexed	2021-08-22T03:19:43Z
id	cronfa57046
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2021-08-21T14:53:26.6716463</datestamp><bib-version>v2</bib-version><id>57046</id><entry>2021-06-08</entry><title>Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning</title><swanseaauthors><author><sid>d66794f9c1357969a5badf654f960275</sid><ORCID>0000-0002-6396-8698</ORCID><firstname>Yuntian</firstname><surname>Feng</surname><name>Yuntian Feng</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>1a8144ef1058bc1310206808a4d274c3</sid><firstname>Tongming</firstname><surname>QU</surname><name>Tongming QU</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-06-08</date><deptcode>CIVL</deptcode><abstract>The analytical description of path-dependent elastic-plastic responses of a granular system is highly complicated because of continuously evolving microstructures and strain localisation within the system undergoing deformation. This study offers an alternative to the current analytical paradigm by developing micromechanics-informed machine-learning based constitutive modelling approaches for granular materials. A set of critical variables associated with the constitutive behaviour of granular materials are identified through an incremental stress-strain relationship analysis. Depending on the strategy to exploit the priori micromechanical knowledge, three different training strategies are explored. The first model uses only the measurable external variables to make stress predictions; the second model utilises a directed graph to link all the external strain sequences and internal microstructural evolution variables into a single prediction model comprised of a series of sub-mappings, and the third model explicitly integrates the physically important non-temporal properties with external strain paths into training through an enhanced Gated Recurrent Unit (GRU). These three models show satisfactory agreement with unseen test specimens based on multi-directional loading cases. The features and applications of each model are explained. Furthermore, the key factors for constitutive training, potential applications and deficiencies of the current work are also discussed in detail.</abstract><type>Journal Article</type><journal>International Journal of Plasticity</journal><volume>144</volume><journalNumber/><paginationStart>103046</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0749-6419</issnPrint><issnElectronic/><keywords>Deep learning, Data-drive, nElastic-plastic constitutive model, Gated Recurrent Unit (GRU), Granular materials, Micromechanics, Discrete element modelling</keywords><publishedDay>1</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-09-01</publishedDate><doi>10.1016/j.ijplas.2021.103046</doi><url>http://dx.doi.org/10.1016/j.ijplas.2021.103046</url><notes/><college>COLLEGE NANME</college><department>Civil Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CIVL</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2021-08-21T14:53:26.6716463</lastEdited><Created>2021-06-08T09:13:15.3920446</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering</level></path><authors><author><firstname>Tongming</firstname><surname>Qu</surname><order>1</order></author><author><firstname>Shaocheng</firstname><surname>Di</surname><order>2</order></author><author><firstname>Yuntian</firstname><surname>Feng</surname><orcid>0000-0002-6396-8698</orcid><order>3</order></author><author><firstname>Min</firstname><surname>Wang</surname><order>4</order></author><author><firstname>Tingting</firstname><surname>Zhao</surname><order>5</order></author><author><firstname>Tongming</firstname><surname>QU</surname><order>6</order></author></authors><documents><document><filename>57046__20072__cdfd47c71a3846b2af8a979637c99ff4.pdf</filename><originalFilename>57046.pdf</originalFilename><uploaded>2021-06-08T09:15:49.7342148</uploaded><type>Output</type><contentLength>1379825</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2022-06-15T00:00:00.0000000</embargoDate><documentNotes>©2021 All rights reserved. All article content, except where otherwise noted, is licensed under a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND)</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2021-08-21T14:53:26.6716463 v2 57046 2021-06-08 Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning d66794f9c1357969a5badf654f960275 0000-0002-6396-8698 Yuntian Feng Yuntian Feng true false 1a8144ef1058bc1310206808a4d274c3 Tongming QU Tongming QU true false 2021-06-08 CIVL The analytical description of path-dependent elastic-plastic responses of a granular system is highly complicated because of continuously evolving microstructures and strain localisation within the system undergoing deformation. This study offers an alternative to the current analytical paradigm by developing micromechanics-informed machine-learning based constitutive modelling approaches for granular materials. A set of critical variables associated with the constitutive behaviour of granular materials are identified through an incremental stress-strain relationship analysis. Depending on the strategy to exploit the priori micromechanical knowledge, three different training strategies are explored. The first model uses only the measurable external variables to make stress predictions; the second model utilises a directed graph to link all the external strain sequences and internal microstructural evolution variables into a single prediction model comprised of a series of sub-mappings, and the third model explicitly integrates the physically important non-temporal properties with external strain paths into training through an enhanced Gated Recurrent Unit (GRU). These three models show satisfactory agreement with unseen test specimens based on multi-directional loading cases. The features and applications of each model are explained. Furthermore, the key factors for constitutive training, potential applications and deficiencies of the current work are also discussed in detail. Journal Article International Journal of Plasticity 144 103046 Elsevier BV 0749-6419 Deep learning, Data-drive, nElastic-plastic constitutive model, Gated Recurrent Unit (GRU), Granular materials, Micromechanics, Discrete element modelling 1 9 2021 2021-09-01 10.1016/j.ijplas.2021.103046 http://dx.doi.org/10.1016/j.ijplas.2021.103046 COLLEGE NANME Civil Engineering COLLEGE CODE CIVL Swansea University 2021-08-21T14:53:26.6716463 2021-06-08T09:13:15.3920446 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Tongming Qu 1 Shaocheng Di 2 Yuntian Feng 0000-0002-6396-8698 3 Min Wang 4 Tingting Zhao 5 Tongming QU 6 57046__20072__cdfd47c71a3846b2af8a979637c99ff4.pdf 57046.pdf 2021-06-08T09:15:49.7342148 Output 1379825 application/pdf Accepted Manuscript true 2022-06-15T00:00:00.0000000 ©2021 All rights reserved. All article content, except where otherwise noted, is licensed under a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND) true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title	Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning
spellingShingle	Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning Yuntian Feng Tongming QU
title_short	Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning
title_full	Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning
title_fullStr	Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning
title_full_unstemmed	Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning
title_sort	Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning
author_id_str_mv	d66794f9c1357969a5badf654f960275 1a8144ef1058bc1310206808a4d274c3
author_id_fullname_str_mv	d66794f9c1357969a5badf654f960275_*_Yuntian Feng 1a8144ef1058bc1310206808a4d274c3_*_Tongming QU
author	Yuntian Feng Tongming QU
author2	Tongming Qu Shaocheng Di Yuntian Feng Min Wang Tingting Zhao Tongming QU
format	Journal article
container_title	International Journal of Plasticity
container_volume	144
container_start_page	103046
publishDate	2021
institution	Swansea University
issn	0749-6419
doi_str_mv	10.1016/j.ijplas.2021.103046
publisher	Elsevier BV
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering
url	http://dx.doi.org/10.1016/j.ijplas.2021.103046
document_store_str	1
active_str	0
description	The analytical description of path-dependent elastic-plastic responses of a granular system is highly complicated because of continuously evolving microstructures and strain localisation within the system undergoing deformation. This study offers an alternative to the current analytical paradigm by developing micromechanics-informed machine-learning based constitutive modelling approaches for granular materials. A set of critical variables associated with the constitutive behaviour of granular materials are identified through an incremental stress-strain relationship analysis. Depending on the strategy to exploit the priori micromechanical knowledge, three different training strategies are explored. The first model uses only the measurable external variables to make stress predictions; the second model utilises a directed graph to link all the external strain sequences and internal microstructural evolution variables into a single prediction model comprised of a series of sub-mappings, and the third model explicitly integrates the physically important non-temporal properties with external strain paths into training through an enhanced Gated Recurrent Unit (GRU). These three models show satisfactory agreement with unseen test specimens based on multi-directional loading cases. The features and applications of each model are explained. Furthermore, the key factors for constitutive training, potential applications and deficiencies of the current work are also discussed in detail.
published_date	2021-09-01T04:12:29Z
_version_	1763753852027273216
score	11.013148

Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning

Similar Items