No Cover Image

Journal article 427 views 137 downloads

Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling

Tongming QU, Shaoheng Guan Guan, Yuntian Feng Orcid Logo, Gang Ma, Wei Zhou, Jidong Zhao

International Journal of Plasticity, Volume: 164, Start page: 103576

Swansea University Authors: Tongming QU, Shaoheng Guan Guan, Yuntian Feng Orcid Logo

  • 62759.pdf

    PDF | Version of Record

    © 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

    Download (12MB)

Check full text

DOI (Published version): 10.1016/j.ijplas.2023.103576

Abstract

Constitutive relation remains one of the most important, yet fundamental challenges in the study of granular materials. Instead of using closed-form phenomenological models or numerical multiscale modelling, machine learning has emerged as an alternative paradigm to revolutionise the constitutive mo...

Full description

Published in: International Journal of Plasticity
ISSN: 0749-6419 1879-2154
Published: Elsevier BV 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa62759
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-02-27T13:26:22Z
last_indexed 2023-03-24T04:22:54Z
id cronfa62759
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>62759</id><entry>2023-02-27</entry><title>Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling</title><swanseaauthors><author><sid>1a8144ef1058bc1310206808a4d274c3</sid><firstname>Tongming</firstname><surname>QU</surname><name>Tongming QU</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>8be5dace79e94a4d0abd32215a13f806</sid><firstname>Shaoheng Guan</firstname><surname>Guan</surname><name>Shaoheng Guan Guan</name><active>true</active><ethesisStudent>false</ethesisStudent></author><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></swanseaauthors><date>2023-02-27</date><deptcode>FGSEN</deptcode><abstract>Constitutive relation remains one of the most important, yet fundamental challenges in the study of granular materials. Instead of using closed-form phenomenological models or numerical multiscale modelling, machine learning has emerged as an alternative paradigm to revolutionise the constitutive modelling of granular materials. However, deep neural networks (DNNs) require massive training data and often fail to make credible extrapolations. This study aims to develop a deep active learning strategy to (i) identify unreliable forecasts without knowing the ground truth; and (ii) continuously improve and verify a data-driven constitutive model until the desired generalisation is satisfied. The role of active learning in constitutive modelling is instantiated through three scenarios: (i) off-line strain-stress data pool of granular materials; (ii) interactive constitutive training and strain-stress data labelling; and (iii) finite element modelling (FEM) driven by deep learning-based constitutive models. The results confirm the capability of active learning in advancing data-driven constitutive modelling of granular materials toward developing a faithful surrogate constitutive model with less data. The same active learning strategy can also be applied to other data-centric applications across various science and engineering fields.</abstract><type>Journal Article</type><journal>International Journal of Plasticity</journal><volume>164</volume><journalNumber/><paginationStart>103576</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0749-6419</issnPrint><issnElectronic>1879-2154</issnElectronic><keywords>Granular materials; Machine learning; Constitutive models; Active learning; Discrete element model; Finite element model</keywords><publishedDay>1</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-05-01</publishedDate><doi>10.1016/j.ijplas.2023.103576</doi><url>http://dx.doi.org/10.1016/j.ijplas.2023.103576</url><notes/><college>COLLEGE NANME</college><department>Science and Engineering - Faculty</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>FGSEN</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>The study was financially supported by National Natural Science Foundation of China (via General Project #11972030) and Research Grants Council of Hong Kong (under GRF #16208720).</funders><projectreference/><lastEdited>2023-06-01T16:24:39.0496424</lastEdited><Created>2023-02-27T13:22:03.5318505</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>Shaoheng Guan</firstname><surname>Guan</surname><order>2</order></author><author><firstname>Yuntian</firstname><surname>Feng</surname><orcid>0000-0002-6396-8698</orcid><order>3</order></author><author><firstname>Gang</firstname><surname>Ma</surname><order>4</order></author><author><firstname>Wei</firstname><surname>Zhou</surname><order>5</order></author><author><firstname>Jidong</firstname><surname>Zhao</surname><order>6</order></author></authors><documents><document><filename>62759__26899__8c8071f8dd4c495ea444920678566677.pdf</filename><originalFilename>62759.pdf</originalFilename><uploaded>2023-03-20T10:21:53.4581055</uploaded><type>Output</type><contentLength>12578670</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 62759 2023-02-27 Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling 1a8144ef1058bc1310206808a4d274c3 Tongming QU Tongming QU true false 8be5dace79e94a4d0abd32215a13f806 Shaoheng Guan Guan Shaoheng Guan Guan true false d66794f9c1357969a5badf654f960275 0000-0002-6396-8698 Yuntian Feng Yuntian Feng true false 2023-02-27 FGSEN Constitutive relation remains one of the most important, yet fundamental challenges in the study of granular materials. Instead of using closed-form phenomenological models or numerical multiscale modelling, machine learning has emerged as an alternative paradigm to revolutionise the constitutive modelling of granular materials. However, deep neural networks (DNNs) require massive training data and often fail to make credible extrapolations. This study aims to develop a deep active learning strategy to (i) identify unreliable forecasts without knowing the ground truth; and (ii) continuously improve and verify a data-driven constitutive model until the desired generalisation is satisfied. The role of active learning in constitutive modelling is instantiated through three scenarios: (i) off-line strain-stress data pool of granular materials; (ii) interactive constitutive training and strain-stress data labelling; and (iii) finite element modelling (FEM) driven by deep learning-based constitutive models. The results confirm the capability of active learning in advancing data-driven constitutive modelling of granular materials toward developing a faithful surrogate constitutive model with less data. The same active learning strategy can also be applied to other data-centric applications across various science and engineering fields. Journal Article International Journal of Plasticity 164 103576 Elsevier BV 0749-6419 1879-2154 Granular materials; Machine learning; Constitutive models; Active learning; Discrete element model; Finite element model 1 5 2023 2023-05-01 10.1016/j.ijplas.2023.103576 http://dx.doi.org/10.1016/j.ijplas.2023.103576 COLLEGE NANME Science and Engineering - Faculty COLLEGE CODE FGSEN Swansea University The study was financially supported by National Natural Science Foundation of China (via General Project #11972030) and Research Grants Council of Hong Kong (under GRF #16208720). 2023-06-01T16:24:39.0496424 2023-02-27T13:22:03.5318505 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Tongming QU 1 Shaoheng Guan Guan 2 Yuntian Feng 0000-0002-6396-8698 3 Gang Ma 4 Wei Zhou 5 Jidong Zhao 6 62759__26899__8c8071f8dd4c495ea444920678566677.pdf 62759.pdf 2023-03-20T10:21:53.4581055 Output 12578670 application/pdf Version of Record true © 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling
spellingShingle Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling
Tongming QU
Shaoheng Guan Guan
Yuntian Feng
title_short Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling
title_full Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling
title_fullStr Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling
title_full_unstemmed Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling
title_sort Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling
author_id_str_mv 1a8144ef1058bc1310206808a4d274c3
8be5dace79e94a4d0abd32215a13f806
d66794f9c1357969a5badf654f960275
author_id_fullname_str_mv 1a8144ef1058bc1310206808a4d274c3_***_Tongming QU
8be5dace79e94a4d0abd32215a13f806_***_Shaoheng Guan Guan
d66794f9c1357969a5badf654f960275_***_Yuntian Feng
author Tongming QU
Shaoheng Guan Guan
Yuntian Feng
author2 Tongming QU
Shaoheng Guan Guan
Yuntian Feng
Gang Ma
Wei Zhou
Jidong Zhao
format Journal article
container_title International Journal of Plasticity
container_volume 164
container_start_page 103576
publishDate 2023
institution Swansea University
issn 0749-6419
1879-2154
doi_str_mv 10.1016/j.ijplas.2023.103576
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.2023.103576
document_store_str 1
active_str 0
description Constitutive relation remains one of the most important, yet fundamental challenges in the study of granular materials. Instead of using closed-form phenomenological models or numerical multiscale modelling, machine learning has emerged as an alternative paradigm to revolutionise the constitutive modelling of granular materials. However, deep neural networks (DNNs) require massive training data and often fail to make credible extrapolations. This study aims to develop a deep active learning strategy to (i) identify unreliable forecasts without knowing the ground truth; and (ii) continuously improve and verify a data-driven constitutive model until the desired generalisation is satisfied. The role of active learning in constitutive modelling is instantiated through three scenarios: (i) off-line strain-stress data pool of granular materials; (ii) interactive constitutive training and strain-stress data labelling; and (iii) finite element modelling (FEM) driven by deep learning-based constitutive models. The results confirm the capability of active learning in advancing data-driven constitutive modelling of granular materials toward developing a faithful surrogate constitutive model with less data. The same active learning strategy can also be applied to other data-centric applications across various science and engineering fields.
published_date 2023-05-01T16:24:37Z
_version_ 1767514390224961536
score 11.013148

Similar Items