No Cover Image

Journal article 21928 views

A machine learning-based multi-scale computational framework for granular materials

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

Acta Geotechnica, Volume: 18, Issue: 4, Pages: 1699 - 1720

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

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1007/s11440-022-01709-z

Abstract

With the development of experimental measurement technology and high-fidelity numerical simulations of granular materials, empirical-based classical constitutive models may not be able to take full advantage of the rapidly increasing available datasets. Machine learning-based models can inherently a...

Full description

Published in: Acta Geotechnica
ISSN: 1861-1125 1861-1133
Published: Springer Science and Business Media LLC 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa60725
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-08-03T16:20:05Z
last_indexed 2023-01-13T19:21:04Z
id cronfa60725
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>60725</id><entry>2022-08-03</entry><title>A machine learning-based multi-scale computational framework for granular materials</title><swanseaauthors><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>1a8144ef1058bc1310206808a4d274c3</sid><firstname>Tongming</firstname><surname>QU</surname><name>Tongming QU</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>2022-08-03</date><deptcode>FGSEN</deptcode><abstract>With the development of experimental measurement technology and high-fidelity numerical simulations of granular materials, empirical-based classical constitutive models may not be able to take full advantage of the rapidly increasing available datasets. Machine learning-based models can inherently avoid phenomenological assumptions to directly learn the constitutive relationship from the datasets, and the trained model is sufficiently flexible to be reconstructed once new training samples are added. In this work, a coupled finite element method and machine learning (FEM-ML) computational framework is proposed for simulating granular materials. Gaussian process-based random loading paths and coupled FEM-DEM simulations are used to generate training samples. A parametrisation of the material deformation history is used to represent the historical influence of granular materials. An uncertainty-level-based active learning is utilised to evaluate the informativeness of data points for network training and then to establish an effective resampling scheme from a massive dataset. Two examples are provided to show the applicability of the implemented FEM-ML framework. The performance of the proposed framework is also evaluated, the error is systematically analysed, and possible improvements are discussed. The results demonstrate that the FEM-ML framework offers considerable improvements in terms of computational efficiency and competence to simulate the mechanical responses of granular materials.</abstract><type>Journal Article</type><journal>Acta Geotechnica</journal><volume>18</volume><journalNumber>4</journalNumber><paginationStart>1699</paginationStart><paginationEnd>1720</paginationEnd><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1861-1125</issnPrint><issnElectronic>1861-1133</issnElectronic><keywords>DEM; FEM; Granular materials; Machine learning; Multi-scale</keywords><publishedDay>30</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-04-30</publishedDate><doi>10.1007/s11440-022-01709-z</doi><url>http://dx.doi.org/10.1007/s11440-022-01709-z</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/><projectreference/><lastEdited>2023-09-04T18:19:02.0534331</lastEdited><Created>2022-08-03T17:16:18.1008578</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>Shaoheng Guan</firstname><surname>Guan</surname><order>1</order></author><author><firstname>Tongming</firstname><surname>QU</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><orcid>0000-0002-1865-5721</orcid><order>4</order></author><author><firstname>Wei</firstname><surname>Zhou</surname><order>5</order></author></authors><documents><document><filename>Under embargo</filename><originalFilename>Under embargo</originalFilename><uploaded>2022-08-03T17:19:37.7345175</uploaded><type>Output</type><contentLength>2474479</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2023-10-15T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling v2 60725 2022-08-03 A machine learning-based multi-scale computational framework for granular materials 8be5dace79e94a4d0abd32215a13f806 Shaoheng Guan Guan Shaoheng Guan Guan true false 1a8144ef1058bc1310206808a4d274c3 Tongming QU Tongming QU true false d66794f9c1357969a5badf654f960275 0000-0002-6396-8698 Yuntian Feng Yuntian Feng true false 2022-08-03 FGSEN With the development of experimental measurement technology and high-fidelity numerical simulations of granular materials, empirical-based classical constitutive models may not be able to take full advantage of the rapidly increasing available datasets. Machine learning-based models can inherently avoid phenomenological assumptions to directly learn the constitutive relationship from the datasets, and the trained model is sufficiently flexible to be reconstructed once new training samples are added. In this work, a coupled finite element method and machine learning (FEM-ML) computational framework is proposed for simulating granular materials. Gaussian process-based random loading paths and coupled FEM-DEM simulations are used to generate training samples. A parametrisation of the material deformation history is used to represent the historical influence of granular materials. An uncertainty-level-based active learning is utilised to evaluate the informativeness of data points for network training and then to establish an effective resampling scheme from a massive dataset. Two examples are provided to show the applicability of the implemented FEM-ML framework. The performance of the proposed framework is also evaluated, the error is systematically analysed, and possible improvements are discussed. The results demonstrate that the FEM-ML framework offers considerable improvements in terms of computational efficiency and competence to simulate the mechanical responses of granular materials. Journal Article Acta Geotechnica 18 4 1699 1720 Springer Science and Business Media LLC 1861-1125 1861-1133 DEM; FEM; Granular materials; Machine learning; Multi-scale 30 4 2023 2023-04-30 10.1007/s11440-022-01709-z http://dx.doi.org/10.1007/s11440-022-01709-z COLLEGE NANME Science and Engineering - Faculty COLLEGE CODE FGSEN Swansea University 2023-09-04T18:19:02.0534331 2022-08-03T17:16:18.1008578 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Shaoheng Guan Guan 1 Tongming QU 2 Yuntian Feng 0000-0002-6396-8698 3 Gang Ma 0000-0002-1865-5721 4 Wei Zhou 5 Under embargo Under embargo 2022-08-03T17:19:37.7345175 Output 2474479 application/pdf Accepted Manuscript true 2023-10-15T00:00:00.0000000 true eng
title A machine learning-based multi-scale computational framework for granular materials
spellingShingle A machine learning-based multi-scale computational framework for granular materials
Shaoheng Guan Guan
Tongming QU
Yuntian Feng
title_short A machine learning-based multi-scale computational framework for granular materials
title_full A machine learning-based multi-scale computational framework for granular materials
title_fullStr A machine learning-based multi-scale computational framework for granular materials
title_full_unstemmed A machine learning-based multi-scale computational framework for granular materials
title_sort A machine learning-based multi-scale computational framework for granular materials
author_id_str_mv 8be5dace79e94a4d0abd32215a13f806
1a8144ef1058bc1310206808a4d274c3
d66794f9c1357969a5badf654f960275
author_id_fullname_str_mv 8be5dace79e94a4d0abd32215a13f806_***_Shaoheng Guan Guan
1a8144ef1058bc1310206808a4d274c3_***_Tongming QU
d66794f9c1357969a5badf654f960275_***_Yuntian Feng
author Shaoheng Guan Guan
Tongming QU
Yuntian Feng
author2 Shaoheng Guan Guan
Tongming QU
Yuntian Feng
Gang Ma
Wei Zhou
format Journal article
container_title Acta Geotechnica
container_volume 18
container_issue 4
container_start_page 1699
publishDate 2023
institution Swansea University
issn 1861-1125
1861-1133
doi_str_mv 10.1007/s11440-022-01709-z
publisher Springer Science and Business Media LLC
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/10.1007/s11440-022-01709-z
document_store_str 0
active_str 0
description With the development of experimental measurement technology and high-fidelity numerical simulations of granular materials, empirical-based classical constitutive models may not be able to take full advantage of the rapidly increasing available datasets. Machine learning-based models can inherently avoid phenomenological assumptions to directly learn the constitutive relationship from the datasets, and the trained model is sufficiently flexible to be reconstructed once new training samples are added. In this work, a coupled finite element method and machine learning (FEM-ML) computational framework is proposed for simulating granular materials. Gaussian process-based random loading paths and coupled FEM-DEM simulations are used to generate training samples. A parametrisation of the material deformation history is used to represent the historical influence of granular materials. An uncertainty-level-based active learning is utilised to evaluate the informativeness of data points for network training and then to establish an effective resampling scheme from a massive dataset. Two examples are provided to show the applicability of the implemented FEM-ML framework. The performance of the proposed framework is also evaluated, the error is systematically analysed, and possible improvements are discussed. The results demonstrate that the FEM-ML framework offers considerable improvements in terms of computational efficiency and competence to simulate the mechanical responses of granular materials.
published_date 2023-04-30T18:19:03Z
_version_ 1776128301510688768
score 10.999616

Similar Items