No Cover Image

E-Thesis 445 views

The data-driven-based constitutive model and its application in machine learning-aided multiscale modelling for granular materials / MENGQI WANG

Swansea University Author: MENGQI WANG

  • E-Thesis under embargo until: 2nd May 2027

DOI (Published version): 10.23889/SUThesis.69879

Abstract

Data-driven methods have gained significant attention since Google’s AlphaGo defeated a world champion in 2017. Over the past several years, machine learning (ML), a subset of data-driven approaches, has increasingly attracted interest in the study of granular materials within civil engineering. Unli...

Full description

Published: Swansea University, Wales, UK 2025
Institution: Swansea University
Degree level: Doctoral
Degree name: Ph.D
Supervisor: Feng, Y. T.
URI: https://cronfa.swan.ac.uk/Record/cronfa69879
first_indexed 2025-07-03T11:38:06Z
last_indexed 2025-07-04T06:42:54Z
id cronfa69879
recordtype RisThesis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-07-03T12:42:09.6894225</datestamp><bib-version>v2</bib-version><id>69879</id><entry>2025-07-03</entry><title>The data-driven-based constitutive model and its application in machine learning-aided multiscale modelling for granular materials</title><swanseaauthors><author><sid>c8b7876c8a7f8a18edfa20b3aa0cb111</sid><firstname>MENGQI</firstname><surname>WANG</surname><name>MENGQI WANG</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-07-03</date><abstract>Data-driven methods have gained signi&#xFB01;cant attention since Google&#x2019;s AlphaGo defeated a world champion in 2017. Over the past several years, machine learning (ML), a subset of data-driven approaches, has increasingly attracted interest in the study of granular materials within civil engineering. Unlike traditional techniques, such as phenomenological models and numerical methods used to describe the deformation of granular media, the ML method offers several distinct advantages: 1) ML models can continuously adapt to new data, enhancing their accuracy and performance over time, thereby demonstrating strong adaptability; 2)ML techniques can directly uncovering hidden relationships and extracting insights from data without any assumption, making them particularly effective for predictive analytics;3) ML algorithms execute complex calculations at high speeds, signi&#xFB01;cantly reducing the time required for various tasks. These features of the ML methods make them a promising alternative to bypass the challenges inherent in traditional research methodologies, such as complex assumptions, limited adaptability, and high computational costs. This thesis aims to develop a data-driven multiscale modelling method incorporating an ML-based stress-strain model, capable of precisely capturing history-dependent constitutive behaviours for grain assembly, to accelerate the computational process of the traditional FEM-DEM approach in both 2D and 3D simulations. The whole work comprises the following three main chapters:1. Literature review for machine learning aided modelling of granular materials: The recent advances in ML-aided studies of granular materials are reviewed. Following the literature review work, the key challenges in developing a DEM data-driven FEM-ML framework are identi&#xFB01;ed and discussed.2. The temporal convolution neural network (TCNN)-based constitutive model: The potential of the TCNN-based constitutive model in capturing the mechanical behaviours of granular materials is comprehensively investigated and the applicability of time-sequence ML models in developing the FEM-ML framework is discussed3. The enhanced multi-layer perception (MLP)-based FEM-ML modelling algorithm: A DEM data-based FEM-ML framework is constructed with the enhanced MLP that integrates Frobenius norm-based internal variable. The data-driven multiscale algorithm signi&#xFB01;cantly improves the solving ef&#xFB01;ciency of the traditional FEM-DEM method in 2D BVPs for granular material.4. A physical information-integrated FEM-ML multiscale framework for 3D modelling of granular materials: Three internal variables with physical signi&#xFB01;cance are introduced to develop the MLP-based FEM-ML modelling method for 3D problems.The modelling results obtained by the FEM-ML method are comparable to those from the FEM-DEM approach but achieve signi&#xFB01;cant improvement in computational ef&#xFB01;ciency.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea University, Wales, UK</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Granular materials, Machine learning, Constitutive model, FEM, DEM, FEM-DEM multiscale method, FEM-ML method</keywords><publishedDay>2</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-05-02</publishedDate><doi>10.23889/SUThesis.69879</doi><url/><notes>A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information.</notes><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Feng, Y. T.</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><degreesponsorsfunders>CSC</degreesponsorsfunders><apcterm/><funders>CSC</funders><projectreference/><lastEdited>2025-07-03T12:42:09.6894225</lastEdited><Created>2025-07-03T12:29:20.5650620</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>MENGQI</firstname><surname>WANG</surname><order>1</order></author></authors><documents><document><filename>Under embargo</filename><originalFilename>Under embargo</originalFilename><uploaded>2025-07-03T12:36:58.8268378</uploaded><type>Output</type><contentLength>28138986</contentLength><contentType>application/pdf</contentType><version>E-Thesis</version><cronfaStatus>true</cronfaStatus><embargoDate>2027-05-02T00:00:00.0000000</embargoDate><documentNotes>Copyright: The author, Mengqi Wang, 2024</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2025-07-03T12:42:09.6894225 v2 69879 2025-07-03 The data-driven-based constitutive model and its application in machine learning-aided multiscale modelling for granular materials c8b7876c8a7f8a18edfa20b3aa0cb111 MENGQI WANG MENGQI WANG true false 2025-07-03 Data-driven methods have gained significant attention since Google’s AlphaGo defeated a world champion in 2017. Over the past several years, machine learning (ML), a subset of data-driven approaches, has increasingly attracted interest in the study of granular materials within civil engineering. Unlike traditional techniques, such as phenomenological models and numerical methods used to describe the deformation of granular media, the ML method offers several distinct advantages: 1) ML models can continuously adapt to new data, enhancing their accuracy and performance over time, thereby demonstrating strong adaptability; 2)ML techniques can directly uncovering hidden relationships and extracting insights from data without any assumption, making them particularly effective for predictive analytics;3) ML algorithms execute complex calculations at high speeds, significantly reducing the time required for various tasks. These features of the ML methods make them a promising alternative to bypass the challenges inherent in traditional research methodologies, such as complex assumptions, limited adaptability, and high computational costs. This thesis aims to develop a data-driven multiscale modelling method incorporating an ML-based stress-strain model, capable of precisely capturing history-dependent constitutive behaviours for grain assembly, to accelerate the computational process of the traditional FEM-DEM approach in both 2D and 3D simulations. The whole work comprises the following three main chapters:1. Literature review for machine learning aided modelling of granular materials: The recent advances in ML-aided studies of granular materials are reviewed. Following the literature review work, the key challenges in developing a DEM data-driven FEM-ML framework are identified and discussed.2. The temporal convolution neural network (TCNN)-based constitutive model: The potential of the TCNN-based constitutive model in capturing the mechanical behaviours of granular materials is comprehensively investigated and the applicability of time-sequence ML models in developing the FEM-ML framework is discussed3. The enhanced multi-layer perception (MLP)-based FEM-ML modelling algorithm: A DEM data-based FEM-ML framework is constructed with the enhanced MLP that integrates Frobenius norm-based internal variable. The data-driven multiscale algorithm significantly improves the solving efficiency of the traditional FEM-DEM method in 2D BVPs for granular material.4. A physical information-integrated FEM-ML multiscale framework for 3D modelling of granular materials: Three internal variables with physical significance are introduced to develop the MLP-based FEM-ML modelling method for 3D problems.The modelling results obtained by the FEM-ML method are comparable to those from the FEM-DEM approach but achieve significant improvement in computational efficiency. E-Thesis Swansea University, Wales, UK Granular materials, Machine learning, Constitutive model, FEM, DEM, FEM-DEM multiscale method, FEM-ML method 2 5 2025 2025-05-02 10.23889/SUThesis.69879 A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information. COLLEGE NANME COLLEGE CODE Swansea University Feng, Y. T. Doctoral Ph.D CSC CSC 2025-07-03T12:42:09.6894225 2025-07-03T12:29:20.5650620 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering MENGQI WANG 1 Under embargo Under embargo 2025-07-03T12:36:58.8268378 Output 28138986 application/pdf E-Thesis true 2027-05-02T00:00:00.0000000 Copyright: The author, Mengqi Wang, 2024 true eng
title The data-driven-based constitutive model and its application in machine learning-aided multiscale modelling for granular materials
spellingShingle The data-driven-based constitutive model and its application in machine learning-aided multiscale modelling for granular materials
MENGQI WANG
title_short The data-driven-based constitutive model and its application in machine learning-aided multiscale modelling for granular materials
title_full The data-driven-based constitutive model and its application in machine learning-aided multiscale modelling for granular materials
title_fullStr The data-driven-based constitutive model and its application in machine learning-aided multiscale modelling for granular materials
title_full_unstemmed The data-driven-based constitutive model and its application in machine learning-aided multiscale modelling for granular materials
title_sort The data-driven-based constitutive model and its application in machine learning-aided multiscale modelling for granular materials
author_id_str_mv c8b7876c8a7f8a18edfa20b3aa0cb111
author_id_fullname_str_mv c8b7876c8a7f8a18edfa20b3aa0cb111_***_MENGQI WANG
author MENGQI WANG
author2 MENGQI WANG
format E-Thesis
publishDate 2025
institution Swansea University
doi_str_mv 10.23889/SUThesis.69879
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
document_store_str 0
active_str 0
description Data-driven methods have gained significant attention since Google’s AlphaGo defeated a world champion in 2017. Over the past several years, machine learning (ML), a subset of data-driven approaches, has increasingly attracted interest in the study of granular materials within civil engineering. Unlike traditional techniques, such as phenomenological models and numerical methods used to describe the deformation of granular media, the ML method offers several distinct advantages: 1) ML models can continuously adapt to new data, enhancing their accuracy and performance over time, thereby demonstrating strong adaptability; 2)ML techniques can directly uncovering hidden relationships and extracting insights from data without any assumption, making them particularly effective for predictive analytics;3) ML algorithms execute complex calculations at high speeds, significantly reducing the time required for various tasks. These features of the ML methods make them a promising alternative to bypass the challenges inherent in traditional research methodologies, such as complex assumptions, limited adaptability, and high computational costs. This thesis aims to develop a data-driven multiscale modelling method incorporating an ML-based stress-strain model, capable of precisely capturing history-dependent constitutive behaviours for grain assembly, to accelerate the computational process of the traditional FEM-DEM approach in both 2D and 3D simulations. The whole work comprises the following three main chapters:1. Literature review for machine learning aided modelling of granular materials: The recent advances in ML-aided studies of granular materials are reviewed. Following the literature review work, the key challenges in developing a DEM data-driven FEM-ML framework are identified and discussed.2. The temporal convolution neural network (TCNN)-based constitutive model: The potential of the TCNN-based constitutive model in capturing the mechanical behaviours of granular materials is comprehensively investigated and the applicability of time-sequence ML models in developing the FEM-ML framework is discussed3. The enhanced multi-layer perception (MLP)-based FEM-ML modelling algorithm: A DEM data-based FEM-ML framework is constructed with the enhanced MLP that integrates Frobenius norm-based internal variable. The data-driven multiscale algorithm significantly improves the solving efficiency of the traditional FEM-DEM method in 2D BVPs for granular material.4. A physical information-integrated FEM-ML multiscale framework for 3D modelling of granular materials: Three internal variables with physical significance are introduced to develop the MLP-based FEM-ML modelling method for 3D problems.The modelling results obtained by the FEM-ML method are comparable to those from the FEM-DEM approach but achieve significant improvement in computational efficiency.
published_date 2025-05-02T05:29:21Z
_version_ 1851097938503139328
score 11.089386

Similar Items