No Cover Image

Journal article 740 views

A data-driven approach to predicting the anisotropic mechanical behaviour of voided single crystals

He-Jie Guo, Chao Ling Orcid Logo, Dong-Feng Li, Chenfeng Li Orcid Logo, Yi Sun, Esteban P. Busso Orcid Logo

Journal of the Mechanics and Physics of Solids, Volume: 159, Start page: 104700

Swansea University Author: Chenfeng Li Orcid Logo

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

Check full text

DOI (Published version): 10.1016/j.jmps.2021.104700

Abstract

Machine learning techniques are increasingly used to extract important physical information from a broad range of materials and to identify their processing-structure–property relationships. In this work, a neural network framework is coupled with a crystal plasticity finite element based approach t...

Full description

Published in: Journal of the Mechanics and Physics of Solids
ISSN: 0022-5096
Published: Elsevier BV 2022
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa60464
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-07-13T10:50:23Z
last_indexed 2023-01-13T19:20:36Z
id cronfa60464
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-10-31T20:22:19.5961899</datestamp><bib-version>v2</bib-version><id>60464</id><entry>2022-07-12</entry><title>A data-driven approach to predicting the anisotropic mechanical behaviour of voided single crystals</title><swanseaauthors><author><sid>82fe170d5ae2c840e538a36209e5a3ac</sid><ORCID>0000-0003-0441-211X</ORCID><firstname>Chenfeng</firstname><surname>Li</surname><name>Chenfeng Li</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-07-12</date><deptcode>CIVL</deptcode><abstract>Machine learning techniques are increasingly used to extract important physical information from a broad range of materials and to identify their processing-structure&#x2013;property relationships. In this work, a neural network framework is coupled with a crystal plasticity finite element based approach to predict the deformation and ductile failure behaviour of porous FCC single crystals when subjected to multi-axial loading conditions. The work relies on 3D unit cells with a centrally located spherical void to represent the microstructure of the porous single crystal material, and on a crystallographic slip-based crystal plasticity constitutive model to describe its deformation behaviour. Stress&#x2013;strain data generated by unit cell finite element simulations are relied upon to construct the neural network model. Different strategies for the neural network input and output variables and parameters are first explored so as to optimise performance and accuracy. Both proportional and non-proportional loading conditions resulting from a constant and a varying stress triaxiality during deformation, respectively, are considered.The optimum neural network strategy is shown to successfully predict the behaviour of the porous single crystal under both proportional and non-proportional loading, albeit with the void behaviour at high stress triaxialities better described than that at low triaxialities. The results also reveal that the use of tensorial quantities for both stresses and strains as input and output neural network quantities is more suitable as a form of data representation for multiaxial loading conditions than uniaxial equivalent stress and strain quantities. It was also found that the inclusion of prior knowledge as neural network input quantities in the form of reference stress&#x2013;strain solutions for the void-free single crystal considerably improves the predictive capabilities of the proposed data-driven approach, even when only a very limited number of training cases was used.</abstract><type>Journal Article</type><journal>Journal of the Mechanics and Physics of Solids</journal><volume>159</volume><journalNumber/><paginationStart>104700</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0022-5096</issnPrint><issnElectronic/><keywords>Single crystal, Triaxiality, Ductile fracture, Crystallographic slip, Voids, Neural networks</keywords><publishedDay>1</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-02-01</publishedDate><doi>10.1016/j.jmps.2021.104700</doi><url/><notes/><college>COLLEGE NANME</college><department>Civil Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CIVL</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This publication has emanated from research conducted with the financial support of National Natural Science Foundation of China under grant numbers 11872161, 12002105 and 12011530157 and the Guangdong Basic and Applied Basic Research Foundation under grant numbers 2019A1515110758. Financial support provided by Shenzhen Science and Technology Program (Grant No. KQTD20200820113045083) is also acknowledged.</funders><projectreference/><lastEdited>2022-10-31T20:22:19.5961899</lastEdited><Created>2022-07-12T17:10:46.3533338</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>He-Jie</firstname><surname>Guo</surname><order>1</order></author><author><firstname>Chao</firstname><surname>Ling</surname><orcid>0000-0003-3967-5956</orcid><order>2</order></author><author><firstname>Dong-Feng</firstname><surname>Li</surname><order>3</order></author><author><firstname>Chenfeng</firstname><surname>Li</surname><orcid>0000-0003-0441-211X</orcid><order>4</order></author><author><firstname>Yi</firstname><surname>Sun</surname><order>5</order></author><author><firstname>Esteban P.</firstname><surname>Busso</surname><orcid>0000-0002-9670-7064</orcid><order>6</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2022-10-31T20:22:19.5961899 v2 60464 2022-07-12 A data-driven approach to predicting the anisotropic mechanical behaviour of voided single crystals 82fe170d5ae2c840e538a36209e5a3ac 0000-0003-0441-211X Chenfeng Li Chenfeng Li true false 2022-07-12 CIVL Machine learning techniques are increasingly used to extract important physical information from a broad range of materials and to identify their processing-structure–property relationships. In this work, a neural network framework is coupled with a crystal plasticity finite element based approach to predict the deformation and ductile failure behaviour of porous FCC single crystals when subjected to multi-axial loading conditions. The work relies on 3D unit cells with a centrally located spherical void to represent the microstructure of the porous single crystal material, and on a crystallographic slip-based crystal plasticity constitutive model to describe its deformation behaviour. Stress–strain data generated by unit cell finite element simulations are relied upon to construct the neural network model. Different strategies for the neural network input and output variables and parameters are first explored so as to optimise performance and accuracy. Both proportional and non-proportional loading conditions resulting from a constant and a varying stress triaxiality during deformation, respectively, are considered.The optimum neural network strategy is shown to successfully predict the behaviour of the porous single crystal under both proportional and non-proportional loading, albeit with the void behaviour at high stress triaxialities better described than that at low triaxialities. The results also reveal that the use of tensorial quantities for both stresses and strains as input and output neural network quantities is more suitable as a form of data representation for multiaxial loading conditions than uniaxial equivalent stress and strain quantities. It was also found that the inclusion of prior knowledge as neural network input quantities in the form of reference stress–strain solutions for the void-free single crystal considerably improves the predictive capabilities of the proposed data-driven approach, even when only a very limited number of training cases was used. Journal Article Journal of the Mechanics and Physics of Solids 159 104700 Elsevier BV 0022-5096 Single crystal, Triaxiality, Ductile fracture, Crystallographic slip, Voids, Neural networks 1 2 2022 2022-02-01 10.1016/j.jmps.2021.104700 COLLEGE NANME Civil Engineering COLLEGE CODE CIVL Swansea University This publication has emanated from research conducted with the financial support of National Natural Science Foundation of China under grant numbers 11872161, 12002105 and 12011530157 and the Guangdong Basic and Applied Basic Research Foundation under grant numbers 2019A1515110758. Financial support provided by Shenzhen Science and Technology Program (Grant No. KQTD20200820113045083) is also acknowledged. 2022-10-31T20:22:19.5961899 2022-07-12T17:10:46.3533338 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering He-Jie Guo 1 Chao Ling 0000-0003-3967-5956 2 Dong-Feng Li 3 Chenfeng Li 0000-0003-0441-211X 4 Yi Sun 5 Esteban P. Busso 0000-0002-9670-7064 6
title A data-driven approach to predicting the anisotropic mechanical behaviour of voided single crystals
spellingShingle A data-driven approach to predicting the anisotropic mechanical behaviour of voided single crystals
Chenfeng Li
title_short A data-driven approach to predicting the anisotropic mechanical behaviour of voided single crystals
title_full A data-driven approach to predicting the anisotropic mechanical behaviour of voided single crystals
title_fullStr A data-driven approach to predicting the anisotropic mechanical behaviour of voided single crystals
title_full_unstemmed A data-driven approach to predicting the anisotropic mechanical behaviour of voided single crystals
title_sort A data-driven approach to predicting the anisotropic mechanical behaviour of voided single crystals
author_id_str_mv 82fe170d5ae2c840e538a36209e5a3ac
author_id_fullname_str_mv 82fe170d5ae2c840e538a36209e5a3ac_***_Chenfeng Li
author Chenfeng Li
author2 He-Jie Guo
Chao Ling
Dong-Feng Li
Chenfeng Li
Yi Sun
Esteban P. Busso
format Journal article
container_title Journal of the Mechanics and Physics of Solids
container_volume 159
container_start_page 104700
publishDate 2022
institution Swansea University
issn 0022-5096
doi_str_mv 10.1016/j.jmps.2021.104700
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
document_store_str 0
active_str 0
description Machine learning techniques are increasingly used to extract important physical information from a broad range of materials and to identify their processing-structure–property relationships. In this work, a neural network framework is coupled with a crystal plasticity finite element based approach to predict the deformation and ductile failure behaviour of porous FCC single crystals when subjected to multi-axial loading conditions. The work relies on 3D unit cells with a centrally located spherical void to represent the microstructure of the porous single crystal material, and on a crystallographic slip-based crystal plasticity constitutive model to describe its deformation behaviour. Stress–strain data generated by unit cell finite element simulations are relied upon to construct the neural network model. Different strategies for the neural network input and output variables and parameters are first explored so as to optimise performance and accuracy. Both proportional and non-proportional loading conditions resulting from a constant and a varying stress triaxiality during deformation, respectively, are considered.The optimum neural network strategy is shown to successfully predict the behaviour of the porous single crystal under both proportional and non-proportional loading, albeit with the void behaviour at high stress triaxialities better described than that at low triaxialities. The results also reveal that the use of tensorial quantities for both stresses and strains as input and output neural network quantities is more suitable as a form of data representation for multiaxial loading conditions than uniaxial equivalent stress and strain quantities. It was also found that the inclusion of prior knowledge as neural network input quantities in the form of reference stress–strain solutions for the void-free single crystal considerably improves the predictive capabilities of the proposed data-driven approach, even when only a very limited number of training cases was used.
published_date 2022-02-01T04:18:36Z
_version_ 1763754236763439104
score 11.035634

Similar Items