No Cover Image

Journal article 21895 views 404 downloads

Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network

Jinlong Fu, Shaoqing Cui, Song Cen, Chenfeng Li Orcid Logo

Computer Methods in Applied Mechanics and Engineering, Volume: 373, Start page: 113516

Swansea University Authors: Shaoqing Cui, Chenfeng Li Orcid Logo

  • 55670.pdf

    PDF | Accepted Manuscript

    © 2020. This manuscript version is made available under the CC-BY-NC-ND 4.0 license

    Download (40.98MB)

Check full text

DOI (Published version): 10.1016/j.cma.2020.113516

Abstract

Heterogeneous materials, whether natural or artificial, are usually composed of distinct constituents present in complex microstructures with discontinuous, irregular and hierarchical characteristics. For many heterogeneous materials, such as porous media and composites, the microstructural features...

Full description

Published in: Computer Methods in Applied Mechanics and Engineering
ISSN: 0045-7825
Published: Elsevier BV 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa55670
first_indexed 2020-11-16T15:11:29Z
last_indexed 2021-12-03T04:14:49Z
id cronfa55670
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-12-02T11:17:44.2779703</datestamp><bib-version>v2</bib-version><id>55670</id><entry>2020-11-16</entry><title>Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network</title><swanseaauthors><author><sid>88a9a34dc92416ac83ea8ff485d06ade</sid><ORCID/><firstname>Shaoqing</firstname><surname>Cui</surname><name>Shaoqing Cui</name><active>true</active><ethesisStudent>false</ethesisStudent></author><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>2020-11-16</date><abstract>Heterogeneous materials, whether natural or artificial, are usually composed of distinct constituents present in complex microstructures with discontinuous, irregular and hierarchical characteristics. For many heterogeneous materials, such as porous media and composites, the microstructural features are of fundamental importance for their macroscopic properties. This paper presents a novel method to statistically characterize and reconstruct random microstructures through a deep neural network (DNN) model, which can be used to study the microstructure&#x2013;property relationships. In our method, the digital microstructure image is assumed to be a stationary Markov random field (MRF), and local patterns covering the basic morphological features are collected to train a DNN model, after which statistically equivalent samples can be generated through a DNN-guided reconstruction procedure. Furthermore, to overcome the short-distance limitation associated with the MRF assumption, a multi-level approach is developed to preserve the long-distance morphological features of heterogeneous microstructures. A large number of tests have been conducted to compare the reconstructed and target microstructures in both morphological characteristics and physical properties, and good agreements are observed in all test cases. The proposed method is efficient, accurate, versatile, and especially beneficial to the statistical reconstruction of 2D/3D microstructures with long-distance correlations.</abstract><type>Journal Article</type><journal>Computer Methods in Applied Mechanics and Engineering</journal><volume>373</volume><journalNumber/><paginationStart>113516</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0045-7825</issnPrint><issnElectronic/><keywords>Heterogeneous material, Random microstructure, Characterization and reconstruction, Statistical equivalence, Physical property</keywords><publishedDay>1</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-01-01</publishedDate><doi>10.1016/j.cma.2020.113516</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm/><lastEdited>2021-12-02T11:17:44.2779703</lastEdited><Created>2020-11-16T15:09:20.0391931</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>Jinlong</firstname><surname>Fu</surname><order>1</order></author><author><firstname>Shaoqing</firstname><surname>Cui</surname><orcid/><order>2</order></author><author><firstname>Song</firstname><surname>Cen</surname><order>3</order></author><author><firstname>Chenfeng</firstname><surname>Li</surname><orcid>0000-0003-0441-211X</orcid><order>4</order></author></authors><documents><document><filename>55670__18678__b5c2e882e0cb411da11c8290f3137a4c.pdf</filename><originalFilename>55670.pdf</originalFilename><uploaded>2020-11-17T10:14:03.3244037</uploaded><type>Output</type><contentLength>42967312</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2021-11-06T00:00:00.0000000</embargoDate><documentNotes>&#xA9; 2020. This manuscript version is made available under the CC-BY-NC-ND 4.0 license</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2021-12-02T11:17:44.2779703 v2 55670 2020-11-16 Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network 88a9a34dc92416ac83ea8ff485d06ade Shaoqing Cui Shaoqing Cui true false 82fe170d5ae2c840e538a36209e5a3ac 0000-0003-0441-211X Chenfeng Li Chenfeng Li true false 2020-11-16 Heterogeneous materials, whether natural or artificial, are usually composed of distinct constituents present in complex microstructures with discontinuous, irregular and hierarchical characteristics. For many heterogeneous materials, such as porous media and composites, the microstructural features are of fundamental importance for their macroscopic properties. This paper presents a novel method to statistically characterize and reconstruct random microstructures through a deep neural network (DNN) model, which can be used to study the microstructure–property relationships. In our method, the digital microstructure image is assumed to be a stationary Markov random field (MRF), and local patterns covering the basic morphological features are collected to train a DNN model, after which statistically equivalent samples can be generated through a DNN-guided reconstruction procedure. Furthermore, to overcome the short-distance limitation associated with the MRF assumption, a multi-level approach is developed to preserve the long-distance morphological features of heterogeneous microstructures. A large number of tests have been conducted to compare the reconstructed and target microstructures in both morphological characteristics and physical properties, and good agreements are observed in all test cases. The proposed method is efficient, accurate, versatile, and especially beneficial to the statistical reconstruction of 2D/3D microstructures with long-distance correlations. Journal Article Computer Methods in Applied Mechanics and Engineering 373 113516 Elsevier BV 0045-7825 Heterogeneous material, Random microstructure, Characterization and reconstruction, Statistical equivalence, Physical property 1 1 2021 2021-01-01 10.1016/j.cma.2020.113516 COLLEGE NANME COLLEGE CODE Swansea University 2021-12-02T11:17:44.2779703 2020-11-16T15:09:20.0391931 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Jinlong Fu 1 Shaoqing Cui 2 Song Cen 3 Chenfeng Li 0000-0003-0441-211X 4 55670__18678__b5c2e882e0cb411da11c8290f3137a4c.pdf 55670.pdf 2020-11-17T10:14:03.3244037 Output 42967312 application/pdf Accepted Manuscript true 2021-11-06T00:00:00.0000000 © 2020. This manuscript version is made available under the CC-BY-NC-ND 4.0 license true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network
spellingShingle Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network
Shaoqing Cui
Chenfeng Li
title_short Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network
title_full Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network
title_fullStr Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network
title_full_unstemmed Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network
title_sort Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network
author_id_str_mv 88a9a34dc92416ac83ea8ff485d06ade
82fe170d5ae2c840e538a36209e5a3ac
author_id_fullname_str_mv 88a9a34dc92416ac83ea8ff485d06ade_***_Shaoqing Cui
82fe170d5ae2c840e538a36209e5a3ac_***_Chenfeng Li
author Shaoqing Cui
Chenfeng Li
author2 Jinlong Fu
Shaoqing Cui
Song Cen
Chenfeng Li
format Journal article
container_title Computer Methods in Applied Mechanics and Engineering
container_volume 373
container_start_page 113516
publishDate 2021
institution Swansea University
issn 0045-7825
doi_str_mv 10.1016/j.cma.2020.113516
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 1
active_str 0
description Heterogeneous materials, whether natural or artificial, are usually composed of distinct constituents present in complex microstructures with discontinuous, irregular and hierarchical characteristics. For many heterogeneous materials, such as porous media and composites, the microstructural features are of fundamental importance for their macroscopic properties. This paper presents a novel method to statistically characterize and reconstruct random microstructures through a deep neural network (DNN) model, which can be used to study the microstructure–property relationships. In our method, the digital microstructure image is assumed to be a stationary Markov random field (MRF), and local patterns covering the basic morphological features are collected to train a DNN model, after which statistically equivalent samples can be generated through a DNN-guided reconstruction procedure. Furthermore, to overcome the short-distance limitation associated with the MRF assumption, a multi-level approach is developed to preserve the long-distance morphological features of heterogeneous microstructures. A large number of tests have been conducted to compare the reconstructed and target microstructures in both morphological characteristics and physical properties, and good agreements are observed in all test cases. The proposed method is efficient, accurate, versatile, and especially beneficial to the statistical reconstruction of 2D/3D microstructures with long-distance correlations.
published_date 2021-01-01T05:09:19Z
_version_ 1822286842791198720
score 11.357488

Similar Items