No Cover Image

Journal article 299 views 111 downloads

Data-driven inverse modelling through neural network (deep learning) and computational heat transfer

Hamid Tamaddon-Jahromi, Neeraj Kavan Chakshu, Igor Sazonov Orcid Logo, Llion Evans Orcid Logo, Hywel Thomas Orcid Logo, Perumal Nithiarasu Orcid Logo

Computer Methods in Applied Mechanics and Engineering, Volume: 369

Swansea University Authors: Hamid Tamaddon-Jahromi, Neeraj Kavan Chakshu, Igor Sazonov Orcid Logo, Llion Evans Orcid Logo, Hywel Thomas Orcid Logo, Perumal Nithiarasu Orcid Logo

  • 54477.pdf

    PDF | Version of Record

    Released under the terms of a Creative Commons Attribution License (CC-BY).

    Download (2.54MB)

Abstract

In this work, the potential of carrying out inverse problems with linear and non-linear behaviour is investigated using deep learning methods. In inverse problems, the boundary conditions are determined using sparse measurement of a variable such as velocity or temperature. Although this is mathemat...

Full description

Published in: Computer Methods in Applied Mechanics and Engineering
ISSN: 0045-7825
Published: Elsevier BV 2020
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa54477
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2020-06-15T19:11:20Z
last_indexed 2021-12-03T04:13:01Z
id cronfa54477
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-12-02T11:37:40.9844676</datestamp><bib-version>v2</bib-version><id>54477</id><entry>2020-06-15</entry><title>Data-driven inverse modelling through neural network (deep learning) and computational heat transfer</title><swanseaauthors><author><sid>b3a1417ca93758b719acf764c7ced1c5</sid><firstname>Hamid</firstname><surname>Tamaddon-Jahromi</surname><name>Hamid Tamaddon-Jahromi</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>e21c85ee9062e9be0fff8ab9d77b14d7</sid><firstname>Neeraj Kavan</firstname><surname>Chakshu</surname><name>Neeraj Kavan Chakshu</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>05a507952e26462561085fb6f62c8897</sid><ORCID>0000-0001-6685-2351</ORCID><firstname>Igor</firstname><surname>Sazonov</surname><name>Igor Sazonov</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>74dc5084c47484922a6e0135ebcb9402</sid><ORCID>0000-0002-4964-4187</ORCID><firstname>Llion</firstname><surname>Evans</surname><name>Llion Evans</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>08ebc76b093f3e17fed29281f5cb637e</sid><ORCID>0000-0002-3951-0409</ORCID><firstname>Hywel</firstname><surname>Thomas</surname><name>Hywel Thomas</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>3b28bf59358fc2b9bd9a46897dbfc92d</sid><ORCID>0000-0002-4901-2980</ORCID><firstname>Perumal</firstname><surname>Nithiarasu</surname><name>Perumal Nithiarasu</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2020-06-15</date><deptcode>CIVL</deptcode><abstract>In this work, the potential of carrying out inverse problems with linear and non-linear behaviour is investigated using deep learning methods. In inverse problems, the boundary conditions are determined using sparse measurement of a variable such as velocity or temperature. Although this is mathematically tractable for simple problems, it can be extremely challenging for complex problems. To overcome the non-linear and complex effects, a brute force approach was used on a trial and error basis to find an approximate solution. With the advent of machine learning algorithms it may now be possible to model inverse problems faster and more accurately. In order to demonstrate that machine learning can be used in solving inverse problems, we propose a fusion between computational mechanics and machine learning. The forward problems are solved first to create a database. This database is then used to train the machine learning algorithms. The trained algorithm is then used to determine the boundary conditions of a problem from assumed measurements. The proposed method is tested for the linear/non-linear heat conduction, convection&#x2013;conduction, and natural convection problems in which the boundary conditions are determined by providing three, four, and five temperature measurements. This study demonstrates that the proposed fusion of computational mechanics and machine learning is an effective way of tackling complex inverse problems.</abstract><type>Journal Article</type><journal>Computer Methods in Applied Mechanics and Engineering</journal><volume>369</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0045-7825</issnPrint><issnElectronic/><keywords>Inverse modelling, Computational mechanics, Machine learning, Heat conduction, Heat convection&#x2013;conduction, Natural convection</keywords><publishedDay>1</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2020</publishedYear><publishedDate>2020-09-01</publishedDate><doi>10.1016/j.cma.2020.113217</doi><url/><notes/><college>COLLEGE NANME</college><department>Civil Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CIVL</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>UKRI, EP/R012091/1</funders><lastEdited>2021-12-02T11:37:40.9844676</lastEdited><Created>2020-06-15T14:24:38.2793452</Created><path><level id="1">College of Engineering</level><level id="2">Engineering</level></path><authors><author><firstname>Hamid</firstname><surname>Tamaddon-Jahromi</surname><order>1</order></author><author><firstname>Neeraj Kavan</firstname><surname>Chakshu</surname><order>2</order></author><author><firstname>Igor</firstname><surname>Sazonov</surname><orcid>0000-0001-6685-2351</orcid><order>3</order></author><author><firstname>Llion</firstname><surname>Evans</surname><orcid>0000-0002-4964-4187</orcid><order>4</order></author><author><firstname>Hywel</firstname><surname>Thomas</surname><orcid>0000-0002-3951-0409</orcid><order>5</order></author><author><firstname>Perumal</firstname><surname>Nithiarasu</surname><orcid>0000-0002-4901-2980</orcid><order>6</order></author></authors><documents><document><filename>54477__17614__6bf9c9ec50444af6ba72f369d18a529b.pdf</filename><originalFilename>54477.pdf</originalFilename><uploaded>2020-07-01T13:25:36.4150247</uploaded><type>Output</type><contentLength>2668543</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Released under the terms of a Creative Commons Attribution License (CC-BY).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2021-12-02T11:37:40.9844676 v2 54477 2020-06-15 Data-driven inverse modelling through neural network (deep learning) and computational heat transfer b3a1417ca93758b719acf764c7ced1c5 Hamid Tamaddon-Jahromi Hamid Tamaddon-Jahromi true false e21c85ee9062e9be0fff8ab9d77b14d7 Neeraj Kavan Chakshu Neeraj Kavan Chakshu true false 05a507952e26462561085fb6f62c8897 0000-0001-6685-2351 Igor Sazonov Igor Sazonov true false 74dc5084c47484922a6e0135ebcb9402 0000-0002-4964-4187 Llion Evans Llion Evans true false 08ebc76b093f3e17fed29281f5cb637e 0000-0002-3951-0409 Hywel Thomas Hywel Thomas true false 3b28bf59358fc2b9bd9a46897dbfc92d 0000-0002-4901-2980 Perumal Nithiarasu Perumal Nithiarasu true false 2020-06-15 CIVL In this work, the potential of carrying out inverse problems with linear and non-linear behaviour is investigated using deep learning methods. In inverse problems, the boundary conditions are determined using sparse measurement of a variable such as velocity or temperature. Although this is mathematically tractable for simple problems, it can be extremely challenging for complex problems. To overcome the non-linear and complex effects, a brute force approach was used on a trial and error basis to find an approximate solution. With the advent of machine learning algorithms it may now be possible to model inverse problems faster and more accurately. In order to demonstrate that machine learning can be used in solving inverse problems, we propose a fusion between computational mechanics and machine learning. The forward problems are solved first to create a database. This database is then used to train the machine learning algorithms. The trained algorithm is then used to determine the boundary conditions of a problem from assumed measurements. The proposed method is tested for the linear/non-linear heat conduction, convection–conduction, and natural convection problems in which the boundary conditions are determined by providing three, four, and five temperature measurements. This study demonstrates that the proposed fusion of computational mechanics and machine learning is an effective way of tackling complex inverse problems. Journal Article Computer Methods in Applied Mechanics and Engineering 369 Elsevier BV 0045-7825 Inverse modelling, Computational mechanics, Machine learning, Heat conduction, Heat convection–conduction, Natural convection 1 9 2020 2020-09-01 10.1016/j.cma.2020.113217 COLLEGE NANME Civil Engineering COLLEGE CODE CIVL Swansea University UKRI, EP/R012091/1 2021-12-02T11:37:40.9844676 2020-06-15T14:24:38.2793452 College of Engineering Engineering Hamid Tamaddon-Jahromi 1 Neeraj Kavan Chakshu 2 Igor Sazonov 0000-0001-6685-2351 3 Llion Evans 0000-0002-4964-4187 4 Hywel Thomas 0000-0002-3951-0409 5 Perumal Nithiarasu 0000-0002-4901-2980 6 54477__17614__6bf9c9ec50444af6ba72f369d18a529b.pdf 54477.pdf 2020-07-01T13:25:36.4150247 Output 2668543 application/pdf Version of Record true Released under the terms of a Creative Commons Attribution License (CC-BY). true eng https://creativecommons.org/licenses/by/4.0/
title Data-driven inverse modelling through neural network (deep learning) and computational heat transfer
spellingShingle Data-driven inverse modelling through neural network (deep learning) and computational heat transfer
Hamid Tamaddon-Jahromi
Neeraj Kavan Chakshu
Igor Sazonov
Llion Evans
Hywel Thomas
Perumal Nithiarasu
title_short Data-driven inverse modelling through neural network (deep learning) and computational heat transfer
title_full Data-driven inverse modelling through neural network (deep learning) and computational heat transfer
title_fullStr Data-driven inverse modelling through neural network (deep learning) and computational heat transfer
title_full_unstemmed Data-driven inverse modelling through neural network (deep learning) and computational heat transfer
title_sort Data-driven inverse modelling through neural network (deep learning) and computational heat transfer
author_id_str_mv b3a1417ca93758b719acf764c7ced1c5
e21c85ee9062e9be0fff8ab9d77b14d7
05a507952e26462561085fb6f62c8897
74dc5084c47484922a6e0135ebcb9402
08ebc76b093f3e17fed29281f5cb637e
3b28bf59358fc2b9bd9a46897dbfc92d
author_id_fullname_str_mv b3a1417ca93758b719acf764c7ced1c5_***_Hamid Tamaddon-Jahromi
e21c85ee9062e9be0fff8ab9d77b14d7_***_Neeraj Kavan Chakshu
05a507952e26462561085fb6f62c8897_***_Igor Sazonov
74dc5084c47484922a6e0135ebcb9402_***_Llion Evans
08ebc76b093f3e17fed29281f5cb637e_***_Hywel Thomas
3b28bf59358fc2b9bd9a46897dbfc92d_***_Perumal Nithiarasu
author Hamid Tamaddon-Jahromi
Neeraj Kavan Chakshu
Igor Sazonov
Llion Evans
Hywel Thomas
Perumal Nithiarasu
author2 Hamid Tamaddon-Jahromi
Neeraj Kavan Chakshu
Igor Sazonov
Llion Evans
Hywel Thomas
Perumal Nithiarasu
format Journal article
container_title Computer Methods in Applied Mechanics and Engineering
container_volume 369
publishDate 2020
institution Swansea University
issn 0045-7825
doi_str_mv 10.1016/j.cma.2020.113217
publisher Elsevier BV
college_str College of Engineering
hierarchytype
hierarchy_top_id collegeofengineering
hierarchy_top_title College of Engineering
hierarchy_parent_id collegeofengineering
hierarchy_parent_title College of Engineering
department_str Engineering{{{_:::_}}}College of Engineering{{{_:::_}}}Engineering
document_store_str 1
active_str 0
description In this work, the potential of carrying out inverse problems with linear and non-linear behaviour is investigated using deep learning methods. In inverse problems, the boundary conditions are determined using sparse measurement of a variable such as velocity or temperature. Although this is mathematically tractable for simple problems, it can be extremely challenging for complex problems. To overcome the non-linear and complex effects, a brute force approach was used on a trial and error basis to find an approximate solution. With the advent of machine learning algorithms it may now be possible to model inverse problems faster and more accurately. In order to demonstrate that machine learning can be used in solving inverse problems, we propose a fusion between computational mechanics and machine learning. The forward problems are solved first to create a database. This database is then used to train the machine learning algorithms. The trained algorithm is then used to determine the boundary conditions of a problem from assumed measurements. The proposed method is tested for the linear/non-linear heat conduction, convection–conduction, and natural convection problems in which the boundary conditions are determined by providing three, four, and five temperature measurements. This study demonstrates that the proposed fusion of computational mechanics and machine learning is an effective way of tackling complex inverse problems.
published_date 2020-09-01T04:09:06Z
_version_ 1737027534581661696
score 10.8781185