No Cover Image

Journal article 226 views 140 downloads

Deep learning or interpolation for inverse modelling of heat and fluid flow problems?

Rainald Löhner, Harbir Antil, Hamid Tamaddon-Jahromi, Neeraj Kavan Chakshu, Perumal Nithiarasu Orcid Logo

International Journal of Numerical Methods for Heat & Fluid Flow, Volume: 31, Issue: 9, Pages: 3036 - 3046

Swansea University Authors: Hamid Tamaddon-Jahromi, Neeraj Kavan Chakshu, Perumal Nithiarasu Orcid Logo

  • 55843.pdf

    PDF | Accepted Manuscript

    Released under the terms of a Creative Commons Attribution Non-commercial International Licence 4.0 (CC BY-NC 4.0)

    Download (3.24MB)

Abstract

PurposeThe purpose of this study is to compare interpolation algorithms and deep neural networks for inverse transfer problems with linear and nonlinear behaviour.Design/methodology/approachA series of runs were conducted for a canonical test problem. These were used as databases or “learning sets”...

Full description

Published in: International Journal of Numerical Methods for Heat & Fluid Flow
ISSN: 0961-5539
Published: Emerald 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa55843
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2020-12-07T11:48:17Z
last_indexed 2021-09-23T03:17:59Z
id cronfa55843
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-09-22T16:34:04.9925599</datestamp><bib-version>v2</bib-version><id>55843</id><entry>2020-12-07</entry><title>Deep learning or interpolation for inverse modelling of heat and fluid flow problems?</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>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>2020-12-07</date><deptcode>CIVL</deptcode><abstract>PurposeThe purpose of this study is to compare interpolation algorithms and deep neural networks for inverse transfer problems with linear and nonlinear behaviour.Design/methodology/approachA series of runs were conducted for a canonical test problem. These were used as databases or &#x201C;learning sets&#x201D; for both interpolation algorithms and deep neural networks. A second set of runs was conducted to test the prediction accuracy of both approaches.FindingsThe results indicate that interpolation algorithms outperform deep neural networks in accuracy for linear heat conduction, while the reverse is true for nonlinear heat conduction problems. For heat convection problems, both methods offer similar levels of accuracy.Originality/valueThis is the first time such a comparison has been made.</abstract><type>Journal Article</type><journal>International Journal of Numerical Methods for Heat &amp; Fluid Flow</journal><volume>31</volume><journalNumber>9</journalNumber><paginationStart>3036</paginationStart><paginationEnd>3046</paginationEnd><publisher>Emerald</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0961-5539</issnPrint><issnElectronic/><keywords>Interpolation, Deep Learning, Deep Neural Networks, Linear heat conduction, Non-Linear heat conduction, Forced and natural convection</keywords><publishedDay>26</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-08-26</publishedDate><doi>10.1108/hff-11-2020-0684</doi><url/><notes/><college>COLLEGE NANME</college><department>Civil Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CIVL</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2021-09-22T16:34:04.9925599</lastEdited><Created>2020-12-07T11:46:00.9027778</Created><path><level id="1">College of Engineering</level><level id="2">Engineering</level></path><authors><author><firstname>Rainald</firstname><surname>L&#xF6;hner</surname><order>1</order></author><author><firstname>Harbir</firstname><surname>Antil</surname><order>2</order></author><author><firstname>Hamid</firstname><surname>Tamaddon-Jahromi</surname><order>3</order></author><author><firstname>Neeraj Kavan</firstname><surname>Chakshu</surname><order>4</order></author><author><firstname>Perumal</firstname><surname>Nithiarasu</surname><orcid>0000-0002-4901-2980</orcid><order>5</order></author></authors><documents><document><filename>55843__18982__8d281f0d94574ecdab792b6ce69efb32.pdf</filename><originalFilename>55843.pdf</originalFilename><uploaded>2021-01-06T10:49:20.3780784</uploaded><type>Output</type><contentLength>3399023</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><documentNotes>Released under the terms of a Creative Commons Attribution Non-commercial International Licence 4.0 (CC BY-NC 4.0)</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2021-09-22T16:34:04.9925599 v2 55843 2020-12-07 Deep learning or interpolation for inverse modelling of heat and fluid flow problems? b3a1417ca93758b719acf764c7ced1c5 Hamid Tamaddon-Jahromi Hamid Tamaddon-Jahromi true false e21c85ee9062e9be0fff8ab9d77b14d7 Neeraj Kavan Chakshu Neeraj Kavan Chakshu true false 3b28bf59358fc2b9bd9a46897dbfc92d 0000-0002-4901-2980 Perumal Nithiarasu Perumal Nithiarasu true false 2020-12-07 CIVL PurposeThe purpose of this study is to compare interpolation algorithms and deep neural networks for inverse transfer problems with linear and nonlinear behaviour.Design/methodology/approachA series of runs were conducted for a canonical test problem. These were used as databases or “learning sets” for both interpolation algorithms and deep neural networks. A second set of runs was conducted to test the prediction accuracy of both approaches.FindingsThe results indicate that interpolation algorithms outperform deep neural networks in accuracy for linear heat conduction, while the reverse is true for nonlinear heat conduction problems. For heat convection problems, both methods offer similar levels of accuracy.Originality/valueThis is the first time such a comparison has been made. Journal Article International Journal of Numerical Methods for Heat & Fluid Flow 31 9 3036 3046 Emerald 0961-5539 Interpolation, Deep Learning, Deep Neural Networks, Linear heat conduction, Non-Linear heat conduction, Forced and natural convection 26 8 2021 2021-08-26 10.1108/hff-11-2020-0684 COLLEGE NANME Civil Engineering COLLEGE CODE CIVL Swansea University 2021-09-22T16:34:04.9925599 2020-12-07T11:46:00.9027778 College of Engineering Engineering Rainald Löhner 1 Harbir Antil 2 Hamid Tamaddon-Jahromi 3 Neeraj Kavan Chakshu 4 Perumal Nithiarasu 0000-0002-4901-2980 5 55843__18982__8d281f0d94574ecdab792b6ce69efb32.pdf 55843.pdf 2021-01-06T10:49:20.3780784 Output 3399023 application/pdf Accepted Manuscript true Released under the terms of a Creative Commons Attribution Non-commercial International Licence 4.0 (CC BY-NC 4.0) true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title Deep learning or interpolation for inverse modelling of heat and fluid flow problems?
spellingShingle Deep learning or interpolation for inverse modelling of heat and fluid flow problems?
Hamid Tamaddon-Jahromi
Neeraj Kavan Chakshu
Perumal Nithiarasu
title_short Deep learning or interpolation for inverse modelling of heat and fluid flow problems?
title_full Deep learning or interpolation for inverse modelling of heat and fluid flow problems?
title_fullStr Deep learning or interpolation for inverse modelling of heat and fluid flow problems?
title_full_unstemmed Deep learning or interpolation for inverse modelling of heat and fluid flow problems?
title_sort Deep learning or interpolation for inverse modelling of heat and fluid flow problems?
author_id_str_mv b3a1417ca93758b719acf764c7ced1c5
e21c85ee9062e9be0fff8ab9d77b14d7
3b28bf59358fc2b9bd9a46897dbfc92d
author_id_fullname_str_mv b3a1417ca93758b719acf764c7ced1c5_***_Hamid Tamaddon-Jahromi
e21c85ee9062e9be0fff8ab9d77b14d7_***_Neeraj Kavan Chakshu
3b28bf59358fc2b9bd9a46897dbfc92d_***_Perumal Nithiarasu
author Hamid Tamaddon-Jahromi
Neeraj Kavan Chakshu
Perumal Nithiarasu
author2 Rainald Löhner
Harbir Antil
Hamid Tamaddon-Jahromi
Neeraj Kavan Chakshu
Perumal Nithiarasu
format Journal article
container_title International Journal of Numerical Methods for Heat & Fluid Flow
container_volume 31
container_issue 9
container_start_page 3036
publishDate 2021
institution Swansea University
issn 0961-5539
doi_str_mv 10.1108/hff-11-2020-0684
publisher Emerald
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 PurposeThe purpose of this study is to compare interpolation algorithms and deep neural networks for inverse transfer problems with linear and nonlinear behaviour.Design/methodology/approachA series of runs were conducted for a canonical test problem. These were used as databases or “learning sets” for both interpolation algorithms and deep neural networks. A second set of runs was conducted to test the prediction accuracy of both approaches.FindingsThe results indicate that interpolation algorithms outperform deep neural networks in accuracy for linear heat conduction, while the reverse is true for nonlinear heat conduction problems. For heat convection problems, both methods offer similar levels of accuracy.Originality/valueThis is the first time such a comparison has been made.
published_date 2021-08-26T04:11:06Z
_version_ 1737027660430704640
score 10.878272