No Cover Image

Journal article 362 views 48 downloads

A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations

Sergi Sanchez-Gamero, Oubay Hassan Orcid Logo, Rubén Sevilla Orcid Logo

International Journal of Computational Fluid Dynamics, Volume: 38, Issue: 2-3, Pages: 221 - 245

Swansea University Authors: Sergi Sanchez-Gamero, Oubay Hassan Orcid Logo, Rubén Sevilla Orcid Logo

  • 65507.VOR.pdf

    PDF | Version of Record

    © 2025 The Author(s). This is an Open Access article distributed under the terms of the Creative Commons Attribution License (CC-BY).

    Download (6.43MB)

Check full text

DOI (Published version): 10.1080/10618562.2024.2306941

Abstract

This work presents a methodology to predict a near-optimal spacing function, which defines the element sizes, suitable to perform steady RANS turbulent viscous flow simulations. The strategy aims at utilising existing high fidelity simulations to compute a target spacing function and train an artifi...

Full description

Published in: International Journal of Computational Fluid Dynamics
ISSN: 1061-8562 1029-0257
Published: Informa UK Limited 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa65507
first_indexed 2024-01-24T16:11:10Z
last_indexed 2025-01-31T20:18:54Z
id cronfa65507
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-01-31T13:11:19.5315148</datestamp><bib-version>v2</bib-version><id>65507</id><entry>2024-01-24</entry><title>A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations</title><swanseaauthors><author><sid>75d991bfc82a42e1a6b4350547e0b7e9</sid><firstname>Sergi</firstname><surname>Sanchez-Gamero</surname><name>Sergi Sanchez-Gamero</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>07479d73eba3773d8904cbfbacc57c5b</sid><ORCID>0000-0001-7472-3218</ORCID><firstname>Oubay</firstname><surname>Hassan</surname><name>Oubay Hassan</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>b542c87f1b891262844e95a682f045b6</sid><ORCID>0000-0002-0061-6214</ORCID><firstname>Rub&#xE9;n</firstname><surname>Sevilla</surname><name>Rub&#xE9;n Sevilla</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-01-24</date><abstract>This work presents a methodology to predict a near-optimal spacing function, which defines the element sizes, suitable to perform steady RANS turbulent viscous flow simulations. The strategy aims at utilising existing high fidelity simulations to compute a target spacing function and train an artificial neural network (ANN) to predict the spacing function for new simulations, either unseen operating conditions or unseen geometric configurations. Several challenges induced by the use of highly stretched elements are addressed. The final goal is to substantially reduce the time and human expertise that is nowadays required to produce suitable meshes for simulations. Numerical examples involving turbulent compressible flows in two dimensions are used to demonstrate the ability of the trained ANN to predict a suitable spacing function. The influence of the NN architecture and the size of the training dataset are discussed. Finally, the suitability of the predicted meshes to perform simulations is investigated.</abstract><type>Journal Article</type><journal>International Journal of Computational Fluid Dynamics</journal><volume>38</volume><journalNumber>2-3</journalNumber><paginationStart>221</paginationStart><paginationEnd>245</paginationEnd><publisher>Informa UK Limited</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1061-8562</issnPrint><issnElectronic>1029-0257</issnElectronic><keywords>Mesh generation; spacing function; machine learning; arti&#xFB01;cial neural network; turbulent compressible viscous &#xFB02;ow</keywords><publishedDay>15</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-03-15</publishedDate><doi>10.1080/10618562.2024.2306941</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>The financial support of the Engineering and Physical Sciences Research Council (Grant Number: EP/T009071/1) is gratefully acknowledged.</funders><projectreference/><lastEdited>2025-01-31T13:11:19.5315148</lastEdited><Created>2024-01-24T16:09:01.4872012</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>Sergi</firstname><surname>Sanchez-Gamero</surname><order>1</order></author><author><firstname>Oubay</firstname><surname>Hassan</surname><orcid>0000-0001-7472-3218</orcid><order>2</order></author><author><firstname>Rub&#xE9;n</firstname><surname>Sevilla</surname><orcid>0000-0002-0061-6214</orcid><order>3</order></author></authors><documents><document><filename>65507__33461__4cc936cb15184a4cb5671123403cfe6c.pdf</filename><originalFilename>65507.VOR.pdf</originalFilename><uploaded>2025-01-31T13:08:46.4022261</uploaded><type>Output</type><contentLength>6739968</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2025 The Author(s). This is an Open Access article distributed under the terms of the 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 2025-01-31T13:11:19.5315148 v2 65507 2024-01-24 A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations 75d991bfc82a42e1a6b4350547e0b7e9 Sergi Sanchez-Gamero Sergi Sanchez-Gamero true false 07479d73eba3773d8904cbfbacc57c5b 0000-0001-7472-3218 Oubay Hassan Oubay Hassan true false b542c87f1b891262844e95a682f045b6 0000-0002-0061-6214 Rubén Sevilla Rubén Sevilla true false 2024-01-24 This work presents a methodology to predict a near-optimal spacing function, which defines the element sizes, suitable to perform steady RANS turbulent viscous flow simulations. The strategy aims at utilising existing high fidelity simulations to compute a target spacing function and train an artificial neural network (ANN) to predict the spacing function for new simulations, either unseen operating conditions or unseen geometric configurations. Several challenges induced by the use of highly stretched elements are addressed. The final goal is to substantially reduce the time and human expertise that is nowadays required to produce suitable meshes for simulations. Numerical examples involving turbulent compressible flows in two dimensions are used to demonstrate the ability of the trained ANN to predict a suitable spacing function. The influence of the NN architecture and the size of the training dataset are discussed. Finally, the suitability of the predicted meshes to perform simulations is investigated. Journal Article International Journal of Computational Fluid Dynamics 38 2-3 221 245 Informa UK Limited 1061-8562 1029-0257 Mesh generation; spacing function; machine learning; artificial neural network; turbulent compressible viscous flow 15 3 2024 2024-03-15 10.1080/10618562.2024.2306941 COLLEGE NANME COLLEGE CODE Swansea University SU Library paid the OA fee (TA Institutional Deal) The financial support of the Engineering and Physical Sciences Research Council (Grant Number: EP/T009071/1) is gratefully acknowledged. 2025-01-31T13:11:19.5315148 2024-01-24T16:09:01.4872012 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Sergi Sanchez-Gamero 1 Oubay Hassan 0000-0001-7472-3218 2 Rubén Sevilla 0000-0002-0061-6214 3 65507__33461__4cc936cb15184a4cb5671123403cfe6c.pdf 65507.VOR.pdf 2025-01-31T13:08:46.4022261 Output 6739968 application/pdf Version of Record true © 2025 The Author(s). This is an Open Access article distributed under the terms of the Creative Commons Attribution License (CC-BY). true eng https://creativecommons.org/licenses/by/4.0/
title A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations
spellingShingle A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations
Sergi Sanchez-Gamero
Oubay Hassan
Rubén Sevilla
title_short A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations
title_full A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations
title_fullStr A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations
title_full_unstemmed A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations
title_sort A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations
author_id_str_mv 75d991bfc82a42e1a6b4350547e0b7e9
07479d73eba3773d8904cbfbacc57c5b
b542c87f1b891262844e95a682f045b6
author_id_fullname_str_mv 75d991bfc82a42e1a6b4350547e0b7e9_***_Sergi Sanchez-Gamero
07479d73eba3773d8904cbfbacc57c5b_***_Oubay Hassan
b542c87f1b891262844e95a682f045b6_***_Rubén Sevilla
author Sergi Sanchez-Gamero
Oubay Hassan
Rubén Sevilla
author2 Sergi Sanchez-Gamero
Oubay Hassan
Rubén Sevilla
format Journal article
container_title International Journal of Computational Fluid Dynamics
container_volume 38
container_issue 2-3
container_start_page 221
publishDate 2024
institution Swansea University
issn 1061-8562
1029-0257
doi_str_mv 10.1080/10618562.2024.2306941
publisher Informa UK Limited
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 This work presents a methodology to predict a near-optimal spacing function, which defines the element sizes, suitable to perform steady RANS turbulent viscous flow simulations. The strategy aims at utilising existing high fidelity simulations to compute a target spacing function and train an artificial neural network (ANN) to predict the spacing function for new simulations, either unseen operating conditions or unseen geometric configurations. Several challenges induced by the use of highly stretched elements are addressed. The final goal is to substantially reduce the time and human expertise that is nowadays required to produce suitable meshes for simulations. Numerical examples involving turbulent compressible flows in two dimensions are used to demonstrate the ability of the trained ANN to predict a suitable spacing function. The influence of the NN architecture and the size of the training dataset are discussed. Finally, the suitability of the predicted meshes to perform simulations is investigated.
published_date 2024-03-15T09:31:20Z
_version_ 1830272086035136512
score 11.060726

Similar Items