No Cover Image

Journal article 96 views 4 downloads

Anisotropic mesh spacing prediction using neural networks

Callum Lock, Oubay Hassan Orcid Logo, Rubén Sevilla Orcid Logo, Jason Jones

Computer-Aided Design, Volume: 193, Start page: 104040

Swansea University Authors: Callum Lock, Oubay Hassan Orcid Logo, Rubén Sevilla Orcid Logo, Jason Jones

  • MeshingNNanisotropy.pdf

    PDF | Accepted Manuscript

    Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).

    Download (41.07MB)

Check full text

DOI (Published version): 10.1016/j.cad.2026.104040

Abstract

This work presents a framework to predict near-optimal anisotropic spacing functions suitable to perform simulations with unseen operating conditions or geometric configurations. The strategy consists of utilising the vast amount of high-fidelity data available in industry to compute a target anisot...

Full description

Published in: Computer-Aided Design
ISSN: 0010-4485
Published: Elsevier BV 2026
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71372
first_indexed 2026-02-02T18:02:35Z
last_indexed 2026-03-13T05:24:47Z
id cronfa71372
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-03-12T13:13:56.4158328</datestamp><bib-version>v2</bib-version><id>71372</id><entry>2026-02-02</entry><title>Anisotropic mesh spacing prediction using neural networks</title><swanseaauthors><author><sid>3eeb9d55ddd52c145526e56117933261</sid><firstname>Callum</firstname><surname>Lock</surname><name>Callum Lock</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><author><sid>aa4865d48c53a0df1c1547171826eab9</sid><firstname>Jason</firstname><surname>Jones</surname><name>Jason Jones</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-02-02</date><deptcode>ACEM</deptcode><abstract>This work presents a framework to predict near-optimal anisotropic spacing functions suitable to perform simulations with unseen operating conditions or geometric configurations. The strategy consists of utilising the vast amount of high-fidelity data available in industry to compute a target anisotropic spacing and train an artificial neural network to predict the spacing for unseen scenarios. The trained neural network outputs the metric tensor at the nodes of a coarse background mesh that is then used to generate meshes for unseen cases. Examples are used to demonstrate the effect of the network hyperparameters and the training dataset on the accuracy of the predictions. The potential of the method is demonstrated for examples involving up to 11 geometric parameters on CFD simulations involving a full aircraft configuration.</abstract><type>Journal Article</type><journal>Computer-Aided Design</journal><volume>193</volume><journalNumber/><paginationStart>104040</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0010-4485</issnPrint><issnElectronic/><keywords/><publishedDay>1</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-04-01</publishedDate><doi>10.1016/j.cad.2026.104040</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>Engineering and Physical Sciences Research Council (EP/T517987/1)</funders><projectreference/><lastEdited>2026-03-12T13:13:56.4158328</lastEdited><Created>2026-02-02T17:52:20.3034425</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>Callum</firstname><surname>Lock</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><author><firstname>Jason</firstname><surname>Jones</surname><order>4</order></author></authors><documents><document><filename>71372__36170__741359ce71c4482493cb6697e9264192.pdf</filename><originalFilename>MeshingNNanisotropy.pdf</originalFilename><uploaded>2026-02-02T18:01:13.2180510</uploaded><type>Output</type><contentLength>43067133</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><documentNotes>Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/deed.en</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-03-12T13:13:56.4158328 v2 71372 2026-02-02 Anisotropic mesh spacing prediction using neural networks 3eeb9d55ddd52c145526e56117933261 Callum Lock Callum Lock true false 07479d73eba3773d8904cbfbacc57c5b 0000-0001-7472-3218 Oubay Hassan Oubay Hassan true false b542c87f1b891262844e95a682f045b6 0000-0002-0061-6214 Rubén Sevilla Rubén Sevilla true false aa4865d48c53a0df1c1547171826eab9 Jason Jones Jason Jones true false 2026-02-02 ACEM This work presents a framework to predict near-optimal anisotropic spacing functions suitable to perform simulations with unseen operating conditions or geometric configurations. The strategy consists of utilising the vast amount of high-fidelity data available in industry to compute a target anisotropic spacing and train an artificial neural network to predict the spacing for unseen scenarios. The trained neural network outputs the metric tensor at the nodes of a coarse background mesh that is then used to generate meshes for unseen cases. Examples are used to demonstrate the effect of the network hyperparameters and the training dataset on the accuracy of the predictions. The potential of the method is demonstrated for examples involving up to 11 geometric parameters on CFD simulations involving a full aircraft configuration. Journal Article Computer-Aided Design 193 104040 Elsevier BV 0010-4485 1 4 2026 2026-04-01 10.1016/j.cad.2026.104040 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University Engineering and Physical Sciences Research Council (EP/T517987/1) 2026-03-12T13:13:56.4158328 2026-02-02T17:52:20.3034425 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Callum Lock 1 Oubay Hassan 0000-0001-7472-3218 2 Rubén Sevilla 0000-0002-0061-6214 3 Jason Jones 4 71372__36170__741359ce71c4482493cb6697e9264192.pdf MeshingNNanisotropy.pdf 2026-02-02T18:01:13.2180510 Output 43067133 application/pdf Accepted Manuscript true Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention). true eng https://creativecommons.org/licenses/by/4.0/deed.en
title Anisotropic mesh spacing prediction using neural networks
spellingShingle Anisotropic mesh spacing prediction using neural networks
Callum Lock
Oubay Hassan
Rubén Sevilla
Jason Jones
title_short Anisotropic mesh spacing prediction using neural networks
title_full Anisotropic mesh spacing prediction using neural networks
title_fullStr Anisotropic mesh spacing prediction using neural networks
title_full_unstemmed Anisotropic mesh spacing prediction using neural networks
title_sort Anisotropic mesh spacing prediction using neural networks
author_id_str_mv 3eeb9d55ddd52c145526e56117933261
07479d73eba3773d8904cbfbacc57c5b
b542c87f1b891262844e95a682f045b6
aa4865d48c53a0df1c1547171826eab9
author_id_fullname_str_mv 3eeb9d55ddd52c145526e56117933261_***_Callum Lock
07479d73eba3773d8904cbfbacc57c5b_***_Oubay Hassan
b542c87f1b891262844e95a682f045b6_***_Rubén Sevilla
aa4865d48c53a0df1c1547171826eab9_***_Jason Jones
author Callum Lock
Oubay Hassan
Rubén Sevilla
Jason Jones
author2 Callum Lock
Oubay Hassan
Rubén Sevilla
Jason Jones
format Journal article
container_title Computer-Aided Design
container_volume 193
container_start_page 104040
publishDate 2026
institution Swansea University
issn 0010-4485
doi_str_mv 10.1016/j.cad.2026.104040
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 This work presents a framework to predict near-optimal anisotropic spacing functions suitable to perform simulations with unseen operating conditions or geometric configurations. The strategy consists of utilising the vast amount of high-fidelity data available in industry to compute a target anisotropic spacing and train an artificial neural network to predict the spacing for unseen scenarios. The trained neural network outputs the metric tensor at the nodes of a coarse background mesh that is then used to generate meshes for unseen cases. Examples are used to demonstrate the effect of the network hyperparameters and the training dataset on the accuracy of the predictions. The potential of the method is demonstrated for examples involving up to 11 geometric parameters on CFD simulations involving a full aircraft configuration.
published_date 2026-04-01T05:22:02Z
_version_ 1859704190838767616
score 11.099424

Similar Items