Meshing using neural networks for improving the efficiency of computer modelling

Lock, Callum; Hassan, Oubay; Sevilla, Rubén; Jones, Jason

doi:10.1007/s00366-023-01812-z

Journal article 22668 views 52 downloads

Meshing using neural networks for improving the efficiency of computer modelling

Callum Lock, Oubay Hassan

, Rubén Sevilla

, Jason Jones

Engineering with Computers, Volume: 39, Issue: 6, Pages: 3791 - 3820

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

PDF | Version of Record

© The Author(s) 2023. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0).
Download (6.57MB)

Check full text

DOI (Published version): 10.1007/s00366-023-01812-z

Abstract

This work presents a novel approach capable of predicting an appropriate spacing function that can be used to generate a near-optimal mesh suitable for simulation. The main objective is to make use of the large number of simulations that are nowadays available, and to alleviate the time-consuming me...

Full description

Published in:	Engineering with Computers
ISSN:	0177-0667 1435-5663
Published:	Springer Science and Business Media LLC 2023
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa63253
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2023-04-26T11:02:42Z
last_indexed	2023-04-26T11:02:42Z
id	cronfa63253
recordtype	SURis
fullrecord	<?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>63253</id><entry>2023-04-26</entry><title>Meshing using neural networks for improving the efficiency of computer modelling</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>Rubén</firstname><surname>Sevilla</surname><name>Rubén Sevilla</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>aa4865d48c53a0df1c1547171826eab9</sid><ORCID>0000-0002-7715-1857</ORCID><firstname>Jason</firstname><surname>Jones</surname><name>Jason Jones</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-04-26</date><abstract>This work presents a novel approach capable of predicting an appropriate spacing function that can be used to generate a near-optimal mesh suitable for simulation. The main objective is to make use of the large number of simulations that are nowadays available, and to alleviate the time-consuming mesh generation stage by minimising human intervention. For a given simulation, a technique to produce a set of point sources that leads to a mesh capable of capturing all the features of the solution is proposed. In addition, a method to combine all sets of sources for the simulations available is devised. The global set of sources is used to train a neural network that, for some design parameters (e.g., flow conditions, geometry), predicts the characteristics of the sources. Numerical examples, in the context of three dimensional inviscid compressible flows, are considered to demonstrate the potential of the proposed approach. It is shown that accurate predictions of the required spacing function can be produced, even with reduced training datasets. In addition, the predicted near-optimal meshes are utilised to compute flow solutions, and the results show that the computed aerodynamic coefficients are within the required accuracy for the aerospace industry. An analysis is also presented to demonstrate that the proposed method lies in the category of green AI research, meaning that computational resources and time are substantially reduced with this approach, when compared to current practice in industry.</abstract><type>Journal Article</type><journal>Engineering with Computers</journal><volume>39</volume><journalNumber>6</journalNumber><paginationStart>3791</paginationStart><paginationEnd>3820</paginationEnd><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0177-0667</issnPrint><issnElectronic>1435-5663</issnElectronic><keywords>Mesh generation, Spacing function, Machine learning, Near-optimal mesh prediction, Computational fluid dynamics</keywords><publishedDay>1</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-12-01</publishedDate><doi>10.1007/s00366-023-01812-z</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>Swansea University. The authors are grateful for the financial support provided by the Engineering and Physical Sciences Research Council (EP/T517987/1).</funders><projectreference/><lastEdited>2024-06-06T12:25:31.4623424</lastEdited><Created>2023-04-26T11:55:25.9518438</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>Rubén</firstname><surname>Sevilla</surname><orcid>0000-0002-0061-6214</orcid><order>3</order></author><author><firstname>Jason</firstname><surname>Jones</surname><orcid>0000-0002-7715-1857</orcid><order>4</order></author></authors><documents><document><filename>63253__27212__44326192a62d43eab81c0d35572f35d5.pdf</filename><originalFilename>63253.pdf</originalFilename><uploaded>2023-04-26T12:00:05.6682930</uploaded><type>Output</type><contentLength>6891526</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© The Author(s) 2023. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/.</licence></document></documents><OutputDurs/></rfc1807>
spelling	v2 63253 2023-04-26 Meshing using neural networks for improving the efficiency of computer modelling 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 0000-0002-7715-1857 Jason Jones Jason Jones true false 2023-04-26 This work presents a novel approach capable of predicting an appropriate spacing function that can be used to generate a near-optimal mesh suitable for simulation. The main objective is to make use of the large number of simulations that are nowadays available, and to alleviate the time-consuming mesh generation stage by minimising human intervention. For a given simulation, a technique to produce a set of point sources that leads to a mesh capable of capturing all the features of the solution is proposed. In addition, a method to combine all sets of sources for the simulations available is devised. The global set of sources is used to train a neural network that, for some design parameters (e.g., flow conditions, geometry), predicts the characteristics of the sources. Numerical examples, in the context of three dimensional inviscid compressible flows, are considered to demonstrate the potential of the proposed approach. It is shown that accurate predictions of the required spacing function can be produced, even with reduced training datasets. In addition, the predicted near-optimal meshes are utilised to compute flow solutions, and the results show that the computed aerodynamic coefficients are within the required accuracy for the aerospace industry. An analysis is also presented to demonstrate that the proposed method lies in the category of green AI research, meaning that computational resources and time are substantially reduced with this approach, when compared to current practice in industry. Journal Article Engineering with Computers 39 6 3791 3820 Springer Science and Business Media LLC 0177-0667 1435-5663 Mesh generation, Spacing function, Machine learning, Near-optimal mesh prediction, Computational fluid dynamics 1 12 2023 2023-12-01 10.1007/s00366-023-01812-z COLLEGE NANME COLLEGE CODE Swansea University SU Library paid the OA fee (TA Institutional Deal) Swansea University. The authors are grateful for the financial support provided by the Engineering and Physical Sciences Research Council (EP/T517987/1). 2024-06-06T12:25:31.4623424 2023-04-26T11:55:25.9518438 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 0000-0002-7715-1857 4 63253__27212__44326192a62d43eab81c0d35572f35d5.pdf 63253.pdf 2023-04-26T12:00:05.6682930 Output 6891526 application/pdf Version of Record true © The Author(s) 2023. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0). true eng http://creativecommons.org/licenses/by/4.0/.
title	Meshing using neural networks for improving the efficiency of computer modelling
spellingShingle	Meshing using neural networks for improving the efficiency of computer modelling Callum Lock Oubay Hassan Rubén Sevilla Jason Jones
title_short	Meshing using neural networks for improving the efficiency of computer modelling
title_full	Meshing using neural networks for improving the efficiency of computer modelling
title_fullStr	Meshing using neural networks for improving the efficiency of computer modelling
title_full_unstemmed	Meshing using neural networks for improving the efficiency of computer modelling
title_sort	Meshing using neural networks for improving the efficiency of computer modelling
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	Engineering with Computers
container_volume	39
container_issue	6
container_start_page	3791
publishDate	2023
institution	Swansea University
issn	0177-0667 1435-5663
doi_str_mv	10.1007/s00366-023-01812-z
publisher	Springer Science and Business Media LLC
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 novel approach capable of predicting an appropriate spacing function that can be used to generate a near-optimal mesh suitable for simulation. The main objective is to make use of the large number of simulations that are nowadays available, and to alleviate the time-consuming mesh generation stage by minimising human intervention. For a given simulation, a technique to produce a set of point sources that leads to a mesh capable of capturing all the features of the solution is proposed. In addition, a method to combine all sets of sources for the simulations available is devised. The global set of sources is used to train a neural network that, for some design parameters (e.g., flow conditions, geometry), predicts the characteristics of the sources. Numerical examples, in the context of three dimensional inviscid compressible flows, are considered to demonstrate the potential of the proposed approach. It is shown that accurate predictions of the required spacing function can be produced, even with reduced training datasets. In addition, the predicted near-optimal meshes are utilised to compute flow solutions, and the results show that the computed aerodynamic coefficients are within the required accuracy for the aerospace industry. An analysis is also presented to demonstrate that the proposed method lies in the category of green AI research, meaning that computational resources and time are substantially reduced with this approach, when compared to current practice in industry.
published_date	2023-12-01T12:25:32Z
_version_	1801110822562299904
score	11.016235

Meshing using neural networks for improving the efficiency of computer modelling

Similar Items