No Cover Image

E-Thesis 448 views 308 downloads

Non-intrusive reduced order modelling for aerodynamic applications / KENSLEY BALLA

Swansea University Author: KENSLEY BALLA

DOI (Published version): 10.23889/SUthesis.58705

Abstract

During the design and optimisation of aerodynamic components, the simulations to be performed involve a large number of parameters related to the geometry and flow conditions. In this scenario, the simulation of all possible configurations is not af-fordable. To overcome this problem, the present wo...

Full description

Published: Swansea 2021
Institution: Swansea University
Degree level: Doctoral
Degree name: Ph.D
Supervisor: Hassan, Oubay ; Sevilla, Ruben ; Morgan, Kenneth
URI: https://cronfa.swan.ac.uk/Record/cronfa58705
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-11-19T10:12:09Z
last_indexed 2021-11-20T04:24:37Z
id cronfa58705
recordtype RisThesis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-11-19T10:36:44.9002484</datestamp><bib-version>v2</bib-version><id>58705</id><entry>2021-11-19</entry><title>Non-intrusive reduced order modelling for aerodynamic applications</title><swanseaauthors><author><sid>4eb728e456d3c9801b6f28453d57122e</sid><firstname>KENSLEY</firstname><surname>BALLA</surname><name>KENSLEY BALLA</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-11-19</date><abstract>During the design and optimisation of aerodynamic components, the simulations to be performed involve a large number of parameters related to the geometry and flow conditions. In this scenario, the simulation of all possible configurations is not af-fordable. To overcome this problem, the present work proposes a novel multi-output neural network (NN) for the prediction of aerodynamic coefficients of aerofoils and wings using compressible flow data. Contrary to existing NNs that are designed to predict aerodynamic quantities of interest, the proposed network considers as output the pressure or stresses at a number of selected points on the aerodynamic surface. The proposed approach is compared against the more traditional networks where the aero-dynamic coefficients are directly the outputs of the network. Furthermore, a detailed comparison of the proposed NN against the popular proper orthogonal decomposi-tion (POD) method is presented. The numerical results, involving high dimensional problems with flow and geometric parameters, show the benefits of the proposed ap-proach.The proposed NN is used to accelerate the evaluation of the objective function in an inverse aerodynamic shape design problem. The optimisation algorithm uses the gradient-free modified cuckoo search method. Applications in two and three dimen-sions are shown, demonstrating the potential of the proposed framework in the con-text of both optimisation and inverse design problems. The performance of the pro-posed optimisation framework is also compared against existing frameworks where the more traditional NNs are employed.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>neural network, proper orthogonal decomposition, reduced order model,geometric parameters,NURBS, shape optimisation, inverse design</keywords><publishedDay>19</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-11-19</publishedDate><doi>10.23889/SUthesis.58705</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Hassan, Oubay ; Sevilla, Ruben ; Morgan, Kenneth</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><apcterm/><lastEdited>2021-11-19T10:36:44.9002484</lastEdited><Created>2021-11-19T10:06:04.9320343</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Uncategorised</level></path><authors><author><firstname>KENSLEY</firstname><surname>BALLA</surname><order>1</order></author></authors><documents><document><filename>58705__21589__fb38bb828b96444484d6b5e345bb0e3c.pdf</filename><originalFilename>Balla_Kensley_PhD_Thesis_Final_Redacted_Signature.pdf</originalFilename><uploaded>2021-11-19T10:26:56.6306687</uploaded><type>Output</type><contentLength>12159004</contentLength><contentType>application/pdf</contentType><version>E-Thesis &#x2013; open access</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: The author, Kensley Balla, 2021.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2021-11-19T10:36:44.9002484 v2 58705 2021-11-19 Non-intrusive reduced order modelling for aerodynamic applications 4eb728e456d3c9801b6f28453d57122e KENSLEY BALLA KENSLEY BALLA true false 2021-11-19 During the design and optimisation of aerodynamic components, the simulations to be performed involve a large number of parameters related to the geometry and flow conditions. In this scenario, the simulation of all possible configurations is not af-fordable. To overcome this problem, the present work proposes a novel multi-output neural network (NN) for the prediction of aerodynamic coefficients of aerofoils and wings using compressible flow data. Contrary to existing NNs that are designed to predict aerodynamic quantities of interest, the proposed network considers as output the pressure or stresses at a number of selected points on the aerodynamic surface. The proposed approach is compared against the more traditional networks where the aero-dynamic coefficients are directly the outputs of the network. Furthermore, a detailed comparison of the proposed NN against the popular proper orthogonal decomposi-tion (POD) method is presented. The numerical results, involving high dimensional problems with flow and geometric parameters, show the benefits of the proposed ap-proach.The proposed NN is used to accelerate the evaluation of the objective function in an inverse aerodynamic shape design problem. The optimisation algorithm uses the gradient-free modified cuckoo search method. Applications in two and three dimen-sions are shown, demonstrating the potential of the proposed framework in the con-text of both optimisation and inverse design problems. The performance of the pro-posed optimisation framework is also compared against existing frameworks where the more traditional NNs are employed. E-Thesis Swansea neural network, proper orthogonal decomposition, reduced order model,geometric parameters,NURBS, shape optimisation, inverse design 19 11 2021 2021-11-19 10.23889/SUthesis.58705 COLLEGE NANME COLLEGE CODE Swansea University Hassan, Oubay ; Sevilla, Ruben ; Morgan, Kenneth Doctoral Ph.D 2021-11-19T10:36:44.9002484 2021-11-19T10:06:04.9320343 Faculty of Science and Engineering School of Engineering and Applied Sciences - Uncategorised KENSLEY BALLA 1 58705__21589__fb38bb828b96444484d6b5e345bb0e3c.pdf Balla_Kensley_PhD_Thesis_Final_Redacted_Signature.pdf 2021-11-19T10:26:56.6306687 Output 12159004 application/pdf E-Thesis – open access true Copyright: The author, Kensley Balla, 2021. true eng
title Non-intrusive reduced order modelling for aerodynamic applications
spellingShingle Non-intrusive reduced order modelling for aerodynamic applications
KENSLEY BALLA
title_short Non-intrusive reduced order modelling for aerodynamic applications
title_full Non-intrusive reduced order modelling for aerodynamic applications
title_fullStr Non-intrusive reduced order modelling for aerodynamic applications
title_full_unstemmed Non-intrusive reduced order modelling for aerodynamic applications
title_sort Non-intrusive reduced order modelling for aerodynamic applications
author_id_str_mv 4eb728e456d3c9801b6f28453d57122e
author_id_fullname_str_mv 4eb728e456d3c9801b6f28453d57122e_***_KENSLEY BALLA
author KENSLEY BALLA
author2 KENSLEY BALLA
format E-Thesis
publishDate 2021
institution Swansea University
doi_str_mv 10.23889/SUthesis.58705
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 Engineering and Applied Sciences - Uncategorised{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Uncategorised
document_store_str 1
active_str 0
description During the design and optimisation of aerodynamic components, the simulations to be performed involve a large number of parameters related to the geometry and flow conditions. In this scenario, the simulation of all possible configurations is not af-fordable. To overcome this problem, the present work proposes a novel multi-output neural network (NN) for the prediction of aerodynamic coefficients of aerofoils and wings using compressible flow data. Contrary to existing NNs that are designed to predict aerodynamic quantities of interest, the proposed network considers as output the pressure or stresses at a number of selected points on the aerodynamic surface. The proposed approach is compared against the more traditional networks where the aero-dynamic coefficients are directly the outputs of the network. Furthermore, a detailed comparison of the proposed NN against the popular proper orthogonal decomposi-tion (POD) method is presented. The numerical results, involving high dimensional problems with flow and geometric parameters, show the benefits of the proposed ap-proach.The proposed NN is used to accelerate the evaluation of the objective function in an inverse aerodynamic shape design problem. The optimisation algorithm uses the gradient-free modified cuckoo search method. Applications in two and three dimen-sions are shown, demonstrating the potential of the proposed framework in the con-text of both optimisation and inverse design problems. The performance of the pro-posed optimisation framework is also compared against existing frameworks where the more traditional NNs are employed.
published_date 2021-11-19T04:15:26Z
_version_ 1763754038467231744
score 11.012678

Similar Items