Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning

GALEANA, DANIELA

doi:10.23889/SUThesis.71082

E-Thesis 64 views 19 downloads

Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning / DANIELA GALEANA

Swansea University Author: DANIELA GALEANA

PDF | E-Thesis – open access

Copyright: the author, Daniela M. Segura Saleana, 2025. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0)
Download (30.29MB)

DOI (Published version): 10.23889/SUThesis.71082

Abstract

In the ﬁeld of energy applied to ﬂuid dynamics, the net power output of a system is dependant upon the thermal and hydraulic behaviour of the ﬂow in interaction with surrounding objects.For cooling systems applications, the interest relies on the understanding and optimisation of the Thermo-Hydrauli...

Full description

Published:	Swansea 2025
Institution:	Swansea University
Degree level:	Doctoral
Degree name:	Ph.D
Supervisor:	Gil, A. J.
URI:	https://cronfa.swan.ac.uk/Record/cronfa71082

first_indexed	2025-12-04T13:45:33Z
last_indexed	2025-12-05T18:13:29Z
id	cronfa71082
recordtype	RisThesis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2025-12-04T13:48:29.4946368</datestamp><bib-version>v2</bib-version><id>71082</id><entry>2025-12-04</entry><title>Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning</title><swanseaauthors><author><sid>c38774f1b65d00746386e8d88bf387b5</sid><firstname>DANIELA</firstname><surname>GALEANA</surname><name>DANIELA GALEANA</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-12-04</date><abstract>In the ﬁeld of energy applied to ﬂuid dynamics, the net power output of a system is dependant upon the thermal and hydraulic behaviour of the ﬂow in interaction with surrounding objects.For cooling systems applications, the interest relies on the understanding and optimisation of the Thermo-Hydraulic Performance (THP) research. The THP optimisation relevant to this research is that of shape parametrisation. It has been demonstrated that utilising a biomimetic geometry on the ﬂuid-facing surface of a pipe, based on the skin of fast sharks,improves hydraulic performance. However, the design of such geometry introduces a number of challenges that need to be addressed. First, the thermal and hydraulic mechanisms of the ﬂow have a coupled nature, with a trade-oﬀ between them leading to a Multi-Objective Optimisation (MOO) problem. Second, the use of Computational Fluid Dynamics (CFD)to analyse the coupled ﬂow behaviour. This is a cost-eﬀective alternative to experimental testing and a favourable tool for geometry parametrisation. However, CFD implies a back-and-forth process between design and modelling over several iterations of shape parameters, which can make the development of optimal geometries highly time-consuming for the required level of accuracy. Therefore, industry demands for increasing levels of accuracy and the need for optimising the design process itself prompts the search for new means to undertake these tasks.In the ambition to address the above challenges within the computational design process, this thesis puts forward a comparative data-driven computational framework with an associated open-source software. The software generates both a database containing CFD high-ﬁdelity models of parametrised geometries, as well as surrogate models that are trained with such data to approximate the THP optimisation process. The thesis puts forward three novelties. First, the study of the inﬂuence that simpliﬁed biomimetic geometries have in the coupled thermo-hydraulic behaviour of the ﬂow in pipes. Second, a comparative analysis using alternative Machine Learning (ML) techniques in order to identify the advantages and drawbacks of each algorithm across diﬀerent approaches. The considered ML methods are Radial Basis Function (RBF) interpolation, Neural Networks (NN) and Gaussian Processes (GP),with the addition of Proper Orthogonal Decomposition (POD) as a dimensional reduction method prior to the models’ training to potentially ease the computational expense. Third, the framework’s main direction is to use ML algorithms to enrich the search for an optimal geometry within the considered parametric space. The eﬀorts made to reach the objectives of this research have resulted into the open-source software Hammerhead integrated environment for high-ﬁdelity and ML based computational design optimisation. This new framework is developed and implemented using Python3 language, including compatibility with OpenFOAM open-source CFD platform.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>CFD, machine learning, POD, PCA, Gaussian process, neural networks, optimisation, heat transfer, fluid mechanics</keywords><publishedDay>11</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-08-11</publishedDate><doi>10.23889/SUThesis.71082</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Gil, A. J.</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><degreesponsorsfunders>EPSRC</degreesponsorsfunders><apcterm/><funders>EPSRC</funders><projectreference/><lastEdited>2025-12-04T13:48:29.4946368</lastEdited><Created>2025-12-04T13:37:05.7628615</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>DANIELA</firstname><surname>GALEANA</surname><order>1</order></author></authors><documents><document><filename>71082__35762__ed0cef1bd8b94344b2cfb7e6cdfbef41.pdf</filename><originalFilename>2025_Galeana_final.71082.pdf</originalFilename><uploaded>2025-12-04T13:45:02.7334511</uploaded><type>Output</type><contentLength>31759416</contentLength><contentType>application/pdf</contentType><version>E-Thesis – open access</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: the author, Daniela M. Segura Saleana, 2025. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0)</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2025-12-04T13:48:29.4946368 v2 71082 2025-12-04 Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning c38774f1b65d00746386e8d88bf387b5 DANIELA GALEANA DANIELA GALEANA true false 2025-12-04 In the ﬁeld of energy applied to ﬂuid dynamics, the net power output of a system is dependant upon the thermal and hydraulic behaviour of the ﬂow in interaction with surrounding objects.For cooling systems applications, the interest relies on the understanding and optimisation of the Thermo-Hydraulic Performance (THP) research. The THP optimisation relevant to this research is that of shape parametrisation. It has been demonstrated that utilising a biomimetic geometry on the ﬂuid-facing surface of a pipe, based on the skin of fast sharks,improves hydraulic performance. However, the design of such geometry introduces a number of challenges that need to be addressed. First, the thermal and hydraulic mechanisms of the ﬂow have a coupled nature, with a trade-oﬀ between them leading to a Multi-Objective Optimisation (MOO) problem. Second, the use of Computational Fluid Dynamics (CFD)to analyse the coupled ﬂow behaviour. This is a cost-eﬀective alternative to experimental testing and a favourable tool for geometry parametrisation. However, CFD implies a back-and-forth process between design and modelling over several iterations of shape parameters, which can make the development of optimal geometries highly time-consuming for the required level of accuracy. Therefore, industry demands for increasing levels of accuracy and the need for optimising the design process itself prompts the search for new means to undertake these tasks.In the ambition to address the above challenges within the computational design process, this thesis puts forward a comparative data-driven computational framework with an associated open-source software. The software generates both a database containing CFD high-ﬁdelity models of parametrised geometries, as well as surrogate models that are trained with such data to approximate the THP optimisation process. The thesis puts forward three novelties. First, the study of the inﬂuence that simpliﬁed biomimetic geometries have in the coupled thermo-hydraulic behaviour of the ﬂow in pipes. Second, a comparative analysis using alternative Machine Learning (ML) techniques in order to identify the advantages and drawbacks of each algorithm across diﬀerent approaches. The considered ML methods are Radial Basis Function (RBF) interpolation, Neural Networks (NN) and Gaussian Processes (GP),with the addition of Proper Orthogonal Decomposition (POD) as a dimensional reduction method prior to the models’ training to potentially ease the computational expense. Third, the framework’s main direction is to use ML algorithms to enrich the search for an optimal geometry within the considered parametric space. The eﬀorts made to reach the objectives of this research have resulted into the open-source software Hammerhead integrated environment for high-ﬁdelity and ML based computational design optimisation. This new framework is developed and implemented using Python3 language, including compatibility with OpenFOAM open-source CFD platform. E-Thesis Swansea CFD, machine learning, POD, PCA, Gaussian process, neural networks, optimisation, heat transfer, fluid mechanics 11 8 2025 2025-08-11 10.23889/SUThesis.71082 COLLEGE NANME COLLEGE CODE Swansea University Gil, A. J. Doctoral Ph.D EPSRC EPSRC 2025-12-04T13:48:29.4946368 2025-12-04T13:37:05.7628615 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering DANIELA GALEANA 1 71082__35762__ed0cef1bd8b94344b2cfb7e6cdfbef41.pdf 2025_Galeana_final.71082.pdf 2025-12-04T13:45:02.7334511 Output 31759416 application/pdf E-Thesis – open access true Copyright: the author, Daniela M. Segura Saleana, 2025. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0) true eng https://creativecommons.org/licenses/by/4.0/
title	Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning
spellingShingle	Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning DANIELA GALEANA
title_short	Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning
title_full	Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning
title_fullStr	Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning
title_full_unstemmed	Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning
title_sort	Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning
author_id_str_mv	c38774f1b65d00746386e8d88bf387b5
author_id_fullname_str_mv	c38774f1b65d00746386e8d88bf387b5_***_DANIELA GALEANA
author	DANIELA GALEANA
author2	DANIELA GALEANA
format	E-Thesis
publishDate	2025
institution	Swansea University
doi_str_mv	10.23889/SUThesis.71082
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	In the ﬁeld of energy applied to ﬂuid dynamics, the net power output of a system is dependant upon the thermal and hydraulic behaviour of the ﬂow in interaction with surrounding objects.For cooling systems applications, the interest relies on the understanding and optimisation of the Thermo-Hydraulic Performance (THP) research. The THP optimisation relevant to this research is that of shape parametrisation. It has been demonstrated that utilising a biomimetic geometry on the ﬂuid-facing surface of a pipe, based on the skin of fast sharks,improves hydraulic performance. However, the design of such geometry introduces a number of challenges that need to be addressed. First, the thermal and hydraulic mechanisms of the ﬂow have a coupled nature, with a trade-oﬀ between them leading to a Multi-Objective Optimisation (MOO) problem. Second, the use of Computational Fluid Dynamics (CFD)to analyse the coupled ﬂow behaviour. This is a cost-eﬀective alternative to experimental testing and a favourable tool for geometry parametrisation. However, CFD implies a back-and-forth process between design and modelling over several iterations of shape parameters, which can make the development of optimal geometries highly time-consuming for the required level of accuracy. Therefore, industry demands for increasing levels of accuracy and the need for optimising the design process itself prompts the search for new means to undertake these tasks.In the ambition to address the above challenges within the computational design process, this thesis puts forward a comparative data-driven computational framework with an associated open-source software. The software generates both a database containing CFD high-ﬁdelity models of parametrised geometries, as well as surrogate models that are trained with such data to approximate the THP optimisation process. The thesis puts forward three novelties. First, the study of the inﬂuence that simpliﬁed biomimetic geometries have in the coupled thermo-hydraulic behaviour of the ﬂow in pipes. Second, a comparative analysis using alternative Machine Learning (ML) techniques in order to identify the advantages and drawbacks of each algorithm across diﬀerent approaches. The considered ML methods are Radial Basis Function (RBF) interpolation, Neural Networks (NN) and Gaussian Processes (GP),with the addition of Proper Orthogonal Decomposition (POD) as a dimensional reduction method prior to the models’ training to potentially ease the computational expense. Third, the framework’s main direction is to use ML algorithms to enrich the search for an optimal geometry within the considered parametric space. The eﬀorts made to reach the objectives of this research have resulted into the open-source software Hammerhead integrated environment for high-ﬁdelity and ML based computational design optimisation. This new framework is developed and implemented using Python3 language, including compatibility with OpenFOAM open-source CFD platform.
published_date	2025-08-11T05:31:03Z
_version_	1851369836681101312
score	11.089572

Computational Heat Transfer Optimisation in Nuclear Fusion Reactors Using Data-Driven Machine Learning / DANIELA GALEANA

Similar Items