No Cover Image

Journal article 207 views 11 downloads

A physics-driven and machine learning-based digital twinning approach to transient thermal systems

Armando Di Meglio, Nicola Massarotti, Perumal Nithiarasu Orcid Logo

International Journal of Numerical Methods for Heat and Fluid Flow

Swansea University Author: Perumal Nithiarasu Orcid Logo

  • 65598.VoR.pdf

    PDF | Version of Record

    ©Armando Di Meglio, Nicola Massarotti and Perumal Nithiarasu. This article is published under the Creative Commons Attribution (CC BY 4.0) licence.

    Download (3.86MB)

Check full text

DOI (Published version): 10.1108/hff-10-2023-0616

Abstract

Purpose - In this study, we propose a novel digital twinning approach specifically designed for controlling transient thermal systems. The primary objective is to harness the combined power of Deep Learning (DL) and Physics-Based Methods (PBM) to create an active virtual replica of the physical syst...

Full description

Published in: International Journal of Numerical Methods for Heat and Fluid Flow
ISSN: 0961-5539 0961-5539
Published: Emerald 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa65598
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-02-08T17:39:51Z
last_indexed 2024-02-08T17:39:51Z
id cronfa65598
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>65598</id><entry>2024-02-08</entry><title>A physics-driven and machine learning-based digital twinning approach to transient thermal systems</title><swanseaauthors><author><sid>3b28bf59358fc2b9bd9a46897dbfc92d</sid><ORCID>0000-0002-4901-2980</ORCID><firstname>Perumal</firstname><surname>Nithiarasu</surname><name>Perumal Nithiarasu</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-02-08</date><deptcode>ACEM</deptcode><abstract>Purpose - In this study, we propose a novel digital twinning approach specifically designed for controlling transient thermal systems. The primary objective is to harness the combined power of Deep Learning (DL) and Physics-Based Methods (PBM) to create an active virtual replica of the physical system.Design/methodology/approach - To achieve this goal, we introduce a Deep Neural Network (DNN) as the digital twin and a Finite Element (FE) model as the physical system. This integrated approach is employed to address the challenges of controlling an unsteady heat transfer problem with an integrated feedback loop.Findings - The results of our study demonstrate the effectiveness of the proposed digital twinning approach in regulating the maximum temperature within the system under varying and unsteady heat flux conditions. The DNN, trained on stationary data, plays a crucial role in determining the heat transfer coefficients necessary to maintain temperatures below a defined threshold value, such as the material’s melting point. The system is successfully controlled in 1D, 2D, and 3D case studies. However, careful evaluations should be conducted if such a training approach, based on steady-state data, is applied to completely different transient heat transfer problems.Originality/Value - The present work represents one of the first examples of a comprehensive digital twinning approach to transient thermal systems, driven by data. One of the noteworthy features of this approach is its robustness. Adopting a training based on dimensionless data, the approach can seamlessly accommodate changes in thermal capacity and thermal conductivity without the need for retraining.</abstract><type>Journal Article</type><journal>International Journal of Numerical Methods for Heat and Fluid Flow</journal><volume>0</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Emerald</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0961-5539</issnPrint><issnElectronic>0961-5539</issnElectronic><keywords>Digital Twinning; Digital Twin (DT); Transient Heat Transfer; FEM; Deep Learning; Machine Learning; Data Exchange</keywords><publishedDay>30</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-04-30</publishedDate><doi>10.1108/hff-10-2023-0616</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/><projectreference/><lastEdited>2024-06-06T15:33:35.0512986</lastEdited><Created>2024-02-08T17:29:44.5509271</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering</level></path><authors><author><firstname>Armando Di</firstname><surname>Meglio</surname><order>1</order></author><author><firstname>Nicola</firstname><surname>Massarotti</surname><order>2</order></author><author><firstname>Perumal</firstname><surname>Nithiarasu</surname><orcid>0000-0002-4901-2980</orcid><order>3</order></author></authors><documents><document><filename>65598__30555__0d702231ad7c46c1b7520e611e69f9e1.pdf</filename><originalFilename>65598.VoR.pdf</originalFilename><uploaded>2024-06-06T15:31:44.1521072</uploaded><type>Output</type><contentLength>4050000</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>©Armando Di Meglio, Nicola Massarotti and Perumal Nithiarasu. This article is published under the Creative Commons Attribution (CC BY 4.0) licence.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licences/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 65598 2024-02-08 A physics-driven and machine learning-based digital twinning approach to transient thermal systems 3b28bf59358fc2b9bd9a46897dbfc92d 0000-0002-4901-2980 Perumal Nithiarasu Perumal Nithiarasu true false 2024-02-08 ACEM Purpose - In this study, we propose a novel digital twinning approach specifically designed for controlling transient thermal systems. The primary objective is to harness the combined power of Deep Learning (DL) and Physics-Based Methods (PBM) to create an active virtual replica of the physical system.Design/methodology/approach - To achieve this goal, we introduce a Deep Neural Network (DNN) as the digital twin and a Finite Element (FE) model as the physical system. This integrated approach is employed to address the challenges of controlling an unsteady heat transfer problem with an integrated feedback loop.Findings - The results of our study demonstrate the effectiveness of the proposed digital twinning approach in regulating the maximum temperature within the system under varying and unsteady heat flux conditions. The DNN, trained on stationary data, plays a crucial role in determining the heat transfer coefficients necessary to maintain temperatures below a defined threshold value, such as the material’s melting point. The system is successfully controlled in 1D, 2D, and 3D case studies. However, careful evaluations should be conducted if such a training approach, based on steady-state data, is applied to completely different transient heat transfer problems.Originality/Value - The present work represents one of the first examples of a comprehensive digital twinning approach to transient thermal systems, driven by data. One of the noteworthy features of this approach is its robustness. Adopting a training based on dimensionless data, the approach can seamlessly accommodate changes in thermal capacity and thermal conductivity without the need for retraining. Journal Article International Journal of Numerical Methods for Heat and Fluid Flow 0 Emerald 0961-5539 0961-5539 Digital Twinning; Digital Twin (DT); Transient Heat Transfer; FEM; Deep Learning; Machine Learning; Data Exchange 30 4 2024 2024-04-30 10.1108/hff-10-2023-0616 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University 2024-06-06T15:33:35.0512986 2024-02-08T17:29:44.5509271 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering Armando Di Meglio 1 Nicola Massarotti 2 Perumal Nithiarasu 0000-0002-4901-2980 3 65598__30555__0d702231ad7c46c1b7520e611e69f9e1.pdf 65598.VoR.pdf 2024-06-06T15:31:44.1521072 Output 4050000 application/pdf Version of Record true ©Armando Di Meglio, Nicola Massarotti and Perumal Nithiarasu. This article is published under the Creative Commons Attribution (CC BY 4.0) licence. true eng http://creativecommons.org/licences/by/4.0/
title A physics-driven and machine learning-based digital twinning approach to transient thermal systems
spellingShingle A physics-driven and machine learning-based digital twinning approach to transient thermal systems
Perumal Nithiarasu
title_short A physics-driven and machine learning-based digital twinning approach to transient thermal systems
title_full A physics-driven and machine learning-based digital twinning approach to transient thermal systems
title_fullStr A physics-driven and machine learning-based digital twinning approach to transient thermal systems
title_full_unstemmed A physics-driven and machine learning-based digital twinning approach to transient thermal systems
title_sort A physics-driven and machine learning-based digital twinning approach to transient thermal systems
author_id_str_mv 3b28bf59358fc2b9bd9a46897dbfc92d
author_id_fullname_str_mv 3b28bf59358fc2b9bd9a46897dbfc92d_***_Perumal Nithiarasu
author Perumal Nithiarasu
author2 Armando Di Meglio
Nicola Massarotti
Perumal Nithiarasu
format Journal article
container_title International Journal of Numerical Methods for Heat and Fluid Flow
container_volume 0
publishDate 2024
institution Swansea University
issn 0961-5539
0961-5539
doi_str_mv 10.1108/hff-10-2023-0616
publisher Emerald
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 - Electronic and Electrical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering
document_store_str 1
active_str 0
description Purpose - In this study, we propose a novel digital twinning approach specifically designed for controlling transient thermal systems. The primary objective is to harness the combined power of Deep Learning (DL) and Physics-Based Methods (PBM) to create an active virtual replica of the physical system.Design/methodology/approach - To achieve this goal, we introduce a Deep Neural Network (DNN) as the digital twin and a Finite Element (FE) model as the physical system. This integrated approach is employed to address the challenges of controlling an unsteady heat transfer problem with an integrated feedback loop.Findings - The results of our study demonstrate the effectiveness of the proposed digital twinning approach in regulating the maximum temperature within the system under varying and unsteady heat flux conditions. The DNN, trained on stationary data, plays a crucial role in determining the heat transfer coefficients necessary to maintain temperatures below a defined threshold value, such as the material’s melting point. The system is successfully controlled in 1D, 2D, and 3D case studies. However, careful evaluations should be conducted if such a training approach, based on steady-state data, is applied to completely different transient heat transfer problems.Originality/Value - The present work represents one of the first examples of a comprehensive digital twinning approach to transient thermal systems, driven by data. One of the noteworthy features of this approach is its robustness. Adopting a training based on dimensionless data, the approach can seamlessly accommodate changes in thermal capacity and thermal conductivity without the need for retraining.
published_date 2024-04-30T15:33:35Z
_version_ 1801122654009163776
score 11.016593

Similar Items