No Cover Image

E-Thesis 119 views

Data-driven reduced order modelling based on deep learning / RUI FU

Swansea University Author: RUI FU

  • E-Thesis under embargo until: 3rd July 2029

DOI (Published version): 10.23889/SUThesis.67587

Abstract

Reduced Order Modelling (ROM) has become a powerful tool in computational simulations, especially for complex fluid dynamics. ROM-based models (ROMs) offer significant reductions in computational cost while maintaining acceptable accuracy. These models rely on dimensional reduction to simplify complex...

Full description

Published: Swansea University, Wales, UK 2024
Institution: Swansea University
Degree level: Doctoral
Degree name: Ph.D
Supervisor: Feng, Y.
URI: https://cronfa.swan.ac.uk/Record/cronfa67587
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-09-05T10:35:55Z
last_indexed 2024-09-05T10:35:55Z
id cronfa67587
recordtype RisThesis
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>67587</id><entry>2024-09-05</entry><title>Data-driven reduced order modelling based on deep learning</title><swanseaauthors><author><sid>640d89222f17fa0ffa336e58fdae386c</sid><firstname>RUI</firstname><surname>FU</surname><name>RUI FU</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-09-05</date><abstract>Reduced Order Modelling (ROM) has become a powerful tool in computational simulations, especially for complex fluid dynamics. ROM-based models (ROMs) offer significant reductions in computational cost while maintaining acceptable accuracy. These models rely on dimensional reduction to simplify complex dynamic systems into lower-dimensional representations. It is essential for large simulations and real-time analysis when computational efficiency is crucial. The Parametric Reduced Order Models (PROMs) extend the capabilities of traditional ROMs by considering changes in physical parameters or system configurations that affect the variability of dynamic system responses. This parametric feature enables PROMs to adapt to various dynamic environments, enhancing their flexibility and applicability.In recent years, deep learning has performed excellently in handling large datasets and complex systems. Integrating deep learning methods into ROMs and PROMs has opened up new areas for improving the performance and applicability of ROMs and PROMs. With deep learning methods, ROMs are significantly enhanced in robust capabilities for feature extraction, pattern recognition, and the ability to learn complex relationships in data. For PROMs, deep learning helps achieve higher accuracy, better generalisation and faster adaptation to new conditions. In fields such as fluid dynamics and climate modelling, dynamic systems always have significant challenges with their field complexity and high dimensionality. The ROMs/PROMs with deep learning applied in these fields not only enable more efficient computations for simulations but also the extraction of deeper insights from simulation data, enabling improvements in predictive modelling and decision-making. This thesis presents several advancements in the field of Reduced Order Modeling (ROM)for fluid flow problems. The primary contributions are threefold:1. Non-Linear Non-Intrusive ROM(NL-NIROM): A novel nonlinear non-intrusive ROM(NL-NIROM) is introduced for fluid dynamic field time-series prediction, which is based on an Autoencoder network and the self-attention mechanism. Additionally, a linear non-intrusive reduced order model(L-NIROM) is also developed on proper orthogonal decomposition (POD) and self-attention mechanism. The advantage of this NL-NIROM is that it can capture more non-linearity information than POD-based L-NIROM.2. Parametric Non-Linear Non-Intrusive ROM (P-NLNIROM): A new parametric non-linear non-intrusive reduced-order model (P-NLNIROM) for the fluid flow system simulations on different parameter sets is presented. This model is constructed by the Stacked Auto-Encoder(DAE) and Deep Residual Learning Neural network(ResNet). In addition, transfer learning(TL) is employed to extend the prediction range within the parametric space, thereby greatly improving the predictive capabilities of the P-NLNIROM.3. Error Estimate Parametric ROM: Building upon the P-NLNIROM, an error estimate parametric ROM is implemented to correct the predicted simulations caused by P-NLNIROM for higher accuracy and reliability in simulation outputs. To evaluate the effectiveness of this ROM, a numerical experiment on the lock exchange scenarios is presented. It serves as an example case to demonstrate the performance and practical applicability of the error estimate parametric ROM with fluid dynamics simulations.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea University, Wales, UK</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>non-instrusive reduce order modelling, deep learning methods, computational fluid dynamics, N-S equations</keywords><publishedDay>4</publishedDay><publishedMonth>7</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-07-04</publishedDate><doi>10.23889/SUThesis.67587</doi><url/><notes>A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information.</notes><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Feng, Y.</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><degreesponsorsfunders>EPSRC grant: PURIFY (EP/V000756/1)</degreesponsorsfunders><apcterm/><funders>EPSRC grant: PURIFY (EP/V000756/1)</funders><projectreference/><lastEdited>2024-09-05T11:51:40.9052830</lastEdited><Created>2024-09-05T11:21:13.6598978</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>RUI</firstname><surname>FU</surname><order>1</order></author></authors><documents><document><filename>Under embargo</filename><originalFilename>Under embargo</originalFilename><uploaded>2024-09-05T11:32:53.9241619</uploaded><type>Output</type><contentLength>25259644</contentLength><contentType>application/pdf</contentType><version>E-Thesis</version><cronfaStatus>true</cronfaStatus><embargoDate>2029-07-03T00:00:00.0000000</embargoDate><documentNotes>Copyright: The Author, Rui Fu, 2023 CC BY-NC-ND - Distributed under the terms of a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 67587 2024-09-05 Data-driven reduced order modelling based on deep learning 640d89222f17fa0ffa336e58fdae386c RUI FU RUI FU true false 2024-09-05 Reduced Order Modelling (ROM) has become a powerful tool in computational simulations, especially for complex fluid dynamics. ROM-based models (ROMs) offer significant reductions in computational cost while maintaining acceptable accuracy. These models rely on dimensional reduction to simplify complex dynamic systems into lower-dimensional representations. It is essential for large simulations and real-time analysis when computational efficiency is crucial. The Parametric Reduced Order Models (PROMs) extend the capabilities of traditional ROMs by considering changes in physical parameters or system configurations that affect the variability of dynamic system responses. This parametric feature enables PROMs to adapt to various dynamic environments, enhancing their flexibility and applicability.In recent years, deep learning has performed excellently in handling large datasets and complex systems. Integrating deep learning methods into ROMs and PROMs has opened up new areas for improving the performance and applicability of ROMs and PROMs. With deep learning methods, ROMs are significantly enhanced in robust capabilities for feature extraction, pattern recognition, and the ability to learn complex relationships in data. For PROMs, deep learning helps achieve higher accuracy, better generalisation and faster adaptation to new conditions. In fields such as fluid dynamics and climate modelling, dynamic systems always have significant challenges with their field complexity and high dimensionality. The ROMs/PROMs with deep learning applied in these fields not only enable more efficient computations for simulations but also the extraction of deeper insights from simulation data, enabling improvements in predictive modelling and decision-making. This thesis presents several advancements in the field of Reduced Order Modeling (ROM)for fluid flow problems. The primary contributions are threefold:1. Non-Linear Non-Intrusive ROM(NL-NIROM): A novel nonlinear non-intrusive ROM(NL-NIROM) is introduced for fluid dynamic field time-series prediction, which is based on an Autoencoder network and the self-attention mechanism. Additionally, a linear non-intrusive reduced order model(L-NIROM) is also developed on proper orthogonal decomposition (POD) and self-attention mechanism. The advantage of this NL-NIROM is that it can capture more non-linearity information than POD-based L-NIROM.2. Parametric Non-Linear Non-Intrusive ROM (P-NLNIROM): A new parametric non-linear non-intrusive reduced-order model (P-NLNIROM) for the fluid flow system simulations on different parameter sets is presented. This model is constructed by the Stacked Auto-Encoder(DAE) and Deep Residual Learning Neural network(ResNet). In addition, transfer learning(TL) is employed to extend the prediction range within the parametric space, thereby greatly improving the predictive capabilities of the P-NLNIROM.3. Error Estimate Parametric ROM: Building upon the P-NLNIROM, an error estimate parametric ROM is implemented to correct the predicted simulations caused by P-NLNIROM for higher accuracy and reliability in simulation outputs. To evaluate the effectiveness of this ROM, a numerical experiment on the lock exchange scenarios is presented. It serves as an example case to demonstrate the performance and practical applicability of the error estimate parametric ROM with fluid dynamics simulations. E-Thesis Swansea University, Wales, UK non-instrusive reduce order modelling, deep learning methods, computational fluid dynamics, N-S equations 4 7 2024 2024-07-04 10.23889/SUThesis.67587 A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information. COLLEGE NANME COLLEGE CODE Swansea University Feng, Y. Doctoral Ph.D EPSRC grant: PURIFY (EP/V000756/1) EPSRC grant: PURIFY (EP/V000756/1) 2024-09-05T11:51:40.9052830 2024-09-05T11:21:13.6598978 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering RUI FU 1 Under embargo Under embargo 2024-09-05T11:32:53.9241619 Output 25259644 application/pdf E-Thesis true 2029-07-03T00:00:00.0000000 Copyright: The Author, Rui Fu, 2023 CC BY-NC-ND - Distributed under the terms of a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0). true eng https://creativecommons.org/licenses/by-nc-nd/4.0/
title Data-driven reduced order modelling based on deep learning
spellingShingle Data-driven reduced order modelling based on deep learning
RUI FU
title_short Data-driven reduced order modelling based on deep learning
title_full Data-driven reduced order modelling based on deep learning
title_fullStr Data-driven reduced order modelling based on deep learning
title_full_unstemmed Data-driven reduced order modelling based on deep learning
title_sort Data-driven reduced order modelling based on deep learning
author_id_str_mv 640d89222f17fa0ffa336e58fdae386c
author_id_fullname_str_mv 640d89222f17fa0ffa336e58fdae386c_***_RUI FU
author RUI FU
author2 RUI FU
format E-Thesis
publishDate 2024
institution Swansea University
doi_str_mv 10.23889/SUThesis.67587
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 0
active_str 0
description Reduced Order Modelling (ROM) has become a powerful tool in computational simulations, especially for complex fluid dynamics. ROM-based models (ROMs) offer significant reductions in computational cost while maintaining acceptable accuracy. These models rely on dimensional reduction to simplify complex dynamic systems into lower-dimensional representations. It is essential for large simulations and real-time analysis when computational efficiency is crucial. The Parametric Reduced Order Models (PROMs) extend the capabilities of traditional ROMs by considering changes in physical parameters or system configurations that affect the variability of dynamic system responses. This parametric feature enables PROMs to adapt to various dynamic environments, enhancing their flexibility and applicability.In recent years, deep learning has performed excellently in handling large datasets and complex systems. Integrating deep learning methods into ROMs and PROMs has opened up new areas for improving the performance and applicability of ROMs and PROMs. With deep learning methods, ROMs are significantly enhanced in robust capabilities for feature extraction, pattern recognition, and the ability to learn complex relationships in data. For PROMs, deep learning helps achieve higher accuracy, better generalisation and faster adaptation to new conditions. In fields such as fluid dynamics and climate modelling, dynamic systems always have significant challenges with their field complexity and high dimensionality. The ROMs/PROMs with deep learning applied in these fields not only enable more efficient computations for simulations but also the extraction of deeper insights from simulation data, enabling improvements in predictive modelling and decision-making. This thesis presents several advancements in the field of Reduced Order Modeling (ROM)for fluid flow problems. The primary contributions are threefold:1. Non-Linear Non-Intrusive ROM(NL-NIROM): A novel nonlinear non-intrusive ROM(NL-NIROM) is introduced for fluid dynamic field time-series prediction, which is based on an Autoencoder network and the self-attention mechanism. Additionally, a linear non-intrusive reduced order model(L-NIROM) is also developed on proper orthogonal decomposition (POD) and self-attention mechanism. The advantage of this NL-NIROM is that it can capture more non-linearity information than POD-based L-NIROM.2. Parametric Non-Linear Non-Intrusive ROM (P-NLNIROM): A new parametric non-linear non-intrusive reduced-order model (P-NLNIROM) for the fluid flow system simulations on different parameter sets is presented. This model is constructed by the Stacked Auto-Encoder(DAE) and Deep Residual Learning Neural network(ResNet). In addition, transfer learning(TL) is employed to extend the prediction range within the parametric space, thereby greatly improving the predictive capabilities of the P-NLNIROM.3. Error Estimate Parametric ROM: Building upon the P-NLNIROM, an error estimate parametric ROM is implemented to correct the predicted simulations caused by P-NLNIROM for higher accuracy and reliability in simulation outputs. To evaluate the effectiveness of this ROM, a numerical experiment on the lock exchange scenarios is presented. It serves as an example case to demonstrate the performance and practical applicability of the error estimate parametric ROM with fluid dynamics simulations.
published_date 2024-07-04T11:51:41Z
_version_ 1809353016386519040
score 11.033506

Similar Items