No Cover Image

Journal article 556 views 622 downloads

A reduced order model for turbulent flows in the urban environment using machine learning

Dunhui Xiao Orcid Logo, C.E. Heaney, L. Mottet, F. Fang, W. Lin, I.M. Navon, Y. Guo, O.K. Matar, A.G. Robins, C.C. Pain

Building and Environment, Volume: 148, Pages: 323 - 337

Swansea University Author: Dunhui Xiao Orcid Logo

  • urban.pdf

    PDF | Accepted Manuscript

    Released under the terms of a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND).

    Download (2.09MB)

Abstract

To help create a comfortable and healthy indoor and outdoor environment in which to live, there is a need to understand turbulent air flows within the urban environment. To this end, building on a previously reported method [1], we develop a fast-running Non-Intrusive Reduced Order Model (NIROM) for...

Full description

Published in: Building and Environment
ISSN: 0360-1323
Published: 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa46445
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2018-12-06T20:27:44Z
last_indexed 2021-01-16T04:07:07Z
id cronfa46445
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-01-15T10:25:10.4900135</datestamp><bib-version>v2</bib-version><id>46445</id><entry>2018-12-06</entry><title>A reduced order model for turbulent flows in the urban environment using machine learning</title><swanseaauthors><author><sid>62c69b98cbcdc9142622d4f398fdab97</sid><ORCID>0000-0003-2461-523X</ORCID><firstname>Dunhui</firstname><surname>Xiao</surname><name>Dunhui Xiao</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2018-12-06</date><deptcode>AERO</deptcode><abstract>To help create a comfortable and healthy indoor and outdoor environment in which to live, there is a need to understand turbulent air flows within the urban environment. To this end, building on a previously reported method [1], we develop a fast-running Non-Intrusive Reduced Order Model (NIROM) for predicting the turbulent air flows found within an urban environment. To resolve larger scale turbulent fluctuations, we employ a Large Eddy Simulation (LES) model and solve the resulting computational model on unstructured meshes. The objective is to construct a rapid-running NIROM from these results that will have &#x2018;similar&#x2019; dynamics to the original LES model. Based on Proper Orthogonal Decomposition (POD) and machine learning techniques, this Reduced Order Model (ROM) is six orders of magnitude faster than the high-fidelity LES model and we demonstrate how &#x2018;similar&#x2019; it can be to the high-fidelity model by comparing statistical quantities such as the mean flows, Reynolds stresses and probability densities of the velocities. We also include validation of the high-fidelity model against data from wind tunnel experiments.This paper represents a key step towards the use of reduced order modelling for operational purposes with the tantalising possibility of it being used in place of Gaussian plume models, and the potential for greatly improved model fidelity and confidence.</abstract><type>Journal Article</type><journal>Building and Environment</journal><volume>148</volume><journalNumber/><paginationStart>323</paginationStart><paginationEnd>337</paginationEnd><publisher/><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0360-1323</issnPrint><issnElectronic/><keywords>Non-intrusive reduced order modelling, Urban flows, Proper orthogonal decomposition, Machine learning, Gaussian process regression, Operational modelling</keywords><publishedDay>15</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-01-15</publishedDate><doi>10.1016/j.buildenv.2018.10.035</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>AERO</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2021-01-15T10:25:10.4900135</lastEdited><Created>2018-12-06T14:51:12.8651530</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering</level></path><authors><author><firstname>Dunhui</firstname><surname>Xiao</surname><orcid>0000-0003-2461-523X</orcid><order>1</order></author><author><firstname>C.E.</firstname><surname>Heaney</surname><order>2</order></author><author><firstname>L.</firstname><surname>Mottet</surname><order>3</order></author><author><firstname>F.</firstname><surname>Fang</surname><order>4</order></author><author><firstname>W.</firstname><surname>Lin</surname><order>5</order></author><author><firstname>I.M.</firstname><surname>Navon</surname><order>6</order></author><author><firstname>Y.</firstname><surname>Guo</surname><order>7</order></author><author><firstname>O.K.</firstname><surname>Matar</surname><order>8</order></author><author><firstname>A.G.</firstname><surname>Robins</surname><order>9</order></author><author><firstname>C.C.</firstname><surname>Pain</surname><order>10</order></author></authors><documents><document><filename>0046445-13122018164928.pdf</filename><originalFilename>urban.pdf</originalFilename><uploaded>2018-12-13T16:49:28.0700000</uploaded><type>Output</type><contentLength>2199396</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2019-11-15T00:00:00.0000000</embargoDate><documentNotes>Released under the terms of a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2021-01-15T10:25:10.4900135 v2 46445 2018-12-06 A reduced order model for turbulent flows in the urban environment using machine learning 62c69b98cbcdc9142622d4f398fdab97 0000-0003-2461-523X Dunhui Xiao Dunhui Xiao true false 2018-12-06 AERO To help create a comfortable and healthy indoor and outdoor environment in which to live, there is a need to understand turbulent air flows within the urban environment. To this end, building on a previously reported method [1], we develop a fast-running Non-Intrusive Reduced Order Model (NIROM) for predicting the turbulent air flows found within an urban environment. To resolve larger scale turbulent fluctuations, we employ a Large Eddy Simulation (LES) model and solve the resulting computational model on unstructured meshes. The objective is to construct a rapid-running NIROM from these results that will have ‘similar’ dynamics to the original LES model. Based on Proper Orthogonal Decomposition (POD) and machine learning techniques, this Reduced Order Model (ROM) is six orders of magnitude faster than the high-fidelity LES model and we demonstrate how ‘similar’ it can be to the high-fidelity model by comparing statistical quantities such as the mean flows, Reynolds stresses and probability densities of the velocities. We also include validation of the high-fidelity model against data from wind tunnel experiments.This paper represents a key step towards the use of reduced order modelling for operational purposes with the tantalising possibility of it being used in place of Gaussian plume models, and the potential for greatly improved model fidelity and confidence. Journal Article Building and Environment 148 323 337 0360-1323 Non-intrusive reduced order modelling, Urban flows, Proper orthogonal decomposition, Machine learning, Gaussian process regression, Operational modelling 15 1 2019 2019-01-15 10.1016/j.buildenv.2018.10.035 COLLEGE NANME Aerospace Engineering COLLEGE CODE AERO Swansea University 2021-01-15T10:25:10.4900135 2018-12-06T14:51:12.8651530 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering Dunhui Xiao 0000-0003-2461-523X 1 C.E. Heaney 2 L. Mottet 3 F. Fang 4 W. Lin 5 I.M. Navon 6 Y. Guo 7 O.K. Matar 8 A.G. Robins 9 C.C. Pain 10 0046445-13122018164928.pdf urban.pdf 2018-12-13T16:49:28.0700000 Output 2199396 application/pdf Accepted Manuscript true 2019-11-15T00:00:00.0000000 Released under the terms of a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND). true eng
title A reduced order model for turbulent flows in the urban environment using machine learning
spellingShingle A reduced order model for turbulent flows in the urban environment using machine learning
Dunhui Xiao
title_short A reduced order model for turbulent flows in the urban environment using machine learning
title_full A reduced order model for turbulent flows in the urban environment using machine learning
title_fullStr A reduced order model for turbulent flows in the urban environment using machine learning
title_full_unstemmed A reduced order model for turbulent flows in the urban environment using machine learning
title_sort A reduced order model for turbulent flows in the urban environment using machine learning
author_id_str_mv 62c69b98cbcdc9142622d4f398fdab97
author_id_fullname_str_mv 62c69b98cbcdc9142622d4f398fdab97_***_Dunhui Xiao
author Dunhui Xiao
author2 Dunhui Xiao
C.E. Heaney
L. Mottet
F. Fang
W. Lin
I.M. Navon
Y. Guo
O.K. Matar
A.G. Robins
C.C. Pain
format Journal article
container_title Building and Environment
container_volume 148
container_start_page 323
publishDate 2019
institution Swansea University
issn 0360-1323
doi_str_mv 10.1016/j.buildenv.2018.10.035
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 - Aerospace Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering
document_store_str 1
active_str 0
description To help create a comfortable and healthy indoor and outdoor environment in which to live, there is a need to understand turbulent air flows within the urban environment. To this end, building on a previously reported method [1], we develop a fast-running Non-Intrusive Reduced Order Model (NIROM) for predicting the turbulent air flows found within an urban environment. To resolve larger scale turbulent fluctuations, we employ a Large Eddy Simulation (LES) model and solve the resulting computational model on unstructured meshes. The objective is to construct a rapid-running NIROM from these results that will have ‘similar’ dynamics to the original LES model. Based on Proper Orthogonal Decomposition (POD) and machine learning techniques, this Reduced Order Model (ROM) is six orders of magnitude faster than the high-fidelity LES model and we demonstrate how ‘similar’ it can be to the high-fidelity model by comparing statistical quantities such as the mean flows, Reynolds stresses and probability densities of the velocities. We also include validation of the high-fidelity model against data from wind tunnel experiments.This paper represents a key step towards the use of reduced order modelling for operational purposes with the tantalising possibility of it being used in place of Gaussian plume models, and the potential for greatly improved model fidelity and confidence.
published_date 2019-01-15T03:58:01Z
_version_ 1763752942130692096
score 10.993396