No Cover Image

E-Thesis 602 views 182 downloads

Reduced Order Modelling of Hydraulic Valves / PETER HALL

Swansea University Author: PETER HALL

DOI (Published version): 10.23889/SUthesis.63612

Abstract

There is a need for accurate models of small and highly dynamic one-way valves such as those found in engine oil systems. Such reduced order models can then be included in larger oil system models that are too complex to model at high resolution. Two one-way valves are introduced and analysed using...

Full description

Published: Swansea, Wales, UK 2023
Institution: Swansea University
Degree level: Doctoral
Degree name: EngD
Supervisor: Dettmer, Wulf. and Peric, Djordje.
URI: https://cronfa.swan.ac.uk/Record/cronfa63612
first_indexed 2023-06-08T14:13:05Z
last_indexed 2024-11-15T18:01:57Z
id cronfa63612
recordtype RisThesis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-09-29T10:31:20.7574286</datestamp><bib-version>v2</bib-version><id>63612</id><entry>2023-06-08</entry><title>Reduced Order Modelling of Hydraulic Valves</title><swanseaauthors><author><sid>5006f1942471f4c0750d3f0fc93332e7</sid><firstname>PETER</firstname><surname>HALL</surname><name>PETER HALL</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-06-08</date><abstract>There is a need for accurate models of small and highly dynamic one-way valves such as those found in engine oil systems. Such reduced order models can then be included in larger oil system models that are too complex to model at high resolution. Two one-way valves are introduced and analysed using a fluid structure interaction simulation. The behaviour of the valves is examined, and the resultsgenerated are then used to develop two reduced order methodologies. The first is physics based. It combines physical phenomena and steady state simulation results to build up an accurate valve model. This model provides good results but is limited by the applicability of steady state simulations to dynamic behaviour, which is itself dependent on valve geometry and fluid properties. The second approach is based on a type of continuous-time recurrent neural network. This allows training on fluid structure interaction simulations with no need for physical insight. The network is trained directly on the dynamic behaviour and accurately reproduces it. Training methods are discussed. A multiple particle swarm methodology and in situ training technique is presented. The neural network-based model is applied to a more complex valve. Network architecture and size are investigated. A comparison is done over a range of time step sizes. Finally, an example workflow is given presenting the steps to train a neural network and use the resulting reduced order model within a larger oil system model.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea, Wales, UK</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Reduced order modelling, neural network, hydraulic value, fluid structure interaction</keywords><publishedDay>22</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-05-22</publishedDate><doi>10.23889/SUthesis.63612</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Dettmer, Wulf. and Peric, Djordje.</supervisor><degreelevel>Doctoral</degreelevel><degreename>EngD</degreename><degreesponsorsfunders>M2A, Schaeffler</degreesponsorsfunders><apcterm/><funders/><projectreference/><lastEdited>2023-09-29T10:31:20.7574286</lastEdited><Created>2023-06-08T15:06:44.7634307</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Materials Science and Engineering</level></path><authors><author><firstname>PETER</firstname><surname>HALL</surname><order>1</order></author></authors><documents><document><filename>63612__27766__2b54739418f74c75b97457d8b458ee09.pdf</filename><originalFilename>2023_Hall_P.final.63612.pdf</originalFilename><uploaded>2023-06-08T15:13:24.3027277</uploaded><type>Output</type><contentLength>13395565</contentLength><contentType>application/pdf</contentType><version>E-Thesis &#x2013; open access</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: The Author, Peter Hall, 2023.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2023-09-29T10:31:20.7574286 v2 63612 2023-06-08 Reduced Order Modelling of Hydraulic Valves 5006f1942471f4c0750d3f0fc93332e7 PETER HALL PETER HALL true false 2023-06-08 There is a need for accurate models of small and highly dynamic one-way valves such as those found in engine oil systems. Such reduced order models can then be included in larger oil system models that are too complex to model at high resolution. Two one-way valves are introduced and analysed using a fluid structure interaction simulation. The behaviour of the valves is examined, and the resultsgenerated are then used to develop two reduced order methodologies. The first is physics based. It combines physical phenomena and steady state simulation results to build up an accurate valve model. This model provides good results but is limited by the applicability of steady state simulations to dynamic behaviour, which is itself dependent on valve geometry and fluid properties. The second approach is based on a type of continuous-time recurrent neural network. This allows training on fluid structure interaction simulations with no need for physical insight. The network is trained directly on the dynamic behaviour and accurately reproduces it. Training methods are discussed. A multiple particle swarm methodology and in situ training technique is presented. The neural network-based model is applied to a more complex valve. Network architecture and size are investigated. A comparison is done over a range of time step sizes. Finally, an example workflow is given presenting the steps to train a neural network and use the resulting reduced order model within a larger oil system model. E-Thesis Swansea, Wales, UK Reduced order modelling, neural network, hydraulic value, fluid structure interaction 22 5 2023 2023-05-22 10.23889/SUthesis.63612 COLLEGE NANME COLLEGE CODE Swansea University Dettmer, Wulf. and Peric, Djordje. Doctoral EngD M2A, Schaeffler 2023-09-29T10:31:20.7574286 2023-06-08T15:06:44.7634307 Faculty of Science and Engineering School of Engineering and Applied Sciences - Materials Science and Engineering PETER HALL 1 63612__27766__2b54739418f74c75b97457d8b458ee09.pdf 2023_Hall_P.final.63612.pdf 2023-06-08T15:13:24.3027277 Output 13395565 application/pdf E-Thesis – open access true Copyright: The Author, Peter Hall, 2023. true eng
title Reduced Order Modelling of Hydraulic Valves
spellingShingle Reduced Order Modelling of Hydraulic Valves
PETER HALL
title_short Reduced Order Modelling of Hydraulic Valves
title_full Reduced Order Modelling of Hydraulic Valves
title_fullStr Reduced Order Modelling of Hydraulic Valves
title_full_unstemmed Reduced Order Modelling of Hydraulic Valves
title_sort Reduced Order Modelling of Hydraulic Valves
author_id_str_mv 5006f1942471f4c0750d3f0fc93332e7
author_id_fullname_str_mv 5006f1942471f4c0750d3f0fc93332e7_***_PETER HALL
author PETER HALL
author2 PETER HALL
format E-Thesis
publishDate 2023
institution Swansea University
doi_str_mv 10.23889/SUthesis.63612
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 - Materials Science and Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Materials Science and Engineering
document_store_str 1
active_str 0
description There is a need for accurate models of small and highly dynamic one-way valves such as those found in engine oil systems. Such reduced order models can then be included in larger oil system models that are too complex to model at high resolution. Two one-way valves are introduced and analysed using a fluid structure interaction simulation. The behaviour of the valves is examined, and the resultsgenerated are then used to develop two reduced order methodologies. The first is physics based. It combines physical phenomena and steady state simulation results to build up an accurate valve model. This model provides good results but is limited by the applicability of steady state simulations to dynamic behaviour, which is itself dependent on valve geometry and fluid properties. The second approach is based on a type of continuous-time recurrent neural network. This allows training on fluid structure interaction simulations with no need for physical insight. The network is trained directly on the dynamic behaviour and accurately reproduces it. Training methods are discussed. A multiple particle swarm methodology and in situ training technique is presented. The neural network-based model is applied to a more complex valve. Network architecture and size are investigated. A comparison is done over a range of time step sizes. Finally, an example workflow is given presenting the steps to train a neural network and use the resulting reduced order model within a larger oil system model.
published_date 2023-05-22T12:54:51Z
_version_ 1831915636223115264
score 11.059359

Similar Items