본문

서브메뉴

Overcoming Small Datasets in Machine Learning Studies of Multi-Physics Flows in Propulsion.
Overcoming Small Datasets in Machine Learning Studies of Multi-Physics Flows in Propulsion.

상세정보

자료유형  
 학위논문
Control Number  
0017162986
International Standard Book Number  
9798384337959
Dewey Decimal Classification Number  
530
Main Entry-Personal Name  
Chung, Wai Tong.
Publication, Distribution, etc. (Imprint  
[S.l.] : Stanford University., 2024
Publication, Distribution, etc. (Imprint  
Ann Arbor : ProQuest Dissertations & Theses, 2024
Physical Description  
182 p.
General Note  
Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
General Note  
Advisor: Ihme, Matthias.
Dissertation Note  
Thesis (Ph.D.)--Stanford University, 2024.
Summary, Etc.  
요약While machine learning (ML) methods can offer numerous opportunities in modeling multi-physics flows, these approaches often rely on the availability of large datasets for generating reliable predictions. This can be challenging for propulsion applications, especially since data generated by industrial sensors, experiments, and numerical simulations of flow phenomena in propulsion systems can be challenging to collect.In this dissertation, we directly address current gaps in data availability by developing a 2.2 TB ML dataset from 34 high-fidelity direct numerical simulations (DNS) of turbulent flows. We employ this data for benchmarking super-resolution of turbulent flows, and provide insights into the role of different deep learning designs and computational scale in a popular ML application within multi-physics flows.To address issues in accessing data from relatively under-explored flow configurations (e.g., real, hypersonic, and multiphase fluids) in propulsion systems, we investigate opportunities offered by linear regression and random forest models in modeling subgrid-scale (SGS) closure on small turbulent transcritical DNS dataset. Through a priorianalysis, interpretable metrics from random forest models, along with weights within linear regressors, are shown to assist in discovering analytical expressions for modeling SGS stresses and a closure term that arises from a real-fluid equation-of-state.To ameliorate spurious errors that can arise when integrating insufficiently trained ML models within multi-physics flow solvers, we develop a strategy involving an MLbased classifier that assigns three different combustion models of varying fidelity and cost within a shared simulation domain. Results from a posteriorisimulations show that this data-assisted framework demonstrates promise as a tool for controlling the fidelity-cost trade-off in numerical multi-physics flow simulations.Finally, we investigate the benefits of combining domain knowledge with ML by integrating a deep learning model with a stochastic differential equation for predicting the spatio-temporal behavior of laser ignition kernels with sparse ensemble data of a model rocket combustor. Results show that this hybrid reduced-order model can predict dominant ignition modes observed from corresponding experimental measurements, and generate spatially resolved ignition probability, at lower costs than high-fidelity turbulent reacting flow simulations approaches.Overall, the efforts within this dissertation contribute towards overcoming data limitations in ML-based modeling within science and engineering, specifically in the context of multi-physics flows found in propulsion systems.
Subject Added Entry-Topical Term  
Physics.
Subject Added Entry-Topical Term  
Viscosity.
Subject Added Entry-Topical Term  
Mathematical models.
Subject Added Entry-Topical Term  
Neural networks.
Subject Added Entry-Topical Term  
Energy.
Subject Added Entry-Topical Term  
Reynolds number.
Subject Added Entry-Topical Term  
Fluid mechanics.
Added Entry-Corporate Name  
Stanford University.
Host Item Entry  
Dissertations Abstracts International. 86-03B.
Electronic Location and Access  
로그인을 한후 보실 수 있는 자료입니다.
Control Number  
joongbu:655421

MARC

 008250224s2024        us  ||||||||||||||c||eng  d
■001000017162986
■00520250211152120
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384337959
■035    ▼a(MiAaPQ)AAI31460380
■035    ▼a(MiAaPQ)Stanfordxw487vj6602
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a530
■1001  ▼aChung,  Wai  Tong.
■24510▼aOvercoming  Small  Datasets  in  Machine  Learning  Studies  of  Multi-Physics  Flows  in  Propulsion.
■260    ▼a[S.l.]▼bStanford  University.  ▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a182  p.
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-03,  Section:  B.
■500    ▼aAdvisor:  Ihme,  Matthias.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2024.
■520    ▼aWhile  machine  learning  (ML)  methods  can  offer  numerous  opportunities  in  modeling  multi-physics  flows,  these  approaches  often  rely  on  the  availability  of  large  datasets  for  generating  reliable  predictions.  This  can  be  challenging  for  propulsion  applications,  especially  since  data  generated  by  industrial  sensors,  experiments,  and  numerical  simulations  of  flow  phenomena  in  propulsion  systems  can  be  challenging  to  collect.In  this  dissertation,  we  directly  address  current  gaps  in  data  availability  by  developing  a  2.2  TB  ML  dataset  from  34  high-fidelity  direct  numerical  simulations  (DNS)  of  turbulent  flows.  We  employ  this  data  for  benchmarking  super-resolution  of  turbulent  flows,  and  provide  insights  into  the  role  of  different  deep  learning  designs  and  computational  scale  in  a  popular  ML  application  within  multi-physics  flows.To  address  issues  in  accessing  data  from  relatively  under-explored  flow  configurations  (e.g.,  real,  hypersonic,  and  multiphase  fluids)  in  propulsion  systems,  we  investigate  opportunities  offered  by  linear  regression  and  random  forest  models  in  modeling  subgrid-scale  (SGS)  closure  on  small  turbulent  transcritical  DNS  dataset.  Through  a  priorianalysis,  interpretable  metrics  from  random  forest  models,  along  with  weights  within  linear  regressors,  are  shown  to  assist  in  discovering  analytical  expressions  for  modeling  SGS  stresses  and  a  closure  term  that  arises  from  a  real-fluid  equation-of-state.To  ameliorate  spurious  errors  that  can  arise  when  integrating  insufficiently  trained  ML  models  within  multi-physics  flow  solvers,  we  develop  a  strategy  involving  an  MLbased  classifier  that  assigns  three  different  combustion  models  of  varying  fidelity  and  cost  within  a  shared  simulation  domain.  Results  from  a  posteriorisimulations  show  that  this  data-assisted  framework  demonstrates  promise  as  a  tool  for  controlling  the  fidelity-cost  trade-off  in  numerical  multi-physics  flow  simulations.Finally,  we  investigate  the  benefits  of  combining  domain  knowledge  with  ML  by  integrating  a  deep  learning  model  with  a  stochastic  differential  equation  for  predicting  the  spatio-temporal  behavior  of  laser  ignition  kernels  with  sparse  ensemble  data  of  a  model  rocket  combustor.  Results  show  that  this  hybrid  reduced-order  model  can  predict  dominant  ignition  modes  observed  from  corresponding  experimental  measurements,  and  generate  spatially  resolved  ignition  probability,  at  lower  costs  than  high-fidelity  turbulent  reacting  flow  simulations  approaches.Overall,  the  efforts  within  this  dissertation  contribute  towards  overcoming  data  limitations  in  ML-based  modeling  within  science  and  engineering,  specifically  in  the  context  of  multi-physics  flows  found  in  propulsion  systems.
■590    ▼aSchool  code:  0212.
■650  4▼aPhysics.
■650  4▼aViscosity.
■650  4▼aMathematical  models.
■650  4▼aNeural  networks.
■650  4▼aEnergy.
■650  4▼aReynolds  number.
■650  4▼aFluid  mechanics.
■690    ▼a0791
■690    ▼a0605
■690    ▼a0800
■690    ▼a0204
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g86-03B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162986▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    New Books MORE
    Related books MORE
    최근 3년간 통계입니다.

    detalle info

    • Reserva
    • 캠퍼스간 도서대출
    • 서가에 없는 책 신고
    • Mi carpeta
    Material
    número de libro número de llamada Ubicación estado Prestar info
    TQ0031443 T   원문자료 열람가능/출력가능 열람가능/출력가능
    마이폴더 부재도서신고

    * Las reservas están disponibles en el libro de préstamos. Para hacer reservaciones, haga clic en el botón de reserva

    해당 도서를 다른 이용자가 함께 대출한 도서

    Related books

    Related Popular Books

    도서위치