본문

서브메뉴

Development and Assessment of Machine Learning Techniques for Non-Intrusive Probabilistic Surrogate Modeling of High-Fidelity Nuclear Reactor Simulations
Development and Assessment of Machine Learning Techniques for Non-Intrusive Probabilistic ...
Development and Assessment of Machine Learning Techniques for Non-Intrusive Probabilistic Surrogate Modeling of High-Fidelity Nuclear Reactor Simulations

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152104
ISBN  
9798382741093
DDC  
539.76
저자명  
LaFleur, Brandon.
서명/저자  
Development and Assessment of Machine Learning Techniques for Non-Intrusive Probabilistic Surrogate Modeling of High-Fidelity Nuclear Reactor Simulations
발행사항  
[Sl] : University of Michigan, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
228 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
주기사항  
Advisor: Manera, Annalisa.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2024.
초록/해제  
요약With the continuing advancement of computational resources, high-fidelity simulations of neutron transport play an increasingly important role in the design and analysis of nuclear reactor cores. Because of the inherent non-linear interdependency of the flux solution on the coolant properties, neutron transport solvers are often coupled to subchannel thermal-hydraulics or computational fluid dynamic solvers to capture the necessary physics. The challenges present in numerical simulations required for nuclear reactor design, specifically the high computational cost and dimensionality encountered, are not unique to nuclear engineering. A full-order model is often expensive to evaluate in many engineering disciplines, particularly if the governing equations contain non-linear terms. The discretization of these partial differential equations leads to large systems of coupled equations. This limitation has led to the development and deployment of reduced-order modeling techniques. For decades, reduced-order models (ROM) have experienced a wide variety of successes in many fields and have been demonstrated for a wide range of applications. These techniques are not typically applied in the nuclear engineering field, particularly in production environments. Importantly, they have not been applied to high-fidelity multiphysics simulations of nuclear reactors. This work investigates the current state-of-the-art of ROMs and investigates their applicability to commonly encountered nuclear reactor design applications. Specifically, multi-stage convolutional neural network-based ROMs and the newly proposed Non-Linear Independent Dual System (NIDS) algorithm. The following chapters contain a discussion of traditional intrusive projection-based ROMs and works its way to non-intrusive neural network-based ROM methods. This work includes discussions on the theory, merits, challenges, and limitations associated with various methodologies. Furthermore, the uncertainty associated with reducing high-dimensional multiphysics problems is quantified using probabilistic modeling techniques combined with neural network-based ROMs. Specifically, variational inference approaches were applied to the ROMs. Using current state-of-the-art methods in non-intrusive ROMs, coupled with variational inference methods, ROMs are developed for two representative classes of nuclear engineering problems. The first application is a coupled MPACT/CTF model representing a single-assembly configuration experiencing a reactivity insertion accident via rod ejection. The state variables of interest are time-dependent relative pin powers. The second application is a 3D quarter-core MC21 depletion model. The state variables of interest are isotopic depletion trajectories. The performance of associated ROMs are assessed to evaluate the efficacy of using non-intrusive neural network-based ROMs in production design environments. In all contexts analyzed, NIDS methods are shown to outperform convolutional neural network-based algorithms for nuclear engineering applications and perform to a level acceptable in certain production design environments. Finally, a new Python package, Parody, is introduced to facilitate the assessment of ROMs and its potential use for further study of ROMs for nuclear applications is presented and discussed.
일반주제명  
Nuclear engineering
일반주제명  
Nuclear physics
일반주제명  
Computational physics
키워드  
Reduced order modeling
키워드  
Surrogate modeling
키워드  
Discretization independent
키워드  
Nuclear reactor design
키워드  
Reactivity insertion accident
키워드  
Nonlinear dimensionality reduction
기타저자  
University of Michigan Nuclear Engineering & Radiological Sciences
기본자료저록  
Dissertations Abstracts International. 85-12B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017162859
■00520250211152104
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382741093
■035    ▼a(MiAaPQ)AAI31349061
■035    ▼a(MiAaPQ)umichrackham005379
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a539.76
■1001  ▼aLaFleur,  Brandon.
■24510▼aDevelopment  and  Assessment  of  Machine  Learning  Techniques  for  Non-Intrusive  Probabilistic  Surrogate  Modeling  of  High-Fidelity  Nuclear  Reactor  Simulations
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a228  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-12,  Section:  B.
■500    ▼aAdvisor:  Manera,  Annalisa.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2024.
■520    ▼aWith  the  continuing  advancement  of  computational  resources,  high-fidelity  simulations  of  neutron  transport  play  an  increasingly  important  role  in  the  design  and  analysis  of  nuclear  reactor  cores.  Because  of  the  inherent  non-linear  interdependency  of  the  flux  solution  on  the  coolant  properties,  neutron  transport  solvers  are  often  coupled  to  subchannel  thermal-hydraulics  or  computational  fluid  dynamic  solvers  to  capture  the  necessary  physics.  The  challenges  present  in  numerical  simulations  required  for  nuclear  reactor  design,  specifically  the  high  computational  cost  and  dimensionality  encountered,  are  not  unique  to  nuclear  engineering.  A  full-order  model  is  often  expensive  to  evaluate  in  many  engineering  disciplines,  particularly  if  the  governing  equations  contain  non-linear  terms.  The  discretization  of  these  partial  differential  equations  leads  to  large  systems  of  coupled  equations.  This  limitation  has  led  to  the  development  and  deployment  of  reduced-order  modeling  techniques.  For  decades,  reduced-order  models  (ROM)  have  experienced  a  wide  variety  of  successes  in  many  fields  and  have  been  demonstrated  for  a  wide  range  of  applications.  These  techniques  are  not  typically  applied  in  the  nuclear  engineering  field,  particularly  in  production  environments.  Importantly,  they  have  not  been  applied  to  high-fidelity  multiphysics  simulations  of  nuclear  reactors.  This  work  investigates  the  current  state-of-the-art  of  ROMs  and  investigates  their  applicability  to  commonly  encountered  nuclear  reactor  design  applications.  Specifically,  multi-stage  convolutional  neural  network-based  ROMs  and  the  newly  proposed  Non-Linear  Independent  Dual  System  (NIDS)  algorithm.  The  following  chapters  contain  a  discussion  of  traditional  intrusive  projection-based  ROMs  and  works  its  way  to  non-intrusive  neural  network-based  ROM  methods.  This  work  includes  discussions  on  the  theory,  merits,  challenges,  and  limitations  associated  with  various  methodologies.  Furthermore,  the  uncertainty  associated  with  reducing  high-dimensional  multiphysics  problems  is  quantified  using  probabilistic  modeling  techniques  combined  with  neural  network-based  ROMs.  Specifically,  variational  inference  approaches  were  applied  to  the  ROMs.  Using  current  state-of-the-art  methods  in  non-intrusive  ROMs,  coupled  with  variational  inference  methods,  ROMs  are  developed  for  two  representative  classes  of  nuclear  engineering  problems.  The  first  application  is  a  coupled  MPACT/CTF  model  representing  a  single-assembly  configuration  experiencing  a  reactivity  insertion  accident  via  rod  ejection.  The  state  variables  of  interest  are  time-dependent  relative  pin  powers.    The  second  application  is  a  3D  quarter-core  MC21  depletion  model.  The  state  variables  of  interest  are  isotopic  depletion  trajectories.  The  performance  of  associated  ROMs  are  assessed  to  evaluate  the  efficacy  of  using  non-intrusive  neural  network-based  ROMs  in  production  design  environments.  In  all  contexts  analyzed,  NIDS  methods  are  shown  to  outperform  convolutional  neural  network-based  algorithms  for  nuclear  engineering  applications  and  perform  to  a  level  acceptable  in  certain  production  design  environments.  Finally,  a  new  Python  package,  Parody,  is  introduced  to  facilitate  the  assessment  of  ROMs  and  its  potential  use  for  further  study  of  ROMs  for  nuclear  applications  is  presented  and  discussed.
■590    ▼aSchool  code:  0127.
■650  4▼aNuclear  engineering
■650  4▼aNuclear  physics
■650  4▼aComputational  physics
■653    ▼aReduced  order  modeling
■653    ▼aSurrogate  modeling
■653    ▼aDiscretization  independent
■653    ▼aNuclear  reactor  design
■653    ▼aReactivity  insertion  accident
■653    ▼aNonlinear  dimensionality  reduction
■690    ▼a0552
■690    ▼a0756
■690    ▼a0216
■71020▼aUniversity  of  Michigan▼bNuclear  Engineering  &  Radiological  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g85-12B.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162859▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF10122 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.