본문

서브메뉴

Machine Learning Surrogates for Multiphysics Design
Machine Learning Surrogates for Multiphysics Design
Machine Learning Surrogates for Multiphysics Design

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202105700
ISBN  
9798263307752
DDC  
629.1
저자명  
Parrott, Corey M.
서명/저자  
Machine Learning Surrogates for Multiphysics Design
발행사항  
[Sl] : University of Illinois at Urbana-Champaign, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
146 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: James, Kai A.
학위논문주기  
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2024.
초록/해제  
요약Gradient-based optimization techniques are powerful, providing capabilities for optimal design of any system represented with a differentiable physics model. However, the computational cost of these traditional gradient-based methods is amplified for multidisciplinary design optimization (MDO) problems, most notably when coupling between physics disciplines is accounted for. This approach is characteristically iterative. With the current state of the design variable driving physical response, physics simulations are completed, sensitivities computed, and design variables updated (with sometimes costly algorithms to satisfy optimization constraints) in a cyclical process until convergence criteria are met.To alleviate this, this work investigates new methods and applications of machine learning as a surrogate for MDO, allowing for design synthesis in real-time. Though training a machine learning model is still an optimization problem at its core, a trained model is able to synthesize outputs in real-time, only requiring a single forward pass through the network. Some of the key areas of machine learning advancements lie in computer vision, networking, and natural language processing (NLP). Though many of the architectures proposed for these tasks could be trained and applied as a `black box' tool to MDO, the structure of the data would often be unaccounted for. Researchers using machine learning surrogates are often challenged with models that are highly unreliable. Though many designs will appear similar to those produced through physics-based methods (from a qualitative perspective), there are vulnerabilities in producing outliers when analyzed quantitatively. Without the proper mechanisms in place to address the characteristics of problems in physics, the models are susceptible to producing low performing designs.This work is proposed to address management of data and algorithms when creating surrogate models for problems of this sort. This is presented for a number of case studies. A design enhancement model is proposed, filtering single physics designs into those supporting Multiphysics boundary conditions. In this study, an emphasis is placed on the single physics domain used and its correlation to the Multiphysics load path. A multi-head self-attention network is proposed to capture global dependencies of data. This is shown to improve connectivity and stability of synthesized designs. Additionally, a network addressing the combined problem of packaging, routing, and physics-based performance is proposed. With such a large number of constraints, it is found that infusing the physics-based model into the network can become necessary for these cases.Furthermore, this work pursues improvements to methods in multimodal synthesis, focusing on design diversity. Through selective feature extraction with skeletonization algorithms, diversity is selectively imposed on structural features of a controlled size. This is shown to yield diversity in elements that more likely affect convergence to separate local minima, and in some cases, result in synthesis of designs that outperform those produced through physics-based models.The proposed frameworks present mechanisms to better capture the characteristics of the physics-based data, improving surrogate performance for such tasks. These case studies present novel contributions to the literature, with capabilities for a wide range of problems in the field of design optimization.
일반주제명  
Aerospace engineering
일반주제명  
Engineering
일반주제명  
Fluid mechanics
일반주제명  
Robotics
키워드  
Optimization
키워드  
Multidisciplinary design optimization
키워드  
Machine learning
키워드  
Data-driven design
기타저자  
University of Illinois at Urbana-Champaign Aerospace Engineering
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2024        us                              c    eng  d
■001000017361065
■00520260202105700
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263307752
■035    ▼a(MiAaPQ)AAI32409863
■035    ▼a(MiAaPQ)124355
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.1
■1001  ▼aParrott,  Corey  M.
■24510▼aMachine  Learning  Surrogates  for  Multiphysics  Design
■260    ▼a[Sl]▼bUniversity  of  Illinois  at  Urbana-Champaign▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a146  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  James,  Kai  A.
■5021  ▼aThesis  (Ph.D.)--University  of  Illinois  at  Urbana-Champaign,  2024.
■520    ▼aGradient-based  optimization  techniques  are  powerful,  providing  capabilities  for  optimal  design  of  any  system  represented  with  a  differentiable  physics  model.  However,  the  computational  cost  of  these  traditional  gradient-based  methods  is  amplified  for  multidisciplinary  design  optimization  (MDO)  problems,  most  notably  when  coupling  between  physics  disciplines  is  accounted  for.  This  approach  is  characteristically  iterative.  With  the  current  state  of  the  design  variable  driving  physical  response,  physics  simulations  are  completed,  sensitivities  computed,  and  design  variables  updated  (with  sometimes  costly  algorithms  to  satisfy  optimization  constraints)  in  a  cyclical  process  until  convergence  criteria  are  met.To  alleviate  this,  this  work  investigates  new  methods  and  applications  of  machine  learning  as  a  surrogate  for  MDO,  allowing  for  design  synthesis  in  real-time.  Though  training  a  machine  learning  model  is  still  an  optimization  problem  at  its  core,  a  trained  model  is  able  to  synthesize  outputs  in  real-time,  only  requiring  a  single  forward  pass  through  the  network.  Some  of  the  key  areas  of  machine  learning  advancements  lie  in  computer  vision,  networking,  and  natural  language  processing  (NLP).  Though  many  of  the  architectures  proposed  for  these  tasks  could  be  trained  and  applied  as  a  `black  box'  tool  to  MDO,  the  structure  of  the  data  would  often  be  unaccounted  for.  Researchers  using  machine  learning  surrogates  are  often  challenged  with  models  that  are  highly  unreliable.  Though  many  designs  will  appear  similar  to  those  produced  through  physics-based  methods  (from  a  qualitative  perspective),  there  are  vulnerabilities  in  producing  outliers  when  analyzed  quantitatively.  Without  the  proper  mechanisms  in  place  to  address  the  characteristics  of  problems  in  physics,  the  models  are  susceptible  to  producing  low  performing  designs.This  work  is  proposed  to  address  management  of  data  and  algorithms  when  creating  surrogate  models  for  problems  of  this  sort.  This  is  presented  for  a  number  of  case  studies.  A  design  enhancement  model  is  proposed,  filtering  single  physics  designs  into  those  supporting  Multiphysics  boundary  conditions.  In  this  study,  an  emphasis  is  placed  on  the  single  physics  domain  used  and  its  correlation  to  the  Multiphysics  load  path.  A  multi-head  self-attention  network  is  proposed  to  capture  global  dependencies  of  data.  This  is  shown  to  improve  connectivity  and  stability  of  synthesized  designs.  Additionally,  a  network  addressing  the  combined  problem  of  packaging,  routing,  and  physics-based  performance  is  proposed.  With  such  a  large  number  of  constraints,  it  is  found  that  infusing  the  physics-based  model  into  the  network  can  become  necessary  for  these  cases.Furthermore,  this  work  pursues  improvements  to  methods  in  multimodal  synthesis,  focusing  on  design  diversity.  Through  selective  feature  extraction  with  skeletonization  algorithms,  diversity  is  selectively  imposed  on  structural  features  of  a  controlled  size.  This  is  shown  to  yield  diversity  in  elements  that  more  likely  affect  convergence  to  separate  local  minima,  and  in  some  cases,  result  in  synthesis  of  designs  that  outperform  those  produced  through  physics-based  models.The  proposed  frameworks  present  mechanisms  to  better  capture  the  characteristics  of  the  physics-based  data,  improving  surrogate  performance  for  such  tasks.  These  case  studies  present  novel  contributions  to  the  literature,  with  capabilities  for  a  wide  range  of  problems  in  the  field  of  design  optimization.
■590    ▼aSchool  code:  0090.
■650  4▼aAerospace  engineering
■650  4▼aEngineering
■650  4▼aFluid  mechanics
■650  4▼aRobotics
■653    ▼aOptimization
■653    ▼aMultidisciplinary  design  optimization
■653    ▼aMachine  learning
■653    ▼aData-driven  design
■690    ▼a0538
■690    ▼a0800
■690    ▼a0537
■690    ▼a0204
■690    ▼a0771
■71020▼aUniversity  of  Illinois  at  Urbana-Champaign▼bAerospace  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0090
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17361065▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF16742 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.