본문

서브메뉴

Dataset Construction and Characterization for Learning Automotive Aerodynamics
Dataset Construction and Characterization for Learning Automotive Aerodynamics
Dataset Construction and Characterization for Learning Automotive Aerodynamics

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202104740
ISBN  
9798290651910
DDC  
629.222
저자명  
Benjamin, Mark.
서명/저자  
Dataset Construction and Characterization for Learning Automotive Aerodynamics
발행사항  
[Sl] : Stanford University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
121 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
주기사항  
Advisor: Iaccarino, Gianluca.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2024.
초록/해제  
요약The cost of numerical simulations for automotive aerodynamics optimization makes data-driven surrogates an appealing alternative. However, there is a data insufficiency problem in this application space. Owing to the proprietary nature of commercial automotive designs, training datasets for drag prediction models are limited to a few freely-available, realistic geometries. Additionally, existing datasets suffer from a lack of quantification of intrinsic properties-such as diversity-that correlate with predictive performance on unseen samples; in other words, there is a dataset characterization problem.In this work, a database construction strategy is proposed that allows for the controlled generation of an arbitrary number of samples, by convex interpolation between a small number of basis geometries. A set of geometries is then constructed using this method, using the DrivAer automotive reference geometry for the basis cases. Large-eddy simulations are used to obtain the aerodynamic quantities of interest for each geometry. Convolutional neural network-based models are trained with this dataset to make aerodynamics predictions. The proposed method allows for a characterization of datasets based on size, density, and diversity. A formal measure of diversity for a given dataset is developed. Then, datasets of successively increasing diversity but constant size are constructed, and it is shown that the dataset diversity has an impact on the predictive accuracy of the neural networks. The proposed method allows for more rigorous a priori evaluation of models than is currently possible and can be applied readily to other problems of shape optimization.
일반주제명  
Automobiles
일반주제명  
Design optimization
일반주제명  
Multidimensional scaling
일반주제명  
Industrial research
일반주제명  
Fluid dynamics
일반주제명  
Reynolds number
일반주제명  
Energy consumption
일반주제명  
Geometry
일반주제명  
Aerodynamics
일반주제명  
Neural networks
일반주제명  
Aeronomy
일반주제명  
Mechanical engineering
키워드  
Automotive aerodynamics
키워드  
Dataset construction
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2024        us                              c    eng  d
■001000017358709
■00520260202104740
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798290651910
■035    ▼a(MiAaPQ)AAI32149699
■035    ▼a(MiAaPQ)Stanfordnx392gr8211
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a629.222
■1001  ▼aBenjamin,  Mark.
■24510▼aDataset  Construction  and  Characterization  for  Learning  Automotive  Aerodynamics
■260    ▼a[Sl]▼bStanford  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a121  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-03,  Section:  B.
■500    ▼aAdvisor:  Iaccarino,  Gianluca.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2024.
■520    ▼aThe  cost  of  numerical  simulations  for  automotive  aerodynamics  optimization  makes  data-driven  surrogates  an  appealing  alternative.  However,  there  is  a  data  insufficiency  problem  in  this  application  space.  Owing  to  the  proprietary  nature  of  commercial  automotive  designs,  training  datasets  for  drag  prediction  models  are  limited  to  a  few  freely-available,  realistic  geometries.  Additionally,  existing  datasets  suffer  from  a  lack  of  quantification  of  intrinsic  properties-such  as  diversity-that  correlate  with  predictive  performance  on  unseen  samples;  in  other  words,  there  is  a  dataset  characterization  problem.In  this  work,  a  database  construction  strategy  is  proposed  that  allows  for  the  controlled  generation  of  an  arbitrary  number  of  samples,  by  convex  interpolation  between  a  small  number  of  basis  geometries.  A  set  of  geometries  is  then  constructed  using  this  method,  using  the  DrivAer  automotive  reference  geometry  for  the  basis  cases.  Large-eddy  simulations  are  used  to  obtain  the  aerodynamic  quantities  of  interest  for  each  geometry.  Convolutional  neural  network-based  models  are  trained  with  this  dataset  to  make  aerodynamics  predictions.  The  proposed  method  allows  for  a  characterization  of  datasets  based  on  size,  density,  and  diversity.  A  formal  measure  of  diversity  for  a  given  dataset  is  developed.  Then,  datasets  of  successively  increasing  diversity  but  constant  size  are  constructed,  and  it  is  shown  that  the  dataset  diversity  has  an  impact  on  the  predictive  accuracy  of  the  neural  networks.  The  proposed  method  allows  for  more  rigorous  a  priori  evaluation  of  models  than  is  currently  possible  and  can  be  applied  readily  to  other  problems  of  shape  optimization.
■590    ▼aSchool  code:  0212.
■650  4▼aAutomobiles
■650  4▼aDesign  optimization
■650  4▼aMultidimensional  scaling
■650  4▼aIndustrial  research
■650  4▼aFluid  dynamics
■650  4▼aReynolds  number
■650  4▼aEnergy  consumption
■650  4▼aGeometry
■650  4▼aAerodynamics
■650  4▼aNeural  networks
■650  4▼aAeronomy
■650  4▼aMechanical  engineering
■653    ▼aAutomotive  aerodynamics
■653    ▼aDataset  construction
■690    ▼a0367
■690    ▼a0548
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-03B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358709▼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
    TF19253 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.