본문

서브메뉴

Cost-Safety-Aware Inspection Strategy for Truck Fleets with Limited Historical Data
Cost-Safety-Aware Inspection Strategy for Truck Fleets with Limited Historical Data
Cost-Safety-Aware Inspection Strategy for Truck Fleets with Limited Historical Data

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20250211151359
ISBN  
9798382372341
DDC  
004
저자명  
Shi, Ying.
서명/저자  
Cost-Safety-Aware Inspection Strategy for Truck Fleets with Limited Historical Data
발행사항  
[Sl] : Carnegie Mellon University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
143 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
주기사항  
Advisor: Tang, Pingbo.
학위논문주기  
Thesis (Ph.D.)--Carnegie Mellon University, 2024.
초록/해제  
요약Heavy-duty trucks are a significant segment of the population involved in fatal accidents. In order to prevent crashes caused by vehicle malfunctions, effective inspection planning is essential. This research aims to develop a reliable predictive inspection planning strategy that can predict the future condition of the vehicle and to develop an inspection plan that can identify risky components with a few inspection costs and time. However, the limited historical data decrease the reliability of predictive inspection planning. To address this issue, this research developed data augmentation methods to generate synthetic data to fill in the limited historical data. The research also explores the potential to integrate humans and machines for more reliable inspection planning by handling data limitations from another perspective. This research addresses the challenges that: (1) the data augmentation is required to generate synthetic data similar to data in the real world, (2) the need for a comprehensive summary of characteristics of humans and machines in inspection planning, especially their advantages and limitations; (3) the need for integrating human knowledge into machine learning models with utilizing their advantages and avoiding limitations. To address the challenges, the researcher: (1) proposed a data augmentation method adapted to brake inspection planning considering the brake deterioration mechanism; (2) compared human and machine performance in inspection planning and summarized the scenarios in which human or machine perform better; (3) obtained a comprehensive summary of the advantages and limitations of human and machine inspection planning; and (4) This research proposed a framework for a human-machine collaboration mode that combines human and machine advantages and avoids their limitations. The outcomes of the research are expected to provide commercial fleets with reliable interpretation-based inspection suggestions, which can ensure vehicle safety with minimum inspection resources.
일반주제명  
Computer science
일반주제명  
Environmental engineering
키워드  
Data imputation
키워드  
Data sparsity
키워드  
Human knowledge
키워드  
Human-machine collaboration
키워드  
Predictive inspection
기타저자  
Carnegie Mellon University Civil and Environmental Engineering
기본자료저록  
Dissertations Abstracts International. 85-11B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017161457
■00520250211151359
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382372341
■035    ▼a(MiAaPQ)AAI31244101
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aShi,  Ying.
■24510▼aCost-Safety-Aware  Inspection  Strategy  for  Truck  Fleets  with  Limited  Historical  Data
■260    ▼a[Sl]▼bCarnegie  Mellon  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a143  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-11,  Section:  B.
■500    ▼aAdvisor:  Tang,  Pingbo.
■5021  ▼aThesis  (Ph.D.)--Carnegie  Mellon  University,  2024.
■520    ▼aHeavy-duty  trucks  are  a  significant  segment  of  the  population  involved  in  fatal  accidents.  In  order  to  prevent  crashes  caused  by  vehicle  malfunctions,  effective  inspection  planning  is  essential.  This  research  aims  to  develop  a  reliable  predictive  inspection  planning  strategy  that  can  predict  the  future  condition  of  the  vehicle  and  to  develop  an  inspection  plan  that  can  identify  risky  components  with  a  few  inspection  costs  and  time.  However,  the  limited  historical  data  decrease  the  reliability  of  predictive  inspection  planning.  To  address  this  issue,  this  research  developed  data  augmentation  methods  to  generate  synthetic  data  to  fill  in  the  limited  historical  data.  The  research  also  explores  the  potential  to  integrate  humans  and  machines  for  more  reliable  inspection  planning  by  handling  data  limitations  from  another  perspective.  This  research  addresses  the  challenges  that:  (1)  the  data  augmentation  is  required  to  generate  synthetic  data  similar  to  data  in  the  real  world,  (2)  the  need  for  a  comprehensive  summary  of  characteristics  of  humans  and  machines  in  inspection  planning,  especially  their  advantages  and  limitations;  (3)  the  need  for  integrating  human  knowledge  into  machine  learning  models  with  utilizing  their  advantages  and  avoiding  limitations.  To  address  the  challenges,  the  researcher:  (1)  proposed  a  data  augmentation  method  adapted  to  brake  inspection  planning  considering  the  brake  deterioration  mechanism;  (2)  compared  human  and  machine  performance  in  inspection  planning  and  summarized  the  scenarios  in  which  human  or  machine  perform  better;  (3)  obtained  a  comprehensive  summary  of  the  advantages  and  limitations  of  human  and  machine  inspection  planning;  and  (4)  This  research  proposed  a  framework  for  a  human-machine  collaboration  mode  that  combines  human  and  machine  advantages  and  avoids  their  limitations.  The  outcomes  of  the  research  are  expected  to  provide  commercial  fleets  with  reliable  interpretation-based  inspection  suggestions,  which  can  ensure  vehicle  safety  with  minimum  inspection  resources.
■590    ▼aSchool  code:  0041.
■650  4▼aComputer  science
■650  4▼aEnvironmental  engineering
■653    ▼aData  imputation
■653    ▼aData  sparsity
■653    ▼aHuman  knowledge
■653    ▼aHuman-machine  collaboration
■653    ▼aPredictive  inspection
■690    ▼a0543
■690    ▼a0984
■690    ▼a0775
■71020▼aCarnegie  Mellon  University▼bCivil  and  Environmental  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-11B.
■790    ▼a0041
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161457▼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

    Info Détail de la recherche.

    • Réservation
    • n'existe pas
    • My Folder
    • Demande Première utilisation
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Matériel
    Reg No. Call No. emplacement Status Lend Info
    TF10107 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Les réservations sont disponibles dans le livre d'emprunt. Pour faire des réservations, S'il vous plaît cliquer sur le bouton de réservation

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.