본문

서브메뉴

Development of Deep Meta-Learning Framework for Cross-Domain Multisensory Systems
Development of Deep Meta-Learning Framework for Cross-Domain Multisensory Systems
Development of Deep Meta-Learning Framework for Cross-Domain Multisensory Systems

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105519
ISBN  
9798263338688
DDC  
621
저자명  
Xie, Tingli.
서명/저자  
Development of Deep Meta-Learning Framework for Cross-Domain Multisensory Systems
발행사항  
[Sl] : Georgia Institute of Technology, 2023
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2023
형태사항  
210 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: A.
주기사항  
Advisor: Choi, Seung-Kyum.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2023.
초록/해제  
요약Prognostics and health management (PHM) for complex industrial systems is required for cost reduction, maintenance schedules, and reducing system failures. Catastrophic failure usually causes significant damage and may cause injury or fatality, making early and accurate diagnostics of paramount importance. As important parts of industrial systems, the reliability and availability of critical components and machinery are essential to ensuring safe and continuous operation in modern industry. With the development of sensor and information technologies, multisensory systems are widely used in the modern industry, which use multiple measurements (e.g., vibratory, electrical, thermal, acoustic, and oil-based data, etc.) to adequately reflect the health condition of critical machinery. As a result, it is necessary to develop intelligent and accurate PHM methods for multisensory systems.However, the existing deep learning (DL)-based PHM methodologies still have some critical limitations: 1) the majority of the existing PHM methodologies were vibration-based methods and did not consider the integration of information across multiple measurements; 2) critical machines usually operate under normal condition while abnormal conditions rarely happen, leaving only a small or limited data of abnormal conditions. Also, modern industrial equipment generally operates in complex and varying conditions, which causes the cross-domain problem and substantially degrades the identification performance of DL-based models; 3) when new health conditions occur in testing samples, most DL-based approaches may misclassify samples into the existing types of health conditions defined from the training data, which will cause open-set misclassification problems in the DL model.To address these issues, a deep meta-learning framework for cross-domain multisensory systems is investigated, which uses information fusion strategy, meta-learning, and convolution neural network (CNN). First, to enhance the utilization of multisignal data in CNN-based models, a multisignals-to-RGB-image conversion method is proposed for feature-level information fusion, which uses principal component analysis (PCA) to fuse multisignal data into three-channel red-green-blue (RGB) images for further identification. Second, a novel method called information fusion-based meta-learning (IFML) for cross-domain few-shot problems is proposed, which can not only be generalized to identify abnormal conditions with limited labeled samples, but also be used for different cross-domain scenarios. Third, the deep meta-open generative adversarial network (DMO-GAN) is proposed to enhance model generalization and solve open-set misclassification problems. The effectiveness and generalization of the proposed framework are validated in several industrial datasets consisting of different multisensory systems.
일반주제명  
Industrial equipment
일반주제명  
Technological change
일반주제명  
Failure
일반주제명  
Deep learning
일반주제명  
Wavelet transforms
일반주제명  
Fiber optics
일반주제명  
Monitoring systems
일반주제명  
Fourier transforms
일반주제명  
Fault diagnosis
일반주제명  
Machinery
일반주제명  
Neural networks
일반주제명  
Design
일반주제명  
Acoustics
일반주제명  
Industrial engineering
일반주제명  
Mathematics
일반주제명  
Optics
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-05A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2023        us                              c    eng  d
■001000017360399
■00520260202105519
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263338688
■035    ▼a(MiAaPQ)AAI32309456
■035    ▼a(MiAaPQ)GeorgiaTech76822
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621
■1001  ▼aXie,  Tingli.
■24510▼aDevelopment  of  Deep  Meta-Learning  Framework  for  Cross-Domain  Multisensory  Systems
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2023
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2023
■300    ▼a210  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  A.
■500    ▼aAdvisor:  Choi,  Seung-Kyum.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2023.
■520    ▼aPrognostics  and  health  management  (PHM)  for  complex  industrial  systems  is  required  for  cost  reduction,  maintenance  schedules,  and  reducing  system  failures.  Catastrophic  failure  usually  causes  significant  damage  and  may  cause  injury  or  fatality,  making  early  and  accurate  diagnostics  of  paramount  importance.  As  important  parts  of  industrial  systems,  the  reliability  and  availability  of  critical  components  and  machinery  are  essential  to  ensuring  safe  and  continuous  operation  in  modern  industry.  With  the  development  of  sensor  and  information  technologies,  multisensory  systems  are  widely  used  in  the  modern  industry,  which  use  multiple  measurements  (e.g.,  vibratory,  electrical,  thermal,  acoustic,  and  oil-based  data,  etc.)  to  adequately  reflect  the  health  condition  of  critical  machinery.  As  a  result,  it  is  necessary  to  develop  intelligent  and  accurate  PHM  methods  for  multisensory  systems.However,  the  existing  deep  learning  (DL)-based  PHM  methodologies  still  have  some  critical  limitations:  1)  the  majority  of  the  existing  PHM  methodologies  were  vibration-based  methods  and  did  not  consider  the  integration  of  information  across  multiple  measurements;  2)  critical  machines  usually  operate  under  normal  condition  while  abnormal  conditions  rarely  happen,  leaving  only  a  small  or  limited  data  of  abnormal  conditions.  Also,  modern  industrial  equipment  generally  operates  in  complex  and  varying  conditions,  which  causes  the  cross-domain  problem  and  substantially  degrades  the  identification  performance  of  DL-based  models;  3)  when  new  health  conditions  occur  in  testing  samples,  most  DL-based  approaches  may  misclassify  samples  into  the  existing  types  of  health  conditions  defined  from  the  training  data,  which  will  cause  open-set  misclassification  problems  in  the  DL  model.To  address  these  issues,  a  deep  meta-learning  framework  for  cross-domain  multisensory  systems  is  investigated,  which  uses  information  fusion  strategy,  meta-learning,  and  convolution  neural  network  (CNN).  First,  to  enhance  the  utilization  of  multisignal  data  in  CNN-based  models,  a  multisignals-to-RGB-image  conversion  method  is  proposed  for  feature-level  information  fusion,  which  uses  principal  component  analysis  (PCA)  to  fuse  multisignal  data  into  three-channel  red-green-blue  (RGB)  images  for  further  identification.  Second,  a  novel  method  called  information  fusion-based  meta-learning  (IFML)  for  cross-domain  few-shot  problems  is  proposed,  which  can  not  only  be  generalized  to  identify  abnormal  conditions  with  limited  labeled  samples,  but  also  be  used  for  different  cross-domain  scenarios.  Third,  the  deep  meta-open  generative  adversarial  network  (DMO-GAN)  is  proposed  to  enhance  model  generalization  and  solve  open-set  misclassification  problems.  The  effectiveness  and  generalization  of  the  proposed  framework  are  validated  in  several  industrial  datasets  consisting  of  different  multisensory  systems.
■590    ▼aSchool  code:  0078.
■650  4▼aIndustrial  equipment
■650  4▼aTechnological  change
■650  4▼aFailure
■650  4▼aDeep  learning
■650  4▼aWavelet  transforms
■650  4▼aFiber  optics
■650  4▼aMonitoring  systems
■650  4▼aFourier  transforms
■650  4▼aFault  diagnosis
■650  4▼aMachinery
■650  4▼aNeural  networks
■650  4▼aDesign
■650  4▼aAcoustics
■650  4▼aIndustrial  engineering
■650  4▼aMathematics
■650  4▼aOptics
■690    ▼a0389
■690    ▼a0986
■690    ▼a0800
■690    ▼a0546
■690    ▼a0629
■690    ▼a0405
■690    ▼a0752
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-05A.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360399▼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
    TF17143 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.