Recent Research and Applications in Variational Autoencoders for Industrial Prognosis and Health Management: A Survey

Whether in the industrial, medical, or real-world domains, more and more data are being collected. The common particularity of all these application domains is that a great part of this data is mostly unlabeled. Thus, designing a learning model with a minimum of labeled data represents a major chall...

Full description

Saved in:
Bibliographic Details
Published in:Prognostics and System Health Management Conference pp. 193 - 203
Main Authors: Zemouri, Ryad, Levesque, Melanie, Boucher, Etienne, Kirouac, Mathieu, Lafleur, Francois, Bernier, Simon, Merkhouf, Arezki
Format: Conference Proceeding
Language:English
Published: IEEE 01.05.2022
Subjects:
Deep learning
Prognosis and Health Management
Variational Autoencoders
ISSN:2166-5656
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Whether in the industrial, medical, or real-world domains, more and more data are being collected. The common particularity of all these application domains is that a great part of this data is mostly unlabeled. Thus, designing a learning model with a minimum of labeled data represents a major challenge in the coming years. A particular emphasis has recently been put on unsupervised learning methods based on the idea of autoencoding. The objective of these methods is twofold: to reduce the dimensionality of the input space and to reconstruct the original observation from this lower dimensional representation space. The variational form of these autoencoders, called the Variational Autoencoders (VAEs), is particularly successful in almost all application areas. This enthusiasm comes from the fact that VAEs allow to take advantage of the theoretical foundations of the Variational Bayesian methods and the learning capabilities of artificial neural networks. This review paper gives to the PHM community a synthesis of the latest publications in the PHM domain using the VAEs related to four topics: 1) Data-Driven Soft Sensors for missing values and data outliers, 2) reconstruction error for fault detection, 3) resampling approach for imbalanced data generation and minority class and 4) the variational embedding as PHM preprocessing pipelines and data transformations. After a review of the theoretical foundations and some practical tricks to succeed the implementation of the VAEs in industrial applications, the four main topics used to exploit the VAEs in the PHM domain are detailed. Finally, a global view of the research done at the research institute of Hydro-Québec regarding the diagnosis and failure detection of hydro-generators with VAEs are presented.
AbstractList Whether in the industrial, medical, or real-world domains, more and more data are being collected. The common particularity of all these application domains is that a great part of this data is mostly unlabeled. Thus, designing a learning model with a minimum of labeled data represents a major challenge in the coming years. A particular emphasis has recently been put on unsupervised learning methods based on the idea of autoencoding. The objective of these methods is twofold: to reduce the dimensionality of the input space and to reconstruct the original observation from this lower dimensional representation space. The variational form of these autoencoders, called the Variational Autoencoders (VAEs), is particularly successful in almost all application areas. This enthusiasm comes from the fact that VAEs allow to take advantage of the theoretical foundations of the Variational Bayesian methods and the learning capabilities of artificial neural networks. This review paper gives to the PHM community a synthesis of the latest publications in the PHM domain using the VAEs related to four topics: 1) Data-Driven Soft Sensors for missing values and data outliers, 2) reconstruction error for fault detection, 3) resampling approach for imbalanced data generation and minority class and 4) the variational embedding as PHM preprocessing pipelines and data transformations. After a review of the theoretical foundations and some practical tricks to succeed the implementation of the VAEs in industrial applications, the four main topics used to exploit the VAEs in the PHM domain are detailed. Finally, a global view of the research done at the research institute of Hydro-Québec regarding the diagnosis and failure detection of hydro-generators with VAEs are presented.
Author Zemouri, Ryad
Levesque, Melanie
Lafleur, Francois
Boucher, Etienne
Kirouac, Mathieu
Bernier, Simon
Merkhouf, Arezki
Author_xml – sequence: 1
  givenname: Ryad
  surname: Zemouri
  fullname: Zemouri, Ryad
  email: zemouri.ryad@hydroquebec.com
  organization: Centre de Recherche d'Hydro-Québec (CRHQ),Varennes,Canada,J3X1S1
– sequence: 2
  givenname: Melanie
  surname: Levesque
  fullname: Levesque, Melanie
  organization: Centre de Recherche d'Hydro-Québec (CRHQ),Varennes,Canada,J3X1S1
– sequence: 3
  givenname: Etienne
  surname: Boucher
  fullname: Boucher, Etienne
  email: etienne.boucher.2@umontreal.ca
  organization: Université de Montréal-MILA
– sequence: 4
  givenname: Mathieu
  surname: Kirouac
  fullname: Kirouac, Mathieu
  organization: Centre de Recherche d'Hydro-Québec (CRHQ),Varennes,Canada,J3X1S1
– sequence: 5
  givenname: Francois
  surname: Lafleur
  fullname: Lafleur, Francois
  organization: Centre de Recherche d'Hydro-Québec (CRHQ),Varennes,Canada,J3X1S1
– sequence: 6
  givenname: Simon
  surname: Bernier
  fullname: Bernier, Simon
  organization: Centre de Recherche d'Hydro-Québec (CRHQ),Varennes,Canada,J3X1S1
– sequence: 7
  givenname: Arezki
  surname: Merkhouf
  fullname: Merkhouf, Arezki
  organization: Centre de Recherche d'Hydro-Québec (CRHQ),Varennes,Canada,J3X1S1
BookMark eNotj01PAjEYhKvRREF-gZeevC12-7Vbb4SokEAk-BFv5N22CzVLS9pdE_69K3qazOTJTGaALnzwFqG7nIzznKj71WxJCaXZIngTvKBc8PFvMCaEcHqGBrmUghdK8M9zdE17lwkp5BUapfTVM6QoFKfiGnVrq61v8domC1HvMHiDJ4dD4zS0LviEnccfEN3JQYMnXRus18HYmHAdIp5706W2Bxq8imHrQ3Lp1DKz0LQ7vAQPW7vvRx7wBL928dseb9BlDU2yo38dovenx7fpLFu8PM-nk0XmKGFtxupCE4A651V_oS6JJpJJCbIWlVVSVcKIXDOA3DBTcKVLqKQthSIlLStm2BDd_vU6a-3mEN0e4nGjSlL299kPGMZi1A
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/PHM2022-London52454.2022.00042
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL) (UW System Shared)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 166547954X
9781665479547
EISSN 2166-5656
EndPage 203
ExternalDocumentID 9808794
Genre orig-research
GroupedDBID 6IE
6IF
6IH
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-i203t-3f7c0aaf14b216f80c06366a6f5be969b5d51c3aa1d3d749c8ab6e8590828b3d3
IEDL.DBID RIE
ISICitedReferencesCount 19
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000945467800020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:23:47 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-3f7c0aaf14b216f80c06366a6f5be969b5d51c3aa1d3d749c8ab6e8590828b3d3
PageCount 11
ParticipantIDs ieee_primary_9808794
PublicationCentury 2000
PublicationDate 2022-May
PublicationDateYYYYMMDD 2022-05-01
PublicationDate_xml – month: 05
  year: 2022
  text: 2022-May
PublicationDecade 2020
PublicationTitle Prognostics and System Health Management Conference
PublicationTitleAbbrev PHM-LONDON
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000779425
Score 1.9145403
Snippet Whether in the industrial, medical, or real-world domains, more and more data are being collected. The common particularity of all these application domains is...
SourceID ieee
SourceType Publisher
StartPage 193
SubjectTerms Deep learning
Prognosis and Health Management
Variational Autoencoders
Title Recent Research and Applications in Variational Autoencoders for Industrial Prognosis and Health Management: A Survey
URI https://ieeexplore.ieee.org/document/9808794
WOSCitedRecordID wos000945467800020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFH7MIaIXf2zib3IQT9b1Z5J6G-LYQcdAHbuNNHmBXjrZ2oH_vUlatwlevJWUpCUvkC8v3_c9gFsRBExqxT0DVs0BhSbay6QBcjKWKJjB--h03JMXNhrx6TQdt-B-rYVBREc-wwf76O7y1VxWNlXWS7nPzfrZgR3GaK3VWudTfGbehMke3DU2mr3x8DW0XPW6LkYSxi6HEtYGneGvaipuMxkc_u83jqC7UeWR8Xq_OYYWFidwsGUo2IHKoEDTl_zw6YgoFOlv3VGTvCATczxuUoCkX5Vza2Vp6czE4FeyKeVhv2VZePnSjVLrlciGLvNI-uStWqzwqwsfg-f3p6HXFFbw8tCPSi_STPpC6CDOwoBq7ksDVCgVVCcZpjTNEpUEMhIiUJFicSq5yChyVx6dZ5GKTqFdzAs8A5LYYGIgqeQ6NutBUMpRRVqgtuL_7Bw6dgJnn7V3xqyZu4u_my9h34XMEQqvoF0uKryGXbkq8-XixgX8G6S3rvQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwGP2YU7y8eNnEu3kQn6xr0zZNfRvimLiNgXPsbaS5QF862dqB_94krdsEX3wrKUlLvkBOvpxzPoA75nkRV4I6GqzqAwoJlZNwDeR4wCWLNN6XVsc97kWDAZ1M4mENHlZaGCmlJZ_JR_No7_LFjBcmVdaKqUv1-tmC7TAIsFuqtVYZFTfS73C4C_eVkWZr2O1jw1YvK2OEOLBZFFxadOJf9VTsdtI5_N-PHEFzrctDw9WOcww1mZ3AwYalYAMKjQN1X_TDqEMsE6i9cUuN0gyN9QG5SgKidpHPjJmlITQjjWDRupiH-Zbh4aULO0qpWEJrwswTaqP3Yr6UX0346LyMnrtOVVrBSbHr546vIu4yprwgwR5R1OUaqhDCiAoTGZM4CUXocZ8xT_giCmJOWUIktQXSaeIL_xTq2SyTZ4BCE07pccKpCvSKYIRQKXzFpDLy_-QcGmYCp5-le8a0mruLv5tvYa876vemvdfB2yXs2_BZeuEV1PN5Ia9hhy_zdDG_scH_Bue_sjs
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Prognostics+and+System+Health+Management+Conference&rft.atitle=Recent+Research+and+Applications+in+Variational+Autoencoders+for+Industrial+Prognosis+and+Health+Management%3A+A+Survey&rft.au=Zemouri%2C+Ryad&rft.au=Levesque%2C+Melanie&rft.au=Boucher%2C+Etienne&rft.au=Kirouac%2C+Mathieu&rft.date=2022-05-01&rft.pub=IEEE&rft.eissn=2166-5656&rft.spage=193&rft.epage=203&rft_id=info:doi/10.1109%2FPHM2022-London52454.2022.00042&rft.externalDocID=9808794