Semi-Supervised Deep Conditional Variational Autoencoder for Soft Sensor Modeling

Variational autoencoder (VAE) as an unsupervised deep generated model has been widely applied to process modeling for industrial processes due to its excellent ability in nonlinear and uncertain feature extraction. However, soft sensor based on VAE model faces three challenges. First, the constructe...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE sensors journal Ročník 24; číslo 5; s. 7153 - 7164
Hlavní autori: Tang, Xiaochu, Yan, Jiawei, Li, Yuan, Zhang, Xinmin, Song, Zhihuan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.03.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:1530-437X, 1558-1748
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Variational autoencoder (VAE) as an unsupervised deep generated model has been widely applied to process modeling for industrial processes due to its excellent ability in nonlinear and uncertain feature extraction. However, soft sensor based on VAE model faces three challenges. First, the constructed supervised VAE model makes it difficult to describe the correlation between input and output based on self-network. Second, the output of the VAE may suffer from instability and uncontrollability. In addition, the limited labeled data in industries are the third challenge. To solve the above problems, a semi-supervised deep conditional VAE (SS-DCVAE) is constructed for soft sensor based on a supervised DCVAE (S-DCVAE) and an unsupervised DCVAE (U-DCVAE). The S-DCVAE model is constructed by injecting unlabeled data, the actual labels, and estimated labels as constraint conditions from the preneural network. Based on such a conditional supervised structure, the input-output correlation can be strengthened and the generated data can be controlled toward the aim direction. Furthermore, the U-DCVAE model can be built by making the latent distribution as similar as possible to S-DCVAE, as well as only using unlabeled data with corresponding estimated labels. In this way, the unlabeled data can be fully utilized and online prediction can be achieved. Finally, combining the decoder of S-DCVAE model with the encoder of U-DCVAE, the SS-DCVAE model is constructed with both advantages. The effectiveness and superiority of the SS-DCVAE model are demonstrated by comparing the prediction results of the proposed model with other deep learning methods based on industrial cases.
AbstractList Variational autoencoder (VAE) as an unsupervised deep generated model has been widely applied to process modeling for industrial processes due to its excellent ability in nonlinear and uncertain feature extraction. However, soft sensor based on VAE model faces three challenges. First, the constructed supervised VAE model makes it difficult to describe the correlation between input and output based on self-network. Second, the output of the VAE may suffer from instability and uncontrollability. In addition, the limited labeled data in industries are the third challenge. To solve the above problems, a semi-supervised deep conditional VAE (SS-DCVAE) is constructed for soft sensor based on a supervised DCVAE (S-DCVAE) and an unsupervised DCVAE (U-DCVAE). The S-DCVAE model is constructed by injecting unlabeled data, the actual labels, and estimated labels as constraint conditions from the preneural network. Based on such a conditional supervised structure, the input–output correlation can be strengthened and the generated data can be controlled toward the aim direction. Furthermore, the U-DCVAE model can be built by making the latent distribution as similar as possible to S-DCVAE, as well as only using unlabeled data with corresponding estimated labels. In this way, the unlabeled data can be fully utilized and online prediction can be achieved. Finally, combining the decoder of S-DCVAE model with the encoder of U-DCVAE, the SS-DCVAE model is constructed with both advantages. The effectiveness and superiority of the SS-DCVAE model are demonstrated by comparing the prediction results of the proposed model with other deep learning methods based on industrial cases.
Author Li, Yuan
Song, Zhihuan
Tang, Xiaochu
Zhang, Xinmin
Yan, Jiawei
Author_xml – sequence: 1
  givenname: Xiaochu
  orcidid: 0000-0002-8787-0978
  surname: Tang
  fullname: Tang, Xiaochu
  email: tangxc0420@126.com
  organization: School of Automation, Shenyang Aerospace University, Shenyang, China
– sequence: 2
  givenname: Jiawei
  orcidid: 0000-0002-4593-2413
  surname: Yan
  fullname: Yan, Jiawei
  organization: School of Automation, Shenyang Aerospace University, Shenyang, China
– sequence: 3
  givenname: Yuan
  surname: Li
  fullname: Li, Yuan
  organization: College of Information Engineering, Shenyang University of Chemical Technology, Shenyang, China
– sequence: 4
  givenname: Xinmin
  orcidid: 0000-0002-4761-3969
  surname: Zhang
  fullname: Zhang, Xinmin
  organization: State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China
– sequence: 5
  givenname: Zhihuan
  surname: Song
  fullname: Song, Zhihuan
  organization: State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China
BookMark eNp9kF1LwzAUhoNMcJv-AMGLgtedSZM07eWY84upSId4F9L0RDK6Ziat4L-3dbsQL7zKS3ifwznPBI0a1wBC5wTPCMH51UOxfJolOGEzSjlhlByhMeE8i4lg2WjIFMeMircTNAlhgzHJBRdj9FLA1sZFtwP_aQNU0TXALlq4prKtdY2qo1flrTrkedc6aLSrwEfG-ahwpo0KaEKfH_vf2jbvp-jYqDrA2eGdovXNcr24i1fPt_eL-SrWSc7aOKOaKIWBJpiktEqrnHJWQcVToU2phFZQmqzMFNWcGUGoKIXhJVPaMJxiOkWX-7E77z46CK3cuM73SwaZ5DThgolkaIl9S3sXggcjtW1_rmm9srUkWA765KBPDvrkQV9Pkj_kztut8l__Mhd7xgLArz7DmFFKvwHpPH4J
CODEN ISJEAZ
CitedBy_id crossref_primary_10_1109_TASE_2025_3576122
crossref_primary_10_1002_cjce_25447
crossref_primary_10_1016_j_ins_2024_121565
crossref_primary_10_1016_j_measurement_2025_116761
crossref_primary_10_1109_TCYB_2025_3580633
crossref_primary_10_1109_TASE_2024_3504736
crossref_primary_10_3390_pr12091807
crossref_primary_10_1016_j_jprocont_2025_103497
Cites_doi 10.1002/9781118501054
10.1109/TIM.2020.2968162
10.1016/j.jprocont.2018.04.006
10.1109/TII.2018.2809730
10.1109/TII.2019.2951622
10.1109/JSEN.2020.3003826
10.1109/TIM.2006.887331
10.1016/j.compchemeng.2007.07.005
10.1016/j.chemolab.2010.11.004
10.1162/neco.2006.18.7.1527
10.1109/TNNLS.2020.3015929
10.48550/arXiv.1312.6114
10.1109/TCYB.2020.3010331
10.48550/ARXIV.1404.7828
10.1109/JSEN.2021.3128562
10.3390/s23229175
10.1109/TII.2019.2902560
10.1016/j.measurement.2017.09.025
10.1109/TIE.2017.2733448
10.1109/TIE.2018.2856200
10.1016/j.eng.2019.01.019
10.1109/TII.2021.3110197
10.1109/TII.2022.3183211
10.1016/j.compchemeng.2008.12.012
10.1109/TIE.2016.2622668
10.1016/j.jprocont.2014.01.012
10.1016/j.measurement.2022.111974
10.1109/TII.2018.2880968
10.1016/j.jprocont.2019.11.004
10.1109/TCST.2018.2856845
10.1038/nature14539
10.1109/JSEN.2022.3201706
10.1016/j.ifacsc.2021.100150
10.1016/j.chemolab.2019.05.001
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
7U5
8FD
L7M
DOI 10.1109/JSEN.2024.3351431
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList Solid State and Superconductivity Abstracts

Database_xml – sequence: 1
  dbid: RIE
  name: IEL
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Geography
Engineering
EISSN 1558-1748
EndPage 7164
ExternalDocumentID 10_1109_JSEN_2024_3351431
10400433
Genre orig-research
GrantInformation_xml – fundername: Natural Science Foundation of Liaoning Province
  grantid: 2023-MS-242
  funderid: 10.13039/501100005047
– fundername: National Natural Science Foundation of China (NSFC)
  grantid: 62273242
  funderid: 10.13039/501100001809
GroupedDBID -~X
0R~
29I
4.4
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AGQYO
AHBIQ
AJQPL
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
EBS
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
TWZ
AAYXX
CITATION
7SP
7U5
8FD
L7M
ID FETCH-LOGICAL-c294t-83c1aa0e320163d6d9354ded567cfba7caebf8b8a3c54f7137b7f5b4acf40603
IEDL.DBID RIE
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001280059600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1530-437X
IngestDate Mon Jun 30 08:29:37 EDT 2025
Sat Nov 29 06:39:52 EST 2025
Tue Nov 18 22:37:17 EST 2025
Wed Aug 27 02:08:38 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c294t-83c1aa0e320163d6d9354ded567cfba7caebf8b8a3c54f7137b7f5b4acf40603
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-4761-3969
0000-0002-4593-2413
0000-0002-8787-0978
PQID 2932574720
PQPubID 75733
PageCount 12
ParticipantIDs proquest_journals_2932574720
crossref_citationtrail_10_1109_JSEN_2024_3351431
ieee_primary_10400433
crossref_primary_10_1109_JSEN_2024_3351431
PublicationCentury 2000
PublicationDate 2024-03-01
PublicationDateYYYYMMDD 2024-03-01
PublicationDate_xml – month: 03
  year: 2024
  text: 2024-03-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE sensors journal
PublicationTitleAbbrev JSEN
PublicationYear 2024
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref35
ref12
ref34
ref15
ref14
Doersch (ref22) 2016
ref36
ref31
ref30
ref11
ref33
ref10
Jiang (ref20) 2016
ref32
ref2
ref1
ref17
ref16
ref19
ref18
ref24
ref23
ref26
ref25
ref21
ref28
ref27
ref29
ref8
ref7
ref9
ref4
ref3
ref6
ref5
References_xml – year: 2016
  ident: ref20
  article-title: Variational deep embedding: An unsupervised and generative approach to clustering
  publication-title: arXiv:1611.05148
– ident: ref1
  doi: 10.1002/9781118501054
– ident: ref23
  doi: 10.1109/TIM.2020.2968162
– ident: ref5
  doi: 10.1016/j.jprocont.2018.04.006
– ident: ref19
  doi: 10.1109/TII.2018.2809730
– ident: ref24
  doi: 10.1109/TII.2019.2951622
– ident: ref31
  doi: 10.1109/JSEN.2020.3003826
– ident: ref10
  doi: 10.1109/TIM.2006.887331
– ident: ref3
  doi: 10.1016/j.compchemeng.2007.07.005
– ident: ref7
  doi: 10.1016/j.chemolab.2010.11.004
– ident: ref11
  doi: 10.1162/neco.2006.18.7.1527
– ident: ref17
  doi: 10.1109/TNNLS.2020.3015929
– ident: ref21
  doi: 10.48550/arXiv.1312.6114
– ident: ref18
  doi: 10.1109/TCYB.2020.3010331
– ident: ref13
  doi: 10.48550/ARXIV.1404.7828
– ident: ref27
  doi: 10.1109/JSEN.2021.3128562
– ident: ref36
  doi: 10.3390/s23229175
– ident: ref33
  doi: 10.1109/TII.2019.2902560
– ident: ref8
  doi: 10.1016/j.measurement.2017.09.025
– ident: ref28
  doi: 10.1109/TIE.2017.2733448
– ident: ref29
  doi: 10.1109/TIE.2018.2856200
– ident: ref4
  doi: 10.1016/j.eng.2019.01.019
– ident: ref25
  doi: 10.1109/TII.2021.3110197
– ident: ref35
  doi: 10.1109/TII.2022.3183211
– ident: ref2
  doi: 10.1016/j.compchemeng.2008.12.012
– ident: ref14
  doi: 10.1109/TIE.2016.2622668
– ident: ref15
  doi: 10.1016/j.jprocont.2014.01.012
– ident: ref6
  doi: 10.1016/j.measurement.2022.111974
– year: 2016
  ident: ref22
  article-title: Tutorial on variational autoencoders
  publication-title: arXiv:1606.05908
– ident: ref16
  doi: 10.1109/TII.2018.2880968
– ident: ref26
  doi: 10.1016/j.jprocont.2019.11.004
– ident: ref32
  doi: 10.1109/TCST.2018.2856845
– ident: ref12
  doi: 10.1038/nature14539
– ident: ref30
  doi: 10.1109/JSEN.2022.3201706
– ident: ref34
  doi: 10.1016/j.ifacsc.2021.100150
– ident: ref9
  doi: 10.1016/j.chemolab.2019.05.001
SSID ssj0019757
Score 2.4473493
Snippet Variational autoencoder (VAE) as an unsupervised deep generated model has been widely applied to process modeling for industrial processes due to its excellent...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 7153
SubjectTerms Data mining
Data models
Decoding
Deep learning
Feature extraction
Labels
Machine learning
Modelling
semi-supervised (SS) model
Sensors
soft sensor
Soft sensors
supervised conditional variational autoencoder (VAE)
Title Semi-Supervised Deep Conditional Variational Autoencoder for Soft Sensor Modeling
URI https://ieeexplore.ieee.org/document/10400433
https://www.proquest.com/docview/2932574720
Volume 24
WOSCitedRecordID wos001280059600001&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
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEL
  customDbUrl:
  eissn: 1558-1748
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0019757
  issn: 1530-437X
  databaseCode: RIE
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlR3JSsNA9GGLoB5cK9aNOXgSokkmySTH4oKIFCWl9BaSmTdY0LZ0Efx730xGqYiCtznMhPD2_QGcVWSE6wyJeLXSXlSJxEtJ8Xg8JV0SKBko2_XefxDdbjoYZI-uWd32wiCiLT7DC3O0uXw1lgsTKiMONxTHeQMaQiR1s9ZXyiATdqwncbDvRVwMXAoz8LPL-_ymS65gGF1wU7jOg29KyG5V-SGKrX653frnn23DpjMkWafG_A6s4GgXNpbGC-7Cmttw_vy-B085vg69fDExsmGGil0jTtjV2GSsbTSQ9clrdpFB1lnMx2bCpcIpI6uW5SSsWU4eL53N9jTTw96C3u1N7-rOc-sUPBlm0dxLuQzK0kdOOj_hKlEZjyOFKk6E1FUpZImVTqu05DKONDmvohI6rqJSatL6Pt-H5mg8wgNgJQoCZCplbKbNVZjxRPJQJ6Gi51InbfA_wVtIN2rcbLx4KazL4WeFwUhhMFI4jLTh_OvJpJ6z8dfllkHB0sUa-m04_kRi4VhxVpA9Q2IpEqF_-MuzI1g3X68ry46hOZ8u8ARW5dt8OJueWir7AFStzrg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlR3JSsNA9OEG6sG1Yl3n4EmIJpkkkxxLVVxqUVKkt5DMvEFB29JF8O99Mx1FEQVvc5gh4e37AziqyAjXGRLxaqW9qBKJl5Li8XhKuiRQMlC26_2hJdrttNvN7lyzuu2FQURbfIYn5mhz-aovJyZURhxuKI7zWZg3q7Ncu9Zn0iATdrAn8bDvRVx0XRIz8LPT6_y8Tc5gGJ1wU7rOg29qyO5V-SGMrYa5WP3nv63BijMlWWOK-3WYwd4GLH8ZMLgBi27H-ePbJtzn-PLk5ZOBkQ4jVOwMccCafZOztvFA9kB-s4sNssZk3DczLhUOGdm1LCdxzXLyeels9qeZLvYadC7OO81Lzy1U8GSYRWMv5TIoSx85af2Eq0RlPI4UqjgRUlelkCVWOq3Skss40uS-ikrouIpKqUnv-3wL5nr9Hm4DK1EQIFMpYzNvrsKMJ5KHOgkVPZc6qYP_Ad5CumHjZufFc2GdDj8rDEYKg5HCYaQOx59PBtNJG39drhkUfLk4hX4d9j6QWDhmHBVk0ZBgikTo7_zy7BAWLzu3raJ11b7ZhSXzpWmd2R7MjYcT3IcF-Tp-Gg0PLMW9A0Px0gE
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=article&rft.atitle=Semi-Supervised+Deep+Conditional+Variational+Autoencoder+for+Soft+Sensor+Modeling&rft.jtitle=IEEE+sensors+journal&rft.au=Tang%2C+Xiaochu&rft.au=Yan%2C+Jiawei&rft.au=Li%2C+Yuan&rft.au=Zhang%2C+Xinmin&rft.date=2024-03-01&rft.pub=IEEE&rft.issn=1530-437X&rft.volume=24&rft.issue=5&rft.spage=7153&rft.epage=7164&rft_id=info:doi/10.1109%2FJSEN.2024.3351431&rft.externalDocID=10400433
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon