Soft Sensor Method based on Quality-related Virtual Sample Generation and Sample-weighted Learning

In process industry, data-driven soft sensor often faces the problem of data shortage in modeling due to factors such as high cost of label samples acquisition and high data repetition rate. The virtual sample generation (VSG) method has been proposed for data augmentation to solve the above problem...

Full description

Saved in:
Bibliographic Details
Published in:Data Driven Control and Learning Systems Conference (Online) pp. 1318 - 1324
Main Authors: Dong, Shuang, Jin, Huaiping, Wang, Bin, Yang, Biao, Liu, Haipeng
Format: Conference Proceeding
Language:English
Published: IEEE 17.05.2024
Subjects:
Accuracy
Data augmentation
Generative adversarial networks
Industries
Learning systems
Linear programming
Predictive models
Sample-weighted learning
Soft sensor
Soft sensors
Supervised variational autoencoder
Virtual sample generation
ISSN:2767-9861
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In process industry, data-driven soft sensor often faces the problem of data shortage in modeling due to factors such as high cost of label samples acquisition and high data repetition rate. The virtual sample generation (VSG) method has been proposed for data augmentation to solve the above problems. Most of the conventional generative models cannot generate virtual samples with labeled data, at the same time, previous data augmentation methods have ignored the quality differences of the generated virtual samples themselves. Thus, this paper proposes a soft sensor method based on quality-related virtual sample generation and sample-weighted learning (QRVSG-SWL). Firstly, this method combines the respective advantages of variational autoencoder (VAE) and generative adversarial network (GAN) to generate labeled virtual samples. Secondly, a prediction model is constructed using virtual samples to calculate the prediction accuracy and distribution differences on real labeled data. Then, sample similarity calculation under supervised latent structures.is performed. Finally, model learns virtual sample weights. The effectiveness of the proposed method is validated by the industrial chlortetracycline (CTC) fermentation process.
AbstractList In process industry, data-driven soft sensor often faces the problem of data shortage in modeling due to factors such as high cost of label samples acquisition and high data repetition rate. The virtual sample generation (VSG) method has been proposed for data augmentation to solve the above problems. Most of the conventional generative models cannot generate virtual samples with labeled data, at the same time, previous data augmentation methods have ignored the quality differences of the generated virtual samples themselves. Thus, this paper proposes a soft sensor method based on quality-related virtual sample generation and sample-weighted learning (QRVSG-SWL). Firstly, this method combines the respective advantages of variational autoencoder (VAE) and generative adversarial network (GAN) to generate labeled virtual samples. Secondly, a prediction model is constructed using virtual samples to calculate the prediction accuracy and distribution differences on real labeled data. Then, sample similarity calculation under supervised latent structures.is performed. Finally, model learns virtual sample weights. The effectiveness of the proposed method is validated by the industrial chlortetracycline (CTC) fermentation process.
Author Yang, Biao
Jin, Huaiping
Liu, Haipeng
Dong, Shuang
Wang, Bin
Author_xml – sequence: 1
  givenname: Shuang
  surname: Dong
  fullname: Dong, Shuang
  organization: Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Department of Automation,Kunming,China,650500
– sequence: 2
  givenname: Huaiping
  surname: Jin
  fullname: Jin, Huaiping
  email: jinhuaiping@gmail.com
  organization: Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Department of Automation,Kunming,China,650500
– sequence: 3
  givenname: Bin
  surname: Wang
  fullname: Wang, Bin
  organization: Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Department of Automation,Kunming,China,650500
– sequence: 4
  givenname: Biao
  surname: Yang
  fullname: Yang, Biao
  organization: Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Department of Automation,Kunming,China,650500
– sequence: 5
  givenname: Haipeng
  surname: Liu
  fullname: Liu, Haipeng
  organization: Kunming University of Science and Technology,Yunnan Key Laboratory of Artificial Intelligence,Kunming,China,650500
BookMark eNo1kMtKAzEYhaMoWGvfwEVeYGouM7kspdUqjIhMcVv-af60kWmmZCLSt3dEXR34zsdZnGtyEfuIhFDO5pwze7dcLupGcSXEXDBRzjlTTFWKnZGZ1dbIismx1eU5mQitdGGN4ldkNgwfjDFRcamsnJC26X2mDcahT_QF8753tIUBHe0jffuELuRTkbCDPKL3kPKIaAOHY4d0hRET5DCaEN0fLb4w7PY_do2QYoi7G3LpoRtw9pdTsn58WC-eivp19by4r4tgeS7Auq3n7dZw6UB67a1zTBsmDfeaQ6mYKV3rtbOVrXhVcjDISgdeglGuFXJKbn9nAyJujikcIJ02_6_Ib-XnWhE
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/DDCLS61622.2024.10606560
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350361674
EISSN 2767-9861
EndPage 1324
ExternalDocumentID 10606560
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China (NSFC)
  grantid: 62163019
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IF
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i91t-a9dcf1bc813da3f7f9dd0780381f71a46084dbf7d95951541a8e04daf3a86db23
IEDL.DBID RIE
IngestDate Wed Aug 27 02:33:51 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i91t-a9dcf1bc813da3f7f9dd0780381f71a46084dbf7d95951541a8e04daf3a86db23
PageCount 7
ParticipantIDs ieee_primary_10606560
PublicationCentury 2000
PublicationDate 2024-May-17
PublicationDateYYYYMMDD 2024-05-17
PublicationDate_xml – month: 05
  year: 2024
  text: 2024-May-17
  day: 17
PublicationDecade 2020
PublicationTitle Data Driven Control and Learning Systems Conference (Online)
PublicationTitleAbbrev DDCLS
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002513693
Score 1.8700716
Snippet In process industry, data-driven soft sensor often faces the problem of data shortage in modeling due to factors such as high cost of label samples acquisition...
SourceID ieee
SourceType Publisher
StartPage 1318
SubjectTerms Accuracy
Data augmentation
Generative adversarial networks
Industries
Learning systems
Linear programming
Predictive models
Sample-weighted learning
Soft sensor
Soft sensors
Supervised variational autoencoder
Virtual sample generation
Title Soft Sensor Method based on Quality-related Virtual Sample Generation and Sample-weighted Learning
URI https://ieeexplore.ieee.org/document/10606560
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELVoxcAEiCK-5YHVpY5df8wtiKFUlVJV3So7Z6MuCQotiH-P7aRFDAxs1smRIp-Sd7679w6he8WMtMIIEhmvhHOTEZsBJ5kIwbkKITCkrsrFRE6narnUs5asnrgwzrnUfOb6cZlq-VAV25gqC194CLcDRHdQR0rZkLX2CZUA1ExotuvWGeiH8Xg0yQUVWSRcZby_e_zXIJWEI0_H_3yDE9T7YeTh2R5rTtGBK8-QzcM_FOfhIlrV-CWNgsYRlQBXJW7EMb5IIqsE02JdR6oIzk3UA8aN3HT0CjYltFbymRKlYXcru_raQ_Onx_nombQzE8ha0w0xGgpPbaEoA8O89BogBAGxHOglNVwMFAfrJehhCK2GnBrlBhyMZ0bFyVLsHHXLqnQXCEsdr4MsM4bTgPKgvIfMqqHmghqr4BL14vms3hpVjNXuaK7-sF-jo-iFWHmn8gZ1N_XW3aLD4mOzfq_vki-_AeMNn0w
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46BT2pOPG3OXjNXH40Tc6bY2I3Bh1jt5E2iezSjrop_vcmaTfx4MFbeIRS8mi_l_fe9z0AHgVVccYVR57xihhTBGVEM0S4C86FC4F16KqcJfF4LOZzOWnI6oELY4wJzWem45ehlq_LfONTZe4Ld-G2g-h9cBAxRnBN19qlVBxUUy7ptl-nK5_6_V6ScsyJp1wR1tk-4NcolYAkg5N_vsMpaP9w8uBkhzZnYM8U5yBL3V8Upu4qWlZwFIZBQ49LGpYFrOUxvlCgqzjTbFl5sghMlVcEhrXgtPcLVIVurOgzpErd7kZ49a0NpoPnaW-ImqkJaCnxGimpc4uzXGCqFbWxlVq7MMAXBG2MFeNdwXRmYy0jF1xFDCthukwrS5Xws6XoBWgVZWEuAYylvxBSohTDDue1sFaTTESScawyoa9A25_PYlXrYiy2R3P9h_0BHA2no2SRvIxfb8Cx94ivw-P4FrTW1cbcgcP8Y718r-6DX78BWpSikw
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%3Abook&rft.genre=proceeding&rft.title=Data+Driven+Control+and+Learning+Systems+Conference+%28Online%29&rft.atitle=Soft+Sensor+Method+based+on+Quality-related+Virtual+Sample+Generation+and+Sample-weighted+Learning&rft.au=Dong%2C+Shuang&rft.au=Jin%2C+Huaiping&rft.au=Wang%2C+Bin&rft.au=Yang%2C+Biao&rft.date=2024-05-17&rft.pub=IEEE&rft.eissn=2767-9861&rft.spage=1318&rft.epage=1324&rft_id=info:doi/10.1109%2FDDCLS61622.2024.10606560&rft.externalDocID=10606560