Fuzzy-Constrained Incremental Random Weight Network for Industrial Process Soft Sensing

Data-driven modeling has emerged as a powerful approach for soft sensing of key performance indices in industrial processes. This approach can leverage the collected process data to establish precise soft sensors without requiring explicit physical knowledge. To cope with uncertainties and nonlinear...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE sensors journal Jg. 25; H. 20; S. 38154 - 38167
Hauptverfasser:	Wang, Qianjin, Luo, Yunfeng, Dai, Wei, Ma, Xiaoping
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 15.10.2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Adaptation models Artificial neural networks Chaos theory Clustering Compact constraint Constraints Data mining Data processing Data-driven modeling Datasets Dynamical systems Fuzzy logic Fuzzy neural networks Greville’s method incremental random weight network (RWN) industrial process soft sensing Intelligent sensors Modelling Nonlinear dynamics Nonlinearity Optimization Performance evaluation Performance indices Soft sensors Subsystems System identification Takagi-Sugeno model Takagi–Sugeno (T–S) fuzzy system Training
ISSN:	1530-437X, 1558-1748
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Data-driven modeling has emerged as a powerful approach for soft sensing of key performance indices in industrial processes. This approach can leverage the collected process data to establish precise soft sensors without requiring explicit physical knowledge. To cope with uncertainties and nonlinearities present in industrial process data, a novel fuzzy randomized incremental model named fuzzy compact constraint-based incremental random weight network (F-CCIRWN) is proposed for industrial process soft sensing by integrating the Takagi-Sugeno (T-S) fuzzy system into CCIRWN. Specifically, all inputs from the input layer are sent to a set of T-S fuzzy subsystems to enhance fuzzy reasoning capability. The defuzzification outputs produced by the fuzzy subsystem layer are directly linked to the output layer. Additionally, the fully connected layer is introduced between the fuzzy subsystem and output layers to perform nonlinear transformation. Then, the fuzzy c-means approach is adopted to estimate the clustering centers of Gaussian membership functions and determine the number of the fuzzy subsystem rules associated with the fuzzy subsystem layer. Subsequently, the Greville's method is employed to design a compact constraint that is capable of effectively choosing the well-performed random parameters in the fully connected layer. Finally, the comprehensive performance evaluation of the proposed F-CCIRWN is conducted on nonlinear dynamic system identification, chaotic time sequence prediction, and data-driven modeling based on real-world benchmark datasets and an industrial dataset. The results indicate that the proposed F-CCIRWN is more suitable for industrial process soft sensing compared to some other state-of-the-art modeling methods.
AbstractList	Data-driven modeling has emerged as a powerful approach for soft sensing of key performance indices in industrial processes. This approach can leverage the collected process data to establish precise soft sensors without requiring explicit physical knowledge. To cope with uncertainties and nonlinearities present in industrial process data, a novel fuzzy randomized incremental model named fuzzy compact constraint-based incremental random weight network (F-CCIRWN) is proposed for industrial process soft sensing by integrating the Takagi-Sugeno (T-S) fuzzy system into CCIRWN. Specifically, all inputs from the input layer are sent to a set of T-S fuzzy subsystems to enhance fuzzy reasoning capability. The defuzzification outputs produced by the fuzzy subsystem layer are directly linked to the output layer. Additionally, the fully connected layer is introduced between the fuzzy subsystem and output layers to perform nonlinear transformation. Then, the fuzzy c-means approach is adopted to estimate the clustering centers of Gaussian membership functions and determine the number of the fuzzy subsystem rules associated with the fuzzy subsystem layer. Subsequently, the Greville's method is employed to design a compact constraint that is capable of effectively choosing the well-performed random parameters in the fully connected layer. Finally, the comprehensive performance evaluation of the proposed F-CCIRWN is conducted on nonlinear dynamic system identification, chaotic time sequence prediction, and data-driven modeling based on real-world benchmark datasets and an industrial dataset. The results indicate that the proposed F-CCIRWN is more suitable for industrial process soft sensing compared to some other state-of-the-art modeling methods.
Author	Ma, Xiaoping Wang, Qianjin Luo, Yunfeng Dai, Wei
Author_xml	– sequence: 1 givenname: Qianjin orcidid: 0000-0002-4076-9493 surname: Wang fullname: Wang, Qianjin email: wangqianjinabc@163.com organization: School of Electrical Engineering, Yancheng Institute of Technology, Yancheng, China – sequence: 2 givenname: Yunfeng orcidid: 0009-0000-8180-9212 surname: Luo fullname: Luo, Yunfeng email: yunfengluoabc@163.com organization: School of Electrical Engineering, Yancheng Institute of Technology, Yancheng, China – sequence: 3 givenname: Wei orcidid: 0000-0003-3057-7225 surname: Dai fullname: Dai, Wei email: weidai@cumt.edu.cn organization: School of Information and Control Engineering and the Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China – sequence: 4 givenname: Xiaoping orcidid: 0000-0003-1692-8797 surname: Ma fullname: Ma, Xiaoping email: xiaopingmacumt@126.com organization: School of Information and Control Engineering and the Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China
BookMark	eNpFkF1PwjAUhhuDiYD-ABMvlng97OnHul0aAoghaESDd83oWhxCi-0WA7_eLZB4dc7F85w35-2hjnVWI3QLeACAs4fnxWg-IJjwAU1wkqbpBeoC52kMgqWddqc4ZlR8XqFeCBuMIRNcdNFyXB-Ph3jobKh8XlpdRFOrvN5pW-Xb6C23hdtFS12uv6porqtf578j43xDFXWjlA306p3SIUQLZ6pooW0o7foaXZp8G_TNefbRx3j0PnyKZy-T6fBxFivC0ioGpohRRJmMElUUmBAwxJh8hVeq_YblGSZCFRy4YDjjXBtmEqC0sXlmGO2j-9PdvXc_tQ6V3Lja2yZSUpIAI1yIrKHgRCnvQvDayL0vd7k_SMCy7U-2_ck2UZ77a5y7k1Nqrf95gIQmBOgfKzduGQ
CODEN	ISJEAZ
Cites_doi	10.1109/JAS.2024.124578 10.1109/TCYB.2017.2734043 10.1016/j.ins.2016.12.007 10.1016/j.knosys.2021.106924 10.1016/j.asoc.2025.113623 10.1109/JSEN.2025.3538942 10.1109/TNNLS.2021.3071292 10.1109/TII.2024.3488777 10.1007/s10462-022-10188-3 10.1109/TII.2023.3297663 10.1109/JSEN.2023.3312614 10.1016/j.asoc.2023.110377 10.1109/TCYB.2019.2925883 10.1109/TSMC.2020.3013972 10.1016/j.knosys.2024.111481 10.1109/TNNLS.2020.2967816 10.1109/TIM.2024.3470037 10.1109/TNNLS.2022.3186671 10.1109/TNNLS.2023.3347767 10.1109/ISPCE-ASIA64773.2024.10756219 10.1142/S012906572150057X 10.1109/JSEN.2025.3550793 10.3390/s24123909 10.1109/TII.2019.2954351 10.1109/TCYB.2023.3263215 10.1109/TII.2023.3329684 10.1109/TFUZZ.2024.3449147 10.1109/JSEN.2024.3447730 10.1109/TII.2023.3301059 10.1109/TFUZZ.2023.3315368 10.1109/TII.2022.3181692 10.1109/TIA.2024.3462696 10.1109/TCSS.2022.3152091 10.1109/JSEN.2024.3498056 10.1109/TII.2021.3096840 10.1016/j.neucom.2024.127833 10.1007/s10462-017-9610-2 10.1109/TNNLS.2023.3334150 10.1109/TNNLS.2021.3053306 10.1109/TNNLS.2023.3289798 10.1109/TII.2024.3438234 10.1109/TII.2017.2734686
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/JSEN.2025.3606888
DatabaseName	IEEE Xplore (IEEE) 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: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography Engineering
EISSN	1558-1748
EndPage	38167
ExternalDocumentID	10_1109_JSEN_2025_3606888 11163621
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 62003293; U24A20272; 62373361 funderid: 10.13039/501100001809 – fundername: Postgraduate Research and Practice Innovation Program of Yancheng Institute of Technology grantid: KYCX24-XZ014 – fundername: Qinglan Project of Jiangsu Province – fundername: Nature Science Foundation of Jiangsu Province grantid: BK20240102 – fundername: Key Research and Development projects in Shanxi Province grantid: 202202100401002
GroupedDBID	-~X 0R~ 29I 4.4 5GY 6IK 97E AAJGR 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 O9- OCL P2P RIA RIE RNS TWZ AAYXX CITATION M43 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c248t-14c2fc2cf932cdd0221f2ffab0bc20254a9027cd515740955ef4f613324859f43
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001594949900049&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	Thu Nov 20 00:53:56 EST 2025 Sat Nov 29 07:06:58 EST 2025 Sat Oct 25 03:12:30 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	20
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-c248t-14c2fc2cf932cdd0221f2ffab0bc20254a9027cd515740955ef4f613324859f43
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-4076-9493 0009-0000-8180-9212 0000-0003-3057-7225 0000-0003-1692-8797
PQID	3261425779
PQPubID	75733
PageCount	14
ParticipantIDs	proquest_journals_3261425779 ieee_primary_11163621 crossref_primary_10_1109_JSEN_2025_3606888
PublicationCentury	2000
PublicationDate	2025-10-15
PublicationDateYYYYMMDD	2025-10-15
PublicationDate_xml	– month: 10 year: 2025 text: 2025-10-15 day: 15
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE sensors journal
PublicationTitleAbbrev	JSEN
PublicationYear	2025
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 ref37 ref14 ref36 ref31 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 ref39 ref16 ref38 ref19 ref18 ref23 ref26 ref25 ref20 ref42 ref41 ref22 ref21 ref43 Broomhead (ref24) 1988; 2 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40
References_xml	– ident: ref3 doi: 10.1109/JAS.2024.124578 – ident: ref27 doi: 10.1109/TCYB.2017.2734043 – ident: ref26 doi: 10.1016/j.ins.2016.12.007 – ident: ref28 doi: 10.1016/j.knosys.2021.106924 – volume: 2 start-page: 321 year: 1988 ident: ref24 article-title: Multivariable functional interpolation and adaptive networks publication-title: Complex Syst. – ident: ref40 doi: 10.1016/j.asoc.2025.113623 – ident: ref2 doi: 10.1109/JSEN.2025.3538942 – ident: ref7 doi: 10.1109/TNNLS.2021.3071292 – ident: ref5 doi: 10.1109/TII.2024.3488777 – ident: ref20 doi: 10.1007/s10462-022-10188-3 – ident: ref23 doi: 10.1109/TII.2023.3297663 – ident: ref12 doi: 10.1109/JSEN.2023.3312614 – ident: ref25 doi: 10.1016/j.asoc.2023.110377 – ident: ref31 doi: 10.1109/TCYB.2019.2925883 – ident: ref1 doi: 10.1109/TSMC.2020.3013972 – ident: ref18 doi: 10.1016/j.knosys.2024.111481 – ident: ref33 doi: 10.1109/TNNLS.2020.2967816 – ident: ref43 doi: 10.1109/TIM.2024.3470037 – ident: ref17 doi: 10.1109/TNNLS.2022.3186671 – ident: ref6 doi: 10.1109/TNNLS.2023.3347767 – ident: ref16 doi: 10.1109/ISPCE-ASIA64773.2024.10756219 – ident: ref41 doi: 10.1142/S012906572150057X – ident: ref4 doi: 10.1109/JSEN.2025.3550793 – ident: ref22 doi: 10.3390/s24123909 – ident: ref34 doi: 10.1109/TII.2019.2954351 – ident: ref13 doi: 10.1109/TCYB.2023.3263215 – ident: ref9 doi: 10.1109/TII.2023.3329684 – ident: ref15 doi: 10.1109/TFUZZ.2024.3449147 – ident: ref19 doi: 10.1109/JSEN.2024.3447730 – ident: ref29 doi: 10.1109/TII.2023.3301059 – ident: ref36 doi: 10.1109/TFUZZ.2023.3315368 – ident: ref21 doi: 10.1109/TII.2022.3181692 – ident: ref30 doi: 10.1109/TIA.2024.3462696 – ident: ref10 doi: 10.1109/TCSS.2022.3152091 – ident: ref11 doi: 10.1109/JSEN.2024.3498056 – ident: ref32 doi: 10.1109/TII.2021.3096840 – ident: ref38 doi: 10.1016/j.neucom.2024.127833 – ident: ref42 doi: 10.1007/s10462-017-9610-2 – ident: ref14 doi: 10.1109/TNNLS.2023.3334150 – ident: ref35 doi: 10.1109/TNNLS.2021.3053306 – ident: ref37 doi: 10.1109/TNNLS.2023.3289798 – ident: ref39 doi: 10.1109/TII.2024.3438234 – ident: ref8 doi: 10.1109/TII.2017.2734686
SSID	ssj0019757
Score	2.4417305
Snippet	Data-driven modeling has emerged as a powerful approach for soft sensing of key performance indices in industrial processes. This approach can leverage the...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Index Database Publisher
StartPage	38154
SubjectTerms	Adaptation models Artificial neural networks Chaos theory Clustering Compact constraint Constraints Data mining Data processing Data-driven modeling Datasets Dynamical systems Fuzzy logic Fuzzy neural networks Greville’s method incremental random weight network (RWN) industrial process soft sensing Intelligent sensors Modelling Nonlinear dynamics Nonlinearity Optimization Performance evaluation Performance indices Soft sensors Subsystems System identification Takagi-Sugeno model Takagi–Sugeno (T–S) fuzzy system Training
Title	Fuzzy-Constrained Incremental Random Weight Network for Industrial Process Soft Sensing
URI	https://ieeexplore.ieee.org/document/11163621 https://www.proquest.com/docview/3261425779
Volume	25
WOSCitedRecordID	wos001594949900049&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: IEEE Electronic Library (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/eLvHCXMwlV1LT8MwDI5gQgIOPMYQg4Fy4ISUrU3TR44IbUIIVYgB261q8wAOdGgPpO3X46QZAyEO3Hpo08qu7c9O7A-hcz9QXi6kIhHXIWFKCgI4jhNZBL6KFEQIS53wdBunaTIc8jvXrG57YZRS9vCZaptLu5cvR2JmSmUdsMsIHC4kO-txHFfNWl9bBjy2Yz3Bgj3CgnjotjB9j3du-t0UUkEatoPIkKwkP4KQZVX55YptfOnt_vPL9tCOA5L4stL8PlpTZR1tfxsvWEebjuH8ZX6ABr3ZYjEnhp_TskIoicE1VMVBWOY-L-XoDQ9soRSn1dlwDIAWr7g9sGsqwH1w3bhvTr6Xzw302Os-XF0TR6pABGXJlPhMUC2o0ADchJQQwn1Ntc4LrxBGRCznkKkKCTgnZmY-ndJMQ8wPzOwzrllwiGrlqFRHCHuhguQFMFiRUJaDu2KJzKn2qSc0qD9pooullLP3anZGZnMOj2dGJZl5X-ZU0kQNI9bVjU6iTdRaKiZz5jXJAHP6xtnE_PiPx07QllndRBk_bKHadDxTp2hDfExfJ-Mz--d8Ak-FwOE
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLYQIAEH3ojxzIETUqBJ07U5IsTEY1SI8dit6vIADnRobEjw63HS8BLiwK2HNqnsxP4cx_4AdlhsolJpQ5vSJlQYrSjiOEl1L2amadBDeOqEm3aa51m3Ky9CsbqvhTHG-MtnZs89-ly-7quROyrbx33ZRIOLwc5EIgRndbnWZ9JApr6xJ-7hiIo47YYkJovk_mnnKMdgkCd7cdPRrGQ_3JDnVflljL2Hac3989_mYTZASXJQ634Bxky1CDPfGgwuwlTgOL9_XYLb1ujt7ZU6hk7PC2E0QeNQHw_iMJdlpfuP5NYflZK8vh1OENKSL3YPEsoKSAeNN-m4u-_V3TJct46uDo9poFWgiotsSJlQ3CquLEI3pTU6cWa5tWUv6iknIlFKjFWVRqSTCtehzlhh0evHrvuZtCJegfGqX5lVIFFiMHxBFNbLuCjRYIlMl9wyHimLCyBrwO6HlIununtG4aOOSBZOJYWbrwgqacCyE-vXi0GiDdj4UEwRNthzgaiTOXOTyrU_PtuGqeOr83bRPsnP1mHazeR8Dks2YHw4GJlNmFQvw4fnwZZfRe-EkcQo
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=Fuzzy-Constrained+Incremental+Random+Weight+Network+for+Industrial+Process+Soft+Sensing&rft.jtitle=IEEE+sensors+journal&rft.au=Wang%2C+Qianjin&rft.au=Luo%2C+Yunfeng&rft.au=Dai%2C+Wei&rft.au=Ma%2C+Xiaoping&rft.date=2025-10-15&rft.pub=IEEE&rft.issn=1530-437X&rft.volume=25&rft.issue=20&rft.spage=38154&rft.epage=38167&rft_id=info:doi/10.1109%2FJSEN.2025.3606888&rft.externalDocID=11163621
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