Fast just-in-time-learning recursive multi-output LSSVR for quality prediction and control of multivariable dynamic systems

Aiming at quality prediction and control of blast furnace (BF) ironmaking process characterized by complicated nonlinear time-varying dynamics, this paper proposes a just-in-time-learning (JITL) recursive multi-output least squares support vector regression (JITL-R-M-LSSVR) algorithm with fast nonli...

Full description

Saved in:

Bibliographic Details
Published in:	Engineering applications of artificial intelligence Vol. 100; p. 104168
Main Authors:	Zhou, Ping, Chen, Weiqi, Yi, Chengming, Jiang, Zhaohui, Yang, Tao, Chai, Tianyou
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01.04.2021
Subjects:	Blast furnace ironmaking process Incremental learning Just-in-time-learning (JITL) Local learning nonlinear modeling Model verification Multi-output LSSVR (M-LSSVR) Nonlinear predictive control Incremental learning Blast furnace ironmaking process Just-in-time-learning (JITL) Multi-output LSSVR (M-LSSVR) Model verification Local learning nonlinear modeling Nonlinear predictive control
ISSN:	0952-1976, 1873-6769
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Aiming at quality prediction and control of blast furnace (BF) ironmaking process characterized by complicated nonlinear time-varying dynamics, this paper proposes a just-in-time-learning (JITL) recursive multi-output least squares support vector regression (JITL-R-M-LSSVR) algorithm with fast nonlinear local learning capability for multivariable dynamic systems. The proposed fast JITL-R-M-LSSVR effectively combines the online local learning of JITL with the multi-output LSSVR (M-LSSVR) based on multi-task transfer learning, and focuses on how to ensure the rapid verification of the local model during online learning of M-LSSVR, and how to perform model pruning while recursively updating the model parameters to improve the calculation efficiency. To this end, the proposed algorithm uses a derived multi-output incremental learning algorithm to recursively update model parameters online in a gentle way, which has better modeling stability and smoothness than the traditional way that discards old models. At the same time, when the model is pruned, a novel multi-output reverse decremental learning algorithm is proposed to adaptively delete the modeling data, so as to effectively control the sample size and reduces the calculation cost. In particular, the model verification of the proposed algorithm only needs to construct the M-LSSVR modeling matrix and the matrix inverse operation once, and the matrix after deleting each modeling sample can be easily obtained by reverse decremental learning of the original modeling matrix, which can achieve fast and efficient model verification. Finally, the effectiveness and practicability of the proposed method are verified by applying it to prediction modeling and predictive control of the molten iron quality in BF ironmaking process. •A fast just-in-time-learning recursive multi-output LSSVR algorithm is proposed.•Fast nonlinear local M-LSSVR modeling of MIMO dynamic systems is achieved online.•Efficient pruning of M-LSSVR is performed by multi-output decremental learning.•Local M-LSSVR model is recursively updated by multi-output incremental learning.•Model verification only computes the modeling matrix and its inverse operation once.
AbstractList	Aiming at quality prediction and control of blast furnace (BF) ironmaking process characterized by complicated nonlinear time-varying dynamics, this paper proposes a just-in-time-learning (JITL) recursive multi-output least squares support vector regression (JITL-R-M-LSSVR) algorithm with fast nonlinear local learning capability for multivariable dynamic systems. The proposed fast JITL-R-M-LSSVR effectively combines the online local learning of JITL with the multi-output LSSVR (M-LSSVR) based on multi-task transfer learning, and focuses on how to ensure the rapid verification of the local model during online learning of M-LSSVR, and how to perform model pruning while recursively updating the model parameters to improve the calculation efficiency. To this end, the proposed algorithm uses a derived multi-output incremental learning algorithm to recursively update model parameters online in a gentle way, which has better modeling stability and smoothness than the traditional way that discards old models. At the same time, when the model is pruned, a novel multi-output reverse decremental learning algorithm is proposed to adaptively delete the modeling data, so as to effectively control the sample size and reduces the calculation cost. In particular, the model verification of the proposed algorithm only needs to construct the M-LSSVR modeling matrix and the matrix inverse operation once, and the matrix after deleting each modeling sample can be easily obtained by reverse decremental learning of the original modeling matrix, which can achieve fast and efficient model verification. Finally, the effectiveness and practicability of the proposed method are verified by applying it to prediction modeling and predictive control of the molten iron quality in BF ironmaking process. •A fast just-in-time-learning recursive multi-output LSSVR algorithm is proposed.•Fast nonlinear local M-LSSVR modeling of MIMO dynamic systems is achieved online.•Efficient pruning of M-LSSVR is performed by multi-output decremental learning.•Local M-LSSVR model is recursively updated by multi-output incremental learning.•Model verification only computes the modeling matrix and its inverse operation once.
ArticleNumber	104168
Author	Chen, Weiqi Yi, Chengming Zhou, Ping Yang, Tao Chai, Tianyou Jiang, Zhaohui
Author_xml	– sequence: 1 givenname: Ping surname: Zhou fullname: Zhou, Ping email: zhouping@mail.neu.edu.cn organization: State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang 110819, PR China – sequence: 2 givenname: Weiqi surname: Chen fullname: Chen, Weiqi organization: State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang 110819, PR China – sequence: 3 givenname: Chengming surname: Yi fullname: Yi, Chengming organization: State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang 110819, PR China – sequence: 4 givenname: Zhaohui surname: Jiang fullname: Jiang, Zhaohui organization: School of Automation, Central South University, Changsha, 410083, PR China – sequence: 5 givenname: Tao surname: Yang fullname: Yang, Tao organization: State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang 110819, PR China – sequence: 6 givenname: Tianyou surname: Chai fullname: Chai, Tianyou organization: State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang 110819, PR China
BookMark	eNqFkNFq2zAUhsVoYUnbVxh6AWWSlcg27GKjLG0hUGjX3ooT-bicYEueJAfMXr4O2W52U87FDwe-H_5vyS588MjYFyVXSirz9bBC_wbDALQqZKHm51qZ6hNbqKrUwpSmvmALWW8KoerSfGbLlA5SSl2tzYL92ULK_DCmLMiLTD2KDiF68m88ohtjoiPyfuwyiTDmYcx89_z8-sTbEPnvETrKEx8iNuQyBc_BN9wFn2PoeGjP4BEiwb5D3kweenI8TSljn67ZZQtdwpu_ecVetj9_3d6L3ePdw-2PnXBaFVnMaySaGveVaVq5ma9ooNVYaV1rV26wLAHR7fd1BWptVO1k3VYbbdYoGyNBXzFz7nUxpBSxtUOkHuJklbQnhfZg_ym0J4X2rHAGv_0HOspw2pkjUPcx_v2M4zzuSBhtcoTezbJmtdk2gT6qeAfMkpb2
CitedBy_id	crossref_primary_10_1016_j_jprocont_2023_01_010 crossref_primary_10_1109_TIM_2024_3353852 crossref_primary_10_1016_j_cie_2023_109278 crossref_primary_10_3390_sym16080977 crossref_primary_10_1016_j_engappai_2021_104341 crossref_primary_10_20965_jaciii_2024_p0284 crossref_primary_10_1016_j_chemolab_2023_104778 crossref_primary_10_1016_j_conengprac_2024_105940 crossref_primary_10_1016_j_engappai_2023_105849 crossref_primary_10_1016_j_anucene_2021_108544 crossref_primary_10_1016_j_engappai_2022_105547 crossref_primary_10_1016_j_conengprac_2022_105328 crossref_primary_10_1109_TSM_2022_3202610 crossref_primary_10_1007_s40831_024_00785_7 crossref_primary_10_1016_j_knosys_2025_113497 crossref_primary_10_1016_j_compchemeng_2025_109002 crossref_primary_10_1109_TIM_2022_3185325 crossref_primary_10_1016_j_jprocont_2023_103032 crossref_primary_10_1016_j_egyr_2023_05_093 crossref_primary_10_1631_FITEE_2200366 crossref_primary_10_1016_j_chemolab_2024_105083 crossref_primary_10_1002_cjce_25169
Cites_doi	10.3724/SP.J.1004.2013.00602 10.1016/S0952-1976(02)00024-6 10.1016/j.engappai.2005.05.006 10.1016/j.jprocont.2007.04.004 10.1021/ie0608713 10.1109/TIE.2017.2772141 10.1109/TCST.2016.2631124 10.1016/S0952-1976(00)00062-2 10.1016/j.jprocont.2009.04.002 10.1016/j.jprocont.2016.04.009 10.1016/j.jprocont.2020.05.012 10.1002/aic.11791 10.1016/j.compchemeng.2010.01.005 10.1109/TNNLS.2017.2749412 10.1109/CICN.2016.97 10.1016/j.automatica.2009.06.028 10.1016/j.jprocont.2013.03.008 10.1016/j.ces.2004.04.020 10.1016/j.conengprac.2020.104474 10.1016/j.conengprac.2019.104120 10.1016/j.jprocont.2018.04.008
ContentType	Journal Article
Copyright	2021 Elsevier Ltd
Copyright_xml	– notice: 2021 Elsevier Ltd
DBID	AAYXX CITATION
DOI	10.1016/j.engappai.2021.104168
DatabaseName	CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences Computer Science
EISSN	1873-6769
ExternalDocumentID	10_1016_j_engappai_2021_104168 S0952197621000154
GroupedDBID	--K --M .DC .~1 0R~ 1B1 1~. 1~5 29G 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABMAC ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SES SET SEW SPC SPCBC SST SSV SSZ T5K TN5 UHS WUQ ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABJNI ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD
ID	FETCH-LOGICAL-c312t-4160e69eb86df050502daf3e83393c75e77aeecbb98a14619c09f85364e0d60a3
ISICitedReferencesCount	23
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000633002300010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0952-1976
IngestDate	Sat Nov 29 07:07:18 EST 2025 Tue Nov 18 21:51:39 EST 2025 Fri Feb 23 02:45:08 EST 2024
IsPeerReviewed	true
IsScholarly	true
Keywords	Incremental learning Blast furnace ironmaking process Just-in-time-learning (JITL) Multi-output LSSVR (M-LSSVR) Model verification Local learning nonlinear modeling Nonlinear predictive control
Language	English
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c312t-4160e69eb86df050502daf3e83393c75e77aeecbb98a14619c09f85364e0d60a3
ParticipantIDs	crossref_primary_10_1016_j_engappai_2021_104168 crossref_citationtrail_10_1016_j_engappai_2021_104168 elsevier_sciencedirect_doi_10_1016_j_engappai_2021_104168
PublicationCentury	2000
PublicationDate	April 2021 2021-04-00
PublicationDateYYYYMMDD	2021-04-01
PublicationDate_xml	– month: 04 year: 2021 text: April 2021
PublicationDecade	2020
PublicationTitle	Engineering applications of artificial intelligence
PublicationYear	2021
Publisher	Elsevier Ltd
Publisher_xml	– name: Elsevier Ltd
References	Zhou, Song, Wang, Chai (b29) 2017; 25 Zhang, R.W., Tian, X.M., Wang, P., 2016. Adaptive generalized predictive control based on just-in-time learning in latent space. In: 2016 8th International Conference on Computational Intelligence and Communication Networks. CICN. pp. 471–475. Fujiwara, Kano, Hasebe, Takinami (b8) 2009; 55 Ghaemi, Sun, Kolmanovsky (b10) 2009; 45 Dong, Krzyzak, Suen (b7) 2002; 15 Song (b21) 2016 Yin, Li, Liu (b25) 2020; 88 Zhou, Guo, Wang, Chai (b28) 2018; 29 Gamero, Colomer, Meléndez, Warren (b9) 2006; 19 An, Shen, Wu, She (b2) 2019 Pan, Li, Cai (b20) 2007; 46 Marutiram, Radhikrishnan (b19) 1991 Zeng, Gao, Su (b26) 2010; 34 Bontempi (b3) 1999 Guo, Bai, Huang (b11) 2020; 92 Jiang, Yin, Kaynak (b12) 2020 An, Chen, Wu, He, She (b1) 2020 Kalmukale, Chiu, Wang (b13) 2007; 17 Li, Hua, Yang, Guan (b16) 2020 Zhou, Zhang, Yang (b30) 2019 Su, Hermanto, Braatz, Chiu (b22) 2016; 43 Yi, Zhou, Chai (b24) 2020; 37 Kansha, Chiu (b14) 2009; 19 Bontempi, Birattari (b4) 2005; 3 Li, Hua, Yang, Guan (b15) 2018; 65 Cheng, Chiu (b6) 2004; 59 Chen (b5) 2001; 14 Wang, Yang, Sun, Zhang, Li (b23) 2018; 68 Liu, Chen (b17) 2013; 23 Liu, Jin, Gao (b18) 2013; 39 Chen (10.1016/j.engappai.2021.104168_b5) 2001; 14 Bontempi (10.1016/j.engappai.2021.104168_b3) 1999 Li (10.1016/j.engappai.2021.104168_b16) 2020 Pan (10.1016/j.engappai.2021.104168_b20) 2007; 46 Zhou (10.1016/j.engappai.2021.104168_b28) 2018; 29 An (10.1016/j.engappai.2021.104168_b2) 2019 Marutiram (10.1016/j.engappai.2021.104168_b19) 1991 Fujiwara (10.1016/j.engappai.2021.104168_b8) 2009; 55 10.1016/j.engappai.2021.104168_b27 Jiang (10.1016/j.engappai.2021.104168_b12) 2020 Yi (10.1016/j.engappai.2021.104168_b24) 2020; 37 Bontempi (10.1016/j.engappai.2021.104168_b4) 2005; 3 Dong (10.1016/j.engappai.2021.104168_b7) 2002; 15 Kansha (10.1016/j.engappai.2021.104168_b14) 2009; 19 Wang (10.1016/j.engappai.2021.104168_b23) 2018; 68 Li (10.1016/j.engappai.2021.104168_b15) 2018; 65 Song (10.1016/j.engappai.2021.104168_b21) 2016 Cheng (10.1016/j.engappai.2021.104168_b6) 2004; 59 Zhou (10.1016/j.engappai.2021.104168_b30) 2019 Guo (10.1016/j.engappai.2021.104168_b11) 2020; 92 Yin (10.1016/j.engappai.2021.104168_b25) 2020; 88 Liu (10.1016/j.engappai.2021.104168_b18) 2013; 39 Su (10.1016/j.engappai.2021.104168_b22) 2016; 43 Liu (10.1016/j.engappai.2021.104168_b17) 2013; 23 Kalmukale (10.1016/j.engappai.2021.104168_b13) 2007; 17 Ghaemi (10.1016/j.engappai.2021.104168_b10) 2009; 45 An (10.1016/j.engappai.2021.104168_b1) 2020 Zeng (10.1016/j.engappai.2021.104168_b26) 2010; 34 Zhou (10.1016/j.engappai.2021.104168_b29) 2017; 25 Gamero (10.1016/j.engappai.2021.104168_b9) 2006; 19
References_xml	– year: 2019 ident: b30 article-title: Hybrid model based intelligent optimization of ironmaking process publication-title: IEEE Trans. Ind. Electron. – volume: 34 start-page: 1854 year: 2010 end-page: 1862 ident: b26 article-title: Data-driven predictive control for blast furnace ironmaking process publication-title: Comput. Chem. Eng. – volume: 65 start-page: 4933 year: 2018 end-page: 4942 ident: b15 article-title: Bayesian block structure sparse based T–S fuzzy modeling for dynamic prediction of hot metal silicon content in the blast furnace publication-title: IEEE Trans. Ind. Electron. – volume: 25 start-page: 1761 year: 2017 end-page: 1774 ident: b29 article-title: Data-driven nonlinear subspace modeling for prediction and control of molten iron quality indices in blast furnace ironmaking publication-title: IEEE Trans. Control Syst. Technol. – year: 2020 ident: b12 article-title: Optimized design of parity relation based residual generator for fault detection: data-driven approaches publication-title: IEEE Trans. Ind. Inf. – year: 2016 ident: b21 article-title: Subspace Modeling and Predictive Control of Multivariate Molten Iron Quality Indices in Blast Furnace Ironmaking Processes – volume: 15 start-page: 151 year: 2002 end-page: 159 ident: b7 article-title: Local learning framework for handwritten character recognition publication-title: Eng. Appl. Artif. Intell. – reference: Zhang, R.W., Tian, X.M., Wang, P., 2016. Adaptive generalized predictive control based on just-in-time learning in latent space. In: 2016 8th International Conference on Computational Intelligence and Communication Networks. CICN. pp. 471–475. – volume: 59 start-page: 2801 year: 2004 end-page: 2810 ident: b6 article-title: A new data-based methodology for nonlinear process modeling publication-title: Chem. Eng. Sci. – volume: 39 start-page: 602 year: 2013 end-page: 609 ident: b18 article-title: Online identification of time-varying processes using just-in-time recursive kernel learning approach publication-title: Acta Automat. Sinica – year: 2020 ident: b16 article-title: A novel MIMO T-S fuzzy modeling for prediction of blast furnace molten iron quality with missing outputs publication-title: IEEE Trans. Fuzzy Syst. – year: 2019 ident: b2 article-title: A multi-time-scale fusion prediction model for the gas utilization rate in a blast furnace publication-title: Control Eng. Pract. – year: 1999 ident: b3 article-title: Local Learning Techniques for Modeling, Prediction and Control – start-page: 488 year: 1991 end-page: 491 ident: b19 article-title: Predictive control of blast furnaces publication-title: Proceedings of TENCON ’91.1991 IEEE Region 10 International Conference on EC3-Energy, Computer, Communication and Control Systems – volume: 17 start-page: 757 year: 2007 end-page: 769 ident: b13 article-title: Partitioned model-based IMC design using JITL modeling technique publication-title: J. Process Control – volume: 68 start-page: 86 year: 2018 end-page: 95 ident: b23 article-title: Effective variable selection and moving window HMM-based approach for iron-making process monitoring publication-title: J. Process Control – volume: 37 start-page: 295 year: 2020 end-page: 306 ident: b24 article-title: Data-driven just-in-time learning based adaptive predictive control for blast furnace ironmaking publication-title: Control Theory Appl. – volume: 45 start-page: 2412 year: 2009 end-page: 2418 ident: b10 article-title: An integrated perturbation analysis and sequential quadratic programming approach for model predictive control publication-title: Automatica – year: 2020 ident: b1 article-title: Two-layer fault diagnosis method for blast furnace based on evidence-conflict reduction on multiple time scales publication-title: Control Eng. Pract. – volume: 19 start-page: 103 year: 2006 end-page: 111 ident: b9 article-title: Predicting aerodynamic instabilities in a blast furnace publication-title: Eng. Appl. Artif. Intell. – volume: 23 start-page: 793 year: 2013 end-page: 804 ident: b17 article-title: Integrated soft sensor using just-in-time support vector regression and probabilistic analysis for quality prediction of multi-grade processes publication-title: J. Process Control – volume: 29 start-page: 4007 year: 2018 end-page: 4021 ident: b28 article-title: Data-driven robust M-LS-SVR-based NARX modeling for estimation and control of molten iron quality indices in blast furnace ironmaking publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 14 start-page: 77 year: 2001 end-page: 85 ident: b5 article-title: A predictive system for blast furnaces by integrating a neural network with qualitative analysis publication-title: Eng. Appl. Artif. Intell. – volume: 46 start-page: 472 year: 2007 end-page: 480 ident: b20 article-title: Lazy learning-based online identification and adaptive PID control: a case study for CSTR process publication-title: Ind. Eng. Chem. Res. – volume: 3 start-page: 56 year: 2005 end-page: 73 ident: b4 article-title: From linearization to lazy learning: a survey of divide-and-conquer techniques for nonlinear control publication-title: Int. J. Comput. Cogn. – volume: 19 start-page: 1067 year: 2009 end-page: 1072 ident: b14 article-title: Adaptive generalized predictive control based on JITL technique publication-title: J. Process Control – volume: 55 start-page: 1754 year: 2009 end-page: 1765 ident: b8 article-title: Soft-sensor development using correlation-based just-in-time modeling publication-title: AICHE J. – volume: 92 start-page: 90 year: 2020 end-page: 97 ident: b11 article-title: Output-relevant variational autoencoder for just-in-time soft sensor modeling with missing data publication-title: J. Process Control – volume: 88 year: 2020 ident: b25 article-title: Lazy reinforcement learning for real-time generation control of parallel cyber–physical–social energy systems publication-title: Eng. Appl. Artif. Intell. – volume: 43 start-page: 1 year: 2016 end-page: 9 ident: b22 article-title: Just-in-time-learning based extended prediction self-adaptive control for batch processes publication-title: J. Process Control – year: 2016 ident: 10.1016/j.engappai.2021.104168_b21 – start-page: 488 year: 1991 ident: 10.1016/j.engappai.2021.104168_b19 article-title: Predictive control of blast furnaces – year: 2020 ident: 10.1016/j.engappai.2021.104168_b12 article-title: Optimized design of parity relation based residual generator for fault detection: data-driven approaches publication-title: IEEE Trans. Ind. Inf. – volume: 39 start-page: 602 issue: 5 year: 2013 ident: 10.1016/j.engappai.2021.104168_b18 article-title: Online identification of time-varying processes using just-in-time recursive kernel learning approach publication-title: Acta Automat. Sinica doi: 10.3724/SP.J.1004.2013.00602 – volume: 15 start-page: 151 issue: 2 year: 2002 ident: 10.1016/j.engappai.2021.104168_b7 article-title: Local learning framework for handwritten character recognition publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/S0952-1976(02)00024-6 – year: 2020 ident: 10.1016/j.engappai.2021.104168_b16 article-title: A novel MIMO T-S fuzzy modeling for prediction of blast furnace molten iron quality with missing outputs publication-title: IEEE Trans. Fuzzy Syst. – volume: 19 start-page: 103 issue: 1 year: 2006 ident: 10.1016/j.engappai.2021.104168_b9 article-title: Predicting aerodynamic instabilities in a blast furnace publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2005.05.006 – volume: 17 start-page: 757 issue: 10 year: 2007 ident: 10.1016/j.engappai.2021.104168_b13 article-title: Partitioned model-based IMC design using JITL modeling technique publication-title: J. Process Control doi: 10.1016/j.jprocont.2007.04.004 – volume: 46 start-page: 472 issue: 2 year: 2007 ident: 10.1016/j.engappai.2021.104168_b20 article-title: Lazy learning-based online identification and adaptive PID control: a case study for CSTR process publication-title: Ind. Eng. Chem. Res. doi: 10.1021/ie0608713 – volume: 65 start-page: 4933 issue: 6 year: 2018 ident: 10.1016/j.engappai.2021.104168_b15 article-title: Bayesian block structure sparse based T–S fuzzy modeling for dynamic prediction of hot metal silicon content in the blast furnace publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2017.2772141 – year: 2019 ident: 10.1016/j.engappai.2021.104168_b30 article-title: Hybrid model based intelligent optimization of ironmaking process publication-title: IEEE Trans. Ind. Electron. – volume: 25 start-page: 1761 issue: 5 year: 2017 ident: 10.1016/j.engappai.2021.104168_b29 article-title: Data-driven nonlinear subspace modeling for prediction and control of molten iron quality indices in blast furnace ironmaking publication-title: IEEE Trans. Control Syst. Technol. doi: 10.1109/TCST.2016.2631124 – volume: 14 start-page: 77 issue: 1 year: 2001 ident: 10.1016/j.engappai.2021.104168_b5 article-title: A predictive system for blast furnaces by integrating a neural network with qualitative analysis publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/S0952-1976(00)00062-2 – volume: 19 start-page: 1067 issue: 7 year: 2009 ident: 10.1016/j.engappai.2021.104168_b14 article-title: Adaptive generalized predictive control based on JITL technique publication-title: J. Process Control doi: 10.1016/j.jprocont.2009.04.002 – volume: 43 start-page: 1 year: 2016 ident: 10.1016/j.engappai.2021.104168_b22 article-title: Just-in-time-learning based extended prediction self-adaptive control for batch processes publication-title: J. Process Control doi: 10.1016/j.jprocont.2016.04.009 – volume: 92 start-page: 90 year: 2020 ident: 10.1016/j.engappai.2021.104168_b11 article-title: Output-relevant variational autoencoder for just-in-time soft sensor modeling with missing data publication-title: J. Process Control doi: 10.1016/j.jprocont.2020.05.012 – volume: 55 start-page: 1754 issue: 7 year: 2009 ident: 10.1016/j.engappai.2021.104168_b8 article-title: Soft-sensor development using correlation-based just-in-time modeling publication-title: AICHE J. doi: 10.1002/aic.11791 – year: 1999 ident: 10.1016/j.engappai.2021.104168_b3 – volume: 34 start-page: 1854 issue: 11 year: 2010 ident: 10.1016/j.engappai.2021.104168_b26 article-title: Data-driven predictive control for blast furnace ironmaking process publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2010.01.005 – volume: 29 start-page: 4007 issue: 9 year: 2018 ident: 10.1016/j.engappai.2021.104168_b28 article-title: Data-driven robust M-LS-SVR-based NARX modeling for estimation and control of molten iron quality indices in blast furnace ironmaking publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2017.2749412 – ident: 10.1016/j.engappai.2021.104168_b27 doi: 10.1109/CICN.2016.97 – volume: 45 start-page: 2412 issue: 10 year: 2009 ident: 10.1016/j.engappai.2021.104168_b10 article-title: An integrated perturbation analysis and sequential quadratic programming approach for model predictive control publication-title: Automatica doi: 10.1016/j.automatica.2009.06.028 – volume: 23 start-page: 793 issue: 6 year: 2013 ident: 10.1016/j.engappai.2021.104168_b17 article-title: Integrated soft sensor using just-in-time support vector regression and probabilistic analysis for quality prediction of multi-grade processes publication-title: J. Process Control doi: 10.1016/j.jprocont.2013.03.008 – volume: 59 start-page: 2801 issue: 13 year: 2004 ident: 10.1016/j.engappai.2021.104168_b6 article-title: A new data-based methodology for nonlinear process modeling publication-title: Chem. Eng. Sci. doi: 10.1016/j.ces.2004.04.020 – volume: 37 start-page: 295 issue: 2 year: 2020 ident: 10.1016/j.engappai.2021.104168_b24 article-title: Data-driven just-in-time learning based adaptive predictive control for blast furnace ironmaking publication-title: Control Theory Appl. – year: 2020 ident: 10.1016/j.engappai.2021.104168_b1 article-title: Two-layer fault diagnosis method for blast furnace based on evidence-conflict reduction on multiple time scales publication-title: Control Eng. Pract. doi: 10.1016/j.conengprac.2020.104474 – year: 2019 ident: 10.1016/j.engappai.2021.104168_b2 article-title: A multi-time-scale fusion prediction model for the gas utilization rate in a blast furnace publication-title: Control Eng. Pract. doi: 10.1016/j.conengprac.2019.104120 – volume: 3 start-page: 56 issue: 1 year: 2005 ident: 10.1016/j.engappai.2021.104168_b4 article-title: From linearization to lazy learning: a survey of divide-and-conquer techniques for nonlinear control publication-title: Int. J. Comput. Cogn. – volume: 68 start-page: 86 year: 2018 ident: 10.1016/j.engappai.2021.104168_b23 article-title: Effective variable selection and moving window HMM-based approach for iron-making process monitoring publication-title: J. Process Control doi: 10.1016/j.jprocont.2018.04.008 – volume: 88 issue: 1 year: 2020 ident: 10.1016/j.engappai.2021.104168_b25 article-title: Lazy reinforcement learning for real-time generation control of parallel cyber–physical–social energy systems publication-title: Eng. Appl. Artif. Intell.
SSID	ssj0003846
Score	2.4145021
Snippet	Aiming at quality prediction and control of blast furnace (BF) ironmaking process characterized by complicated nonlinear time-varying dynamics, this paper...
SourceID	crossref elsevier
SourceType	Enrichment Source Index Database Publisher
StartPage	104168
SubjectTerms	Blast furnace ironmaking process Incremental learning Just-in-time-learning (JITL) Local learning nonlinear modeling Model verification Multi-output LSSVR (M-LSSVR) Nonlinear predictive control
Title	Fast just-in-time-learning recursive multi-output LSSVR for quality prediction and control of multivariable dynamic systems
URI	https://dx.doi.org/10.1016/j.engappai.2021.104168
Volume	100
WOSCitedRecordID	wos000633002300010&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-6769 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0003846 issn: 0952-1976 databaseCode: AIEXJ dateStart: 19950201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Nb9MwFLfKxoEL34iNDfnArXJJ4zSJjxPaNKZpQmxAxSVyEoelKknXJNUQ_xd_356_khQqxg5cosiqnbjvF7_n5_feD6E3Keexx-TRoBty4nkTh4R-7JE4lQxwoJMCqhKFT4Ozs3A6ZR8Gg182F2Y1D4oivL5mi_8qamgDYcvU2TuIux0UGuAehA5XEDtc_0nwR7yqh7OmqkleEEkdT-bW_bGUznUVr67iCEnZ1IumHp6en3_-qOINdYrlD1k5IM0NibjKe9Px7PIsXnZcwQZbp1xpPntTD7pac_N3hQ6H_VNyFXiwVBFKii-kVxK0c2KXjbJurVpV4Qd6ffwi8qu8XapyHTEgim_fe789yY0T_OslLy-bvO_ZcMe9gBjronTJmGl-mHa1dpzeegubybGm5flDFWivxGwErwCz5PlIPmLUdVivvf2bTmwjFW0Q3Cyy40RynEiPcw9tu8GEgULYPnh_OD1pbQAa6hQxO4NebvrmN9psFvVMnYvH6KHZo-ADja0naCCKp-iR2a9gow0qaLKUILbtGfop0Yc3og-36MN99GGFPgzowwZ9uEMfBvRhgz5cZngNfdigDxv0PUefjg4v3h0Tw-9BEjp2awLzdoTPRBz6aSYZFR035RkVIaWMJsFEBAEXIoljFnJJP88Sh2VgXvqecFLf4fQF2irKQrxE2FNljliSxR6sN7IoZkI9h4kALPokoHQHTezfGyWm-L3kYJlHfxfwDnrb9lvo8i-39mBWepExYrVxGgEwb-m7e-envUIPui9nD23Vy0bso_vJqs6r5WuDyhuRa8do
linkProvider	Elsevier
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=Fast+just-in-time-learning+recursive+multi-output+LSSVR+for+quality+prediction+and+control+of+multivariable+dynamic+systems&rft.jtitle=Engineering+applications+of+artificial+intelligence&rft.au=Zhou%2C+Ping&rft.au=Chen%2C+Weiqi&rft.au=Yi%2C+Chengming&rft.au=Jiang%2C+Zhaohui&rft.date=2021-04-01&rft.issn=0952-1976&rft.volume=100&rft.spage=104168&rft_id=info:doi/10.1016%2Fj.engappai.2021.104168&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_engappai_2021_104168
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0952-1976&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0952-1976&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0952-1976&client=summon