Multimode process monitoring based on hierarchical mode identification and stacked denoising autoencoder

•A novel hierarchical mode identification strategy is proposed for multimode process.•An improved density peaks clustering algorithm called LDRSDPC is presented for achieving the transition mode identification.•A decision criterion combined with local density relation is constructed to automatically...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Chemical engineering science Jg. 253; S. 117556
Hauptverfasser: Gao, Huihui, Wei, Chen, Huang, Wenjie, Gao, Xuejin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 18.05.2022
Schlagworte:
ISSN:0009-2509
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract •A novel hierarchical mode identification strategy is proposed for multimode process.•An improved density peaks clustering algorithm called LDRSDPC is presented for achieving the transition mode identification.•A decision criterion combined with local density relation is constructed to automatically determine the clustering center.•A numerical example and Tennessee Eastman process simulations are carried out to demonstrate the effectiveness. In modern plants, industrial processes generally operate under different modes, and reliable monitoring for such processes is highly important. One of the key challenges is how to accurately identify the various modes including steady modes and transitions modes. In this paper, a novel monitoring scheme based on hierarchical mode identification strategy and stacked denoising autoencoder (HMI-SDAE) is proposed for multimode processes. First, a novel mode division strategy called HMI is presented. In HMI, the Gaussian mixture model (GMM) is adopted to realize the preliminary identification of various modes by extracting the global distribution features of the variables. In this way, the whole multimode process is divided into multiple steady modes. An improved density peaks clustering algorithm based on local density relation search (LDRSDPC) is proposed to achieve the transition mode identification by fully utilizing the local distribution features of the process variables involved in any two adjacent steady modes and transition mode between them. A decision criterion combined with local density relation is constructed to automatically determine the clustering center. In this hierarchical way, multiple steady modes and transition modes are divided automatically and accurately. Secondly, the deep nonlinear features embedded in process variables are mined by SDAE, and the robust monitoring model is established for each steady mode. A monitoring statistic is constructed using the reconstruction error for detecting faults. The effectiveness and feasibility of the proposed HMI-SDAE monitoring scheme are illustrated with a numerical example and Tennessee Eastman (TE) process.
AbstractList •A novel hierarchical mode identification strategy is proposed for multimode process.•An improved density peaks clustering algorithm called LDRSDPC is presented for achieving the transition mode identification.•A decision criterion combined with local density relation is constructed to automatically determine the clustering center.•A numerical example and Tennessee Eastman process simulations are carried out to demonstrate the effectiveness. In modern plants, industrial processes generally operate under different modes, and reliable monitoring for such processes is highly important. One of the key challenges is how to accurately identify the various modes including steady modes and transitions modes. In this paper, a novel monitoring scheme based on hierarchical mode identification strategy and stacked denoising autoencoder (HMI-SDAE) is proposed for multimode processes. First, a novel mode division strategy called HMI is presented. In HMI, the Gaussian mixture model (GMM) is adopted to realize the preliminary identification of various modes by extracting the global distribution features of the variables. In this way, the whole multimode process is divided into multiple steady modes. An improved density peaks clustering algorithm based on local density relation search (LDRSDPC) is proposed to achieve the transition mode identification by fully utilizing the local distribution features of the process variables involved in any two adjacent steady modes and transition mode between them. A decision criterion combined with local density relation is constructed to automatically determine the clustering center. In this hierarchical way, multiple steady modes and transition modes are divided automatically and accurately. Secondly, the deep nonlinear features embedded in process variables are mined by SDAE, and the robust monitoring model is established for each steady mode. A monitoring statistic is constructed using the reconstruction error for detecting faults. The effectiveness and feasibility of the proposed HMI-SDAE monitoring scheme are illustrated with a numerical example and Tennessee Eastman (TE) process.
ArticleNumber 117556
Author Huang, Wenjie
Wei, Chen
Gao, Xuejin
Gao, Huihui
Author_xml – sequence: 1
  givenname: Huihui
  surname: Gao
  fullname: Gao, Huihui
  email: gaohh@bjut.edu.cn
– sequence: 2
  givenname: Chen
  surname: Wei
  fullname: Wei, Chen
– sequence: 3
  givenname: Wenjie
  surname: Huang
  fullname: Huang, Wenjie
– sequence: 4
  givenname: Xuejin
  surname: Gao
  fullname: Gao, Xuejin
  email: gaoxuejin@bjut.edu.cn
BookMark eNp9kM9OAjEQxnvAREAfwNu-wK7Thd1l48kQ_yUYL3puynQqg9CStpj49hbw5IHTZGa-32S-byQGzjsS4kZCJUG2t-sKKVY11HUlZdc07UAMAaAv6wb6SzGKcZ3brpMwFKvX_Sbx1hsqdsFnLhZb7zj5wO6zWOpIpvCuWDEFHXDFqDfFUc2GXGKbB4mzQDtTxKTxK-vzxnM88HqfPDnM-nAlLqzeRLr-q2Px8fjwPn8uF29PL_P7RYl136Wyt0TQTdG0tDQww6bpjbTW1qi7VhJSq80Eamt6gBbkTPcaZhYnNG2WANNmMhbd6S4GH2Mgq5DT8ccUNG-UBHUISa1VNqsOIalTSJmU_8hd4K0OP2eZuxND2dJ3DklF5OyYDAfCpIznM_QvvcGG1A
CitedBy_id crossref_primary_10_1016_j_infrared_2024_105532
crossref_primary_10_1016_j_jfranklin_2023_04_030
crossref_primary_10_1088_2631_8695_addd5f
crossref_primary_10_1016_j_chemolab_2022_104711
crossref_primary_10_1016_j_foodchem_2022_135251
crossref_primary_10_1016_j_conengprac_2024_106227
crossref_primary_10_3390_pr12112478
crossref_primary_10_1016_j_engappai_2022_105737
crossref_primary_10_1016_j_compchemeng_2025_109107
crossref_primary_10_1016_j_psep_2023_02_023
crossref_primary_10_1016_j_energy_2023_128128
crossref_primary_10_1109_TIM_2022_3222506
crossref_primary_10_3390_math10142526
crossref_primary_10_1016_j_ins_2022_11_091
crossref_primary_10_1016_j_ces_2023_118581
crossref_primary_10_1016_j_ces_2025_121652
crossref_primary_10_1016_j_cjche_2025_02_025
crossref_primary_10_1016_j_measurement_2023_113700
crossref_primary_10_1016_j_psep_2024_05_065
crossref_primary_10_1109_TIM_2024_3420267
crossref_primary_10_1016_j_jfca_2025_107994
crossref_primary_10_1016_j_psep_2025_107207
crossref_primary_10_1016_j_asoc_2025_113679
crossref_primary_10_1109_TIM_2024_3449983
crossref_primary_10_1002_cjce_25687
crossref_primary_10_1007_s40313_022_00971_6
Cites_doi 10.1016/j.ces.2021.116851
10.1016/j.ces.2020.116233
10.1109/TASE.2020.3010536
10.1016/0098-1354(93)80018-I
10.1021/ie300203u
10.1109/TASE.2016.2636292
10.1016/j.jtice.2010.03.015
10.1016/j.jprocont.2010.12.003
10.1016/j.jprocont.2016.09.006
10.1016/j.compchemeng.2020.107024
10.1109/TII.2019.2942650
10.1016/j.measurement.2019.107190
10.1109/ACCESS.2018.2798278
10.1016/j.patcog.2020.107554
10.1021/ie504380c
10.1016/j.ces.2011.10.011
10.1016/0959-1524(96)00010-8
10.1021/acs.iecr.7b01721
10.1002/aic.14282
10.1002/cjce.23614
10.1126/science.1242072
10.1016/j.jprocont.2018.02.004
10.1016/0098-1354(94)00043-N
10.1109/TASE.2019.2897477
10.1016/j.chemolab.2019.03.012
10.1016/j.compchemeng.2015.09.013
10.1145/1390156.1390294
10.1021/ie202720y
10.1177/0142331219881343
10.1016/j.jfranklin.2020.05.039
10.1021/acs.iecr.5b03993
10.1016/j.neunet.2021.01.010
10.1016/j.ces.2010.08.024
10.1016/j.ins.2018.03.031
10.1016/j.compchemeng.2020.106787
10.1109/TASE.2013.2285571
10.1016/j.jprocont.2019.01.008
10.1016/S1004-9541(12)60604-1
10.1016/j.knosys.2017.07.010
10.1016/j.ces.2017.12.025
ContentType Journal Article
Copyright 2022 Elsevier Ltd
Copyright_xml – notice: 2022 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.ces.2022.117556
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_ces_2022_117556
S0009250922001403
GroupedDBID --K
--M
-~X
.~1
0R~
1B1
1~.
1~5
29B
4.4
457
4G.
5GY
5VS
6J9
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AATTM
AAXKI
AAXUO
ABFNM
ABFRF
ABJNI
ABMAC
ABNUV
ACBEA
ACDAQ
ACGFO
ACGFS
ACNCT
ACRLP
ADBBV
ADEWK
ADEZE
AEBSH
AEFWE
AEIPS
AEKER
AENEX
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHPOS
AIEXJ
AIKHN
AITUG
AKRWK
AKURH
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AXJTR
BKOJK
BLXMC
BNPGV
CS3
DU5
EBS
EFJIC
ENUVR
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
HLY
IHE
J1W
KOM
LX7
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RNS
ROL
RPZ
SCE
SDF
SDG
SDP
SES
SPC
SPCBC
SSG
SSH
SSZ
T5K
XPP
ZMT
~02
~G-
9DU
AAQXK
AAYWO
AAYXX
ABDPE
ABWVN
ABXDB
ACLOT
ACRPL
ACVFH
ADCNI
ADMUD
ADNMO
AEUPX
AFJKZ
AFPUW
AGQPQ
AI.
AIDUJ
AIGII
AIIUN
AKBMS
AKYEP
APXCP
ASPBG
AVWKF
AZFZN
BBWZM
CITATION
EFKBS
EFLBG
EJD
FEDTE
FGOYB
HVGLF
HZ~
NDZJH
R2-
SC5
SEW
T9H
VH1
WUQ
Y6R
ZY4
~HD
ID FETCH-LOGICAL-c297t-9fee074cd6ebd08c559d1fff2ca761ece6ad302fd9006018a9a08fc3e45b00453
ISICitedReferencesCount 28
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000788736700007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0009-2509
IngestDate Sat Nov 29 07:30:19 EST 2025
Tue Nov 18 21:30:51 EST 2025
Sun Apr 06 06:53:07 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Mode identification
Multimode process monitoring
Stacked denoising autoencoder
Gaussian mixture model
Density peaks clustering
Industrial process
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c297t-9fee074cd6ebd08c559d1fff2ca761ece6ad302fd9006018a9a08fc3e45b00453
ParticipantIDs crossref_citationtrail_10_1016_j_ces_2022_117556
crossref_primary_10_1016_j_ces_2022_117556
elsevier_sciencedirect_doi_10_1016_j_ces_2022_117556
PublicationCentury 2000
PublicationDate 2022-05-18
PublicationDateYYYYMMDD 2022-05-18
PublicationDate_xml – month: 05
  year: 2022
  text: 2022-05-18
  day: 18
PublicationDecade 2020
PublicationTitle Chemical engineering science
PublicationYear 2022
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Lou, Wang (b0065) 2017; 56
Song, Tan, Shi (b0105) 2016; 47
Wu, Zhao (b0145) 2020; 141
Ricker (b0090) 1995; 19
Downs, Vogel (b0010) 1993; 17
Yaohui, Zhengming, Fang (b0060) 2017; 133
Wu, Zhou, Zhang, Chen (b0140) 2020; 136
Sun, Zhuang, Xu, Qin, Feng (b0115) 2021
Zhang, Zhao, Gao (b0185) 2018; 178
Zhao (b0200) 2014; 60
Quiñones-Grueiro, Prieto-Moreno, Verde, Llanes-Santiago (b0080) 2019; 189
Vincent, Larochelle, Lajoie, Bengio, Manzagol, Bottou (b0130) 2010; 11
Jiang, Huang, Yan (b0045) 2016; 84
Xie, Shi (b0150) 2012; 51
Yu, Liu (b0175) 2021; 137
Wang, Li, Dai, Lawrence, Yan (b0135) 2020; 16
Gao, Jia, Mao, Zhao (b0020) 2020; 98
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.-A., 2008. Extracting and composing robust features with denoising autoencoders, Proceedings of the 25th international conference on Machine learning. pp. 1096–1103.
Hou, Zhang, Qi (b0030) 2020; 108
Rodriguez, Laio (b0095) 2014; 344
Zhao, Yao, Gao, Wang (b0215) 2010; 65
Jiang, Yan (b0050) 2019; 16
Yu (b0170) 2012; 68
Rashid, Yu (b0085) 2012; 51
Xie, Shi (b0155) 2012; 20
Zhang, Jiang, Zhan, Yang (b0195) 2019; 75
Ji (b0040) 2021; 230
Liu, Wang, Yu (b0055) 2018; 450
Jeng (b0035) 2010; 41
Martin, Morris (b0075) 1996; 6
Yu (b0165) 2018; 15
Tang, Li (b0120) 2020; 42
Chen, Zhang, Cao, Wang (b0005) 2020; 151
Sun, Meng, Palazoglu, Zhao, Zhang, Zhang (b0110) 2011; 21
Song, Shi (b0100) 2018; 6
Guo, Huang, Cai, Zhu (b0025) 2018
Zhang, Shang, Yang, Sun (b0180) 2020; 357
Luo, Bao, Mao, Tang (b0070) 2016; 55
Zhao, Wang, Qin, Gao (b0210) 2015; 54
Zhao, Chen, Jing (b0205) 2021; 18
Du, Tian, Qian (b0015) 2014; 11
Zhang, Jiang, Li, Yang (b0190) 2018; 64
You, Chen (b0160) 2021; 246
Jiang (10.1016/j.ces.2022.117556_b0045) 2016; 84
Chen (10.1016/j.ces.2022.117556_b0005) 2020; 151
Hou (10.1016/j.ces.2022.117556_b0030) 2020; 108
Zhao (10.1016/j.ces.2022.117556_b0215) 2010; 65
Song (10.1016/j.ces.2022.117556_b0105) 2016; 47
Vincent (10.1016/j.ces.2022.117556_b0130) 2010; 11
Yaohui (10.1016/j.ces.2022.117556_b0060) 2017; 133
Rashid (10.1016/j.ces.2022.117556_b0085) 2012; 51
Wu (10.1016/j.ces.2022.117556_b0140) 2020; 136
Zhang (10.1016/j.ces.2022.117556_b0190) 2018; 64
Wu (10.1016/j.ces.2022.117556_b0145) 2020; 141
Guo (10.1016/j.ces.2022.117556_b0025) 2018
Martin (10.1016/j.ces.2022.117556_b0075) 1996; 6
Ricker (10.1016/j.ces.2022.117556_b0090) 1995; 19
Du (10.1016/j.ces.2022.117556_b0015) 2014; 11
Gao (10.1016/j.ces.2022.117556_b0020) 2020; 98
Yu (10.1016/j.ces.2022.117556_b0170) 2012; 68
Jeng (10.1016/j.ces.2022.117556_b0035) 2010; 41
Quiñones-Grueiro (10.1016/j.ces.2022.117556_b0080) 2019; 189
10.1016/j.ces.2022.117556_b0125
Zhang (10.1016/j.ces.2022.117556_b0195) 2019; 75
Song (10.1016/j.ces.2022.117556_b0100) 2018; 6
Sun (10.1016/j.ces.2022.117556_b0115) 2021
Sun (10.1016/j.ces.2022.117556_b0110) 2011; 21
Xie (10.1016/j.ces.2022.117556_b0155) 2012; 20
Tang (10.1016/j.ces.2022.117556_b0120) 2020; 42
Yu (10.1016/j.ces.2022.117556_b0165) 2018; 15
Liu (10.1016/j.ces.2022.117556_b0055) 2018; 450
Luo (10.1016/j.ces.2022.117556_b0070) 2016; 55
Jiang (10.1016/j.ces.2022.117556_b0050) 2019; 16
Zhao (10.1016/j.ces.2022.117556_b0205) 2021; 18
Lou (10.1016/j.ces.2022.117556_b0065) 2017; 56
Zhang (10.1016/j.ces.2022.117556_b0180) 2020; 357
Rodriguez (10.1016/j.ces.2022.117556_b0095) 2014; 344
You (10.1016/j.ces.2022.117556_b0160) 2021; 246
Downs (10.1016/j.ces.2022.117556_b0010) 1993; 17
Zhao (10.1016/j.ces.2022.117556_b0210) 2015; 54
Yu (10.1016/j.ces.2022.117556_b0175) 2021; 137
Zhao (10.1016/j.ces.2022.117556_b0200) 2014; 60
Xie (10.1016/j.ces.2022.117556_b0150) 2012; 51
Zhang (10.1016/j.ces.2022.117556_b0185) 2018; 178
Wang (10.1016/j.ces.2022.117556_b0135) 2020; 16
Ji (10.1016/j.ces.2022.117556_b0040) 2021; 230
References_xml – volume: 11
  start-page: 1133
  year: 2014
  end-page: 1148
  ident: b0015
  article-title: Monitoring for nonlinear multiple modes process based on LL-SVDD-MRDA
  publication-title: IEEE Trans. Autom. Sci. Eng.
– year: 2021
  ident: b0115
  article-title: Data-driven modeling and analysis based on complex network for multimode recognition of industrial processes
  publication-title: Journal of Manufacturing Systems
– volume: 47
  start-page: 136
  year: 2016
  end-page: 149
  ident: b0105
  article-title: Key principal components with recursive local outlier factor for multimode chemical process monitoring
  publication-title: J. Process Control
– volume: 21
  start-page: 627
  year: 2011
  end-page: 638
  ident: b0110
  article-title: A method for multiphase batch process monitoring based on auto phase identification
  publication-title: J. Process Control
– volume: 178
  start-page: 104
  year: 2018
  end-page: 117
  ident: b0185
  article-title: Two-directional concurrent strategy of mode identification and sequential phase division for multimode and multiphase batch process monitoring with uneven lengths
  publication-title: Chem. Eng. Sci.
– volume: 16
  start-page: 1814
  year: 2019
  end-page: 1824
  ident: b0050
  article-title: Multimode Process Monitoring Using Variational Bayesian Inference and Canonical Correlation Analysis
  publication-title: IEEE Trans. Autom. Sci. Eng.
– volume: 246
  start-page: 116851
  year: 2021
  ident: b0160
  article-title: A Variable Relevant Multi-Local PCA Modeling Scheme to Monitor a Nonlinear Chemical Process
  publication-title: Chem. Eng. Sci.
– volume: 42
  start-page: 1022
  year: 2020
  end-page: 1036
  ident: b0120
  article-title: Phase division and transition modeling based on the dominant phase identification for multiphase batch process quality prediction
  publication-title: Trans. Inst. Meas. Control
– volume: 108
  start-page: 107554
  year: 2020
  ident: b0030
  article-title: Density peak clustering based on relative density relationship
  publication-title: Pattern Recognit.
– volume: 133
  start-page: 208
  year: 2017
  end-page: 220
  ident: b0060
  article-title: Adaptive density peak clustering based on K-nearest neighbors with aggregating strategy
  publication-title: Knowledge-Based Syst.
– volume: 55
  start-page: 2035
  year: 2016
  end-page: 2048
  ident: b0070
  article-title: Phase partition and phase-based process monitoring methods for multiphase batch processes with uneven durations
  publication-title: Ind. Eng. Chem. Res.
– volume: 75
  start-page: 136
  year: 2019
  end-page: 155
  ident: b0195
  article-title: Gaussian feature learning based on variational autoencoder for improving nonlinear process monitoring
  publication-title: J. Process Control
– volume: 51
  start-page: 5497
  year: 2012
  end-page: 5505
  ident: b0150
  article-title: Dynamic multimode process modeling and monitoring using adaptive Gaussian mixture models
  publication-title: Ind. Eng. Chem. Res.
– volume: 450
  start-page: 200
  year: 2018
  end-page: 226
  ident: b0055
  article-title: Shared-nearest-neighbor-based clustering by fast search and find of density peaks
  publication-title: Inf. Sci.
– volume: 54
  start-page: 3154
  year: 2015
  end-page: 3166
  ident: b0210
  article-title: Comprehensive subspace decomposition with analysis of between-mode relative changes for multimode process monitoring
  publication-title: Ind. Eng. Chem. Res.
– volume: 15
  start-page: 506
  year: 2018
  end-page: 518
  ident: b0165
  article-title: A novel semiparametric hidden Markov model for process failure mode identification
  publication-title: IEEE Trans. Autom. Sci. Eng.
– volume: 98
  start-page: 254
  year: 2020
  end-page: 262
  ident: b0020
  article-title: A new monitoring method for the between-mode transition of multimode processes
  publication-title: Can. J. Chem. Eng.
– volume: 64
  start-page: 49
  year: 2018
  end-page: 61
  ident: b0190
  article-title: Automated feature learning for nonlinear process monitoring – An approach using stacked denoising autoencoder and k-nearest neighbor rule
  publication-title: J. Process Control
– start-page: 426
  year: 2018
  end-page: 438
  ident: b0025
  article-title: A new local density for density peak clustering
  publication-title: Pacific-Asia Conference on Knowledge Discovery and Data Mining
– volume: 6
  start-page: 349
  year: 1996
  end-page: 358
  ident: b0075
  article-title: Non-parametric confidence bounds for process performance monitoring charts
  publication-title: J. Process Control
– volume: 65
  start-page: 5961
  year: 2010
  end-page: 5975
  ident: b0215
  article-title: Statistical analysis and online monitoring for multimode processes with between-mode transitions
  publication-title: Chem. Eng. Sci.
– volume: 189
  start-page: 56
  year: 2019
  end-page: 71
  ident: b0080
  article-title: Data-driven monitoring of multimode continuous processes: A review
  publication-title: Chemometrics Intell. Lab. Syst.
– volume: 11
  year: 2010
  ident: b0130
  article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
  publication-title: J. Mach. Learn. Res.
– volume: 19
  start-page: 949
  year: 1995
  end-page: 959
  ident: b0090
  article-title: Optimal steady-state operation of the Tennessee Eastman challenge process
  publication-title: Comput. Chem. Eng.
– volume: 6
  start-page: 9740
  year: 2018
  end-page: 9749
  ident: b0100
  article-title: Temporal-spatial global locality projections for multimode process monitoring
  publication-title: IEEE Access
– volume: 17
  start-page: 245
  year: 1993
  end-page: 255
  ident: b0010
  article-title: A plant-wide industrial process control problem
  publication-title: Comput. Chem. Eng.
– volume: 151
  start-page: 107190
  year: 2020
  ident: b0005
  article-title: A novel method of combining nonlinear frequency spectrum and deep learning for complex system fault diagnosis
  publication-title: Measurement
– volume: 68
  start-page: 506
  year: 2012
  end-page: 519
  ident: b0170
  article-title: A nonlinear kernel Gaussian mixture model based inferential monitoring approach for fault detection and diagnosis of chemical processes
  publication-title: Chem. Eng. Sci.
– volume: 357
  start-page: 8229
  year: 2020
  end-page: 8251
  ident: b0180
  article-title: Conditional random field for monitoring multimode processes with stochastic perturbations
  publication-title: J. Franklin Inst.
– volume: 41
  start-page: 475
  year: 2010
  end-page: 481
  ident: b0035
  article-title: Adaptive process monitoring using efficient recursive PCA and moving window PCA algorithms
  publication-title: J. Taiwan Inst. Chem. Eng.
– volume: 84
  start-page: 338
  year: 2016
  end-page: 349
  ident: b0045
  article-title: GMM and optimal principal components-based Bayesian method for multimode fault diagnosis
  publication-title: Comput. Chem. Eng.
– volume: 60
  start-page: 559
  year: 2014
  end-page: 573
  ident: b0200
  article-title: Concurrent phase partition and between-mode statistical analysis for multimode and multiphase batch process monitoring
  publication-title: AICHE J.
– volume: 344
  start-page: 1492
  year: 2014
  end-page: 1496
  ident: b0095
  article-title: Clustering by fast search and find of density peaks
  publication-title: Science
– reference: Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.-A., 2008. Extracting and composing robust features with denoising autoencoders, Proceedings of the 25th international conference on Machine learning. pp. 1096–1103.
– volume: 20
  start-page: 1174
  year: 2012
  end-page: 1179
  ident: b0155
  article-title: Multimode process monitoring based on fuzzy C-means in locality preserving projection subspace
  publication-title: Chin. J. Chem. Eng.
– volume: 137
  start-page: 31
  year: 2021
  end-page: 42
  ident: b0175
  article-title: Extracting and inserting knowledge into stacked denoising auto-encoders
  publication-title: Neural Networks
– volume: 230
  start-page: 116233
  year: 2021
  ident: b0040
  article-title: Statistics Mahalanobis distance for incipient sensor fault detection and diagnosis
  publication-title: Chem. Eng. Sci.
– volume: 136
  start-page: 106787
  year: 2020
  ident: b0140
  article-title: Multimode process monitoring based on fault dependent variable selection and moving window-negative log likelihood probability
  publication-title: Comput. Chem. Eng.
– volume: 56
  start-page: 13800
  year: 2017
  end-page: 13811
  ident: b0065
  article-title: Multimode continuous processes monitoring based on hidden semi-Markov model and principal component analysis
  publication-title: Ind. Eng. Chem. Res.
– volume: 16
  start-page: 3651
  year: 2020
  end-page: 3661
  ident: b0135
  article-title: Data-Driven Mode Identification and Unsupervised Fault Detection for Nonlinear Multimode Processes
  publication-title: IEEE Trans. Ind. Inform.
– volume: 51
  start-page: 5506
  year: 2012
  end-page: 5514
  ident: b0085
  article-title: Hidden Markov model based adaptive independent component analysis approach for complex chemical process monitoring and fault detection
  publication-title: Ind. Eng. Chem. Res.
– volume: 18
  start-page: 1563
  year: 2021
  end-page: 1574
  ident: b0205
  article-title: Condition-driven data analytics and monitoring for wide-range nonstationary and transient continuous processes
  publication-title: IEEE Trans. Automat. Sci. Eng.
– volume: 141
  start-page: 107024
  year: 2020
  ident: b0145
  article-title: Self-adaptive deep learning for multimode process monitoring
  publication-title: Comput. Chem. Eng.
– volume: 246
  start-page: 116851
  year: 2021
  ident: 10.1016/j.ces.2022.117556_b0160
  article-title: A Variable Relevant Multi-Local PCA Modeling Scheme to Monitor a Nonlinear Chemical Process
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2021.116851
– volume: 230
  start-page: 116233
  year: 2021
  ident: 10.1016/j.ces.2022.117556_b0040
  article-title: Statistics Mahalanobis distance for incipient sensor fault detection and diagnosis
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2020.116233
– volume: 18
  start-page: 1563
  issue: 4
  year: 2021
  ident: 10.1016/j.ces.2022.117556_b0205
  article-title: Condition-driven data analytics and monitoring for wide-range nonstationary and transient continuous processes
  publication-title: IEEE Trans. Automat. Sci. Eng.
  doi: 10.1109/TASE.2020.3010536
– volume: 17
  start-page: 245
  issue: 3
  year: 1993
  ident: 10.1016/j.ces.2022.117556_b0010
  article-title: A plant-wide industrial process control problem
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/0098-1354(93)80018-I
– volume: 51
  start-page: 5506
  issue: 15
  year: 2012
  ident: 10.1016/j.ces.2022.117556_b0085
  article-title: Hidden Markov model based adaptive independent component analysis approach for complex chemical process monitoring and fault detection
  publication-title: Ind. Eng. Chem. Res.
  doi: 10.1021/ie300203u
– volume: 15
  start-page: 506
  issue: 2
  year: 2018
  ident: 10.1016/j.ces.2022.117556_b0165
  article-title: A novel semiparametric hidden Markov model for process failure mode identification
  publication-title: IEEE Trans. Autom. Sci. Eng.
  doi: 10.1109/TASE.2016.2636292
– volume: 41
  start-page: 475
  issue: 4
  year: 2010
  ident: 10.1016/j.ces.2022.117556_b0035
  article-title: Adaptive process monitoring using efficient recursive PCA and moving window PCA algorithms
  publication-title: J. Taiwan Inst. Chem. Eng.
  doi: 10.1016/j.jtice.2010.03.015
– volume: 21
  start-page: 627
  issue: 4
  year: 2011
  ident: 10.1016/j.ces.2022.117556_b0110
  article-title: A method for multiphase batch process monitoring based on auto phase identification
  publication-title: J. Process Control
  doi: 10.1016/j.jprocont.2010.12.003
– volume: 47
  start-page: 136
  year: 2016
  ident: 10.1016/j.ces.2022.117556_b0105
  article-title: Key principal components with recursive local outlier factor for multimode chemical process monitoring
  publication-title: J. Process Control
  doi: 10.1016/j.jprocont.2016.09.006
– volume: 141
  start-page: 107024
  year: 2020
  ident: 10.1016/j.ces.2022.117556_b0145
  article-title: Self-adaptive deep learning for multimode process monitoring
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2020.107024
– volume: 16
  start-page: 3651
  issue: 6
  year: 2020
  ident: 10.1016/j.ces.2022.117556_b0135
  article-title: Data-Driven Mode Identification and Unsupervised Fault Detection for Nonlinear Multimode Processes
  publication-title: IEEE Trans. Ind. Inform.
  doi: 10.1109/TII.2019.2942650
– volume: 11
  issue: 12
  year: 2010
  ident: 10.1016/j.ces.2022.117556_b0130
  article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
  publication-title: J. Mach. Learn. Res.
– volume: 151
  start-page: 107190
  year: 2020
  ident: 10.1016/j.ces.2022.117556_b0005
  article-title: A novel method of combining nonlinear frequency spectrum and deep learning for complex system fault diagnosis
  publication-title: Measurement
  doi: 10.1016/j.measurement.2019.107190
– volume: 6
  start-page: 9740
  year: 2018
  ident: 10.1016/j.ces.2022.117556_b0100
  article-title: Temporal-spatial global locality projections for multimode process monitoring
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2018.2798278
– volume: 108
  start-page: 107554
  year: 2020
  ident: 10.1016/j.ces.2022.117556_b0030
  article-title: Density peak clustering based on relative density relationship
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2020.107554
– volume: 54
  start-page: 3154
  issue: 12
  year: 2015
  ident: 10.1016/j.ces.2022.117556_b0210
  article-title: Comprehensive subspace decomposition with analysis of between-mode relative changes for multimode process monitoring
  publication-title: Ind. Eng. Chem. Res.
  doi: 10.1021/ie504380c
– volume: 68
  start-page: 506
  issue: 1
  year: 2012
  ident: 10.1016/j.ces.2022.117556_b0170
  article-title: A nonlinear kernel Gaussian mixture model based inferential monitoring approach for fault detection and diagnosis of chemical processes
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2011.10.011
– volume: 6
  start-page: 349
  issue: 6
  year: 1996
  ident: 10.1016/j.ces.2022.117556_b0075
  article-title: Non-parametric confidence bounds for process performance monitoring charts
  publication-title: J. Process Control
  doi: 10.1016/0959-1524(96)00010-8
– volume: 56
  start-page: 13800
  issue: 46
  year: 2017
  ident: 10.1016/j.ces.2022.117556_b0065
  article-title: Multimode continuous processes monitoring based on hidden semi-Markov model and principal component analysis
  publication-title: Ind. Eng. Chem. Res.
  doi: 10.1021/acs.iecr.7b01721
– volume: 60
  start-page: 559
  issue: 2
  year: 2014
  ident: 10.1016/j.ces.2022.117556_b0200
  article-title: Concurrent phase partition and between-mode statistical analysis for multimode and multiphase batch process monitoring
  publication-title: AICHE J.
  doi: 10.1002/aic.14282
– volume: 98
  start-page: 254
  issue: 1
  year: 2020
  ident: 10.1016/j.ces.2022.117556_b0020
  article-title: A new monitoring method for the between-mode transition of multimode processes
  publication-title: Can. J. Chem. Eng.
  doi: 10.1002/cjce.23614
– volume: 344
  start-page: 1492
  issue: 6191
  year: 2014
  ident: 10.1016/j.ces.2022.117556_b0095
  article-title: Clustering by fast search and find of density peaks
  publication-title: Science
  doi: 10.1126/science.1242072
– volume: 64
  start-page: 49
  year: 2018
  ident: 10.1016/j.ces.2022.117556_b0190
  article-title: Automated feature learning for nonlinear process monitoring – An approach using stacked denoising autoencoder and k-nearest neighbor rule
  publication-title: J. Process Control
  doi: 10.1016/j.jprocont.2018.02.004
– start-page: 426
  year: 2018
  ident: 10.1016/j.ces.2022.117556_b0025
  article-title: A new local density for density peak clustering
– volume: 19
  start-page: 949
  issue: 9
  year: 1995
  ident: 10.1016/j.ces.2022.117556_b0090
  article-title: Optimal steady-state operation of the Tennessee Eastman challenge process
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/0098-1354(94)00043-N
– volume: 16
  start-page: 1814
  issue: 4
  year: 2019
  ident: 10.1016/j.ces.2022.117556_b0050
  article-title: Multimode Process Monitoring Using Variational Bayesian Inference and Canonical Correlation Analysis
  publication-title: IEEE Trans. Autom. Sci. Eng.
  doi: 10.1109/TASE.2019.2897477
– volume: 189
  start-page: 56
  year: 2019
  ident: 10.1016/j.ces.2022.117556_b0080
  article-title: Data-driven monitoring of multimode continuous processes: A review
  publication-title: Chemometrics Intell. Lab. Syst.
  doi: 10.1016/j.chemolab.2019.03.012
– volume: 84
  start-page: 338
  issue: JAN.4
  year: 2016
  ident: 10.1016/j.ces.2022.117556_b0045
  article-title: GMM and optimal principal components-based Bayesian method for multimode fault diagnosis
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2015.09.013
– ident: 10.1016/j.ces.2022.117556_b0125
  doi: 10.1145/1390156.1390294
– volume: 51
  start-page: 5497
  issue: 15
  year: 2012
  ident: 10.1016/j.ces.2022.117556_b0150
  article-title: Dynamic multimode process modeling and monitoring using adaptive Gaussian mixture models
  publication-title: Ind. Eng. Chem. Res.
  doi: 10.1021/ie202720y
– volume: 42
  start-page: 1022
  issue: 5
  year: 2020
  ident: 10.1016/j.ces.2022.117556_b0120
  article-title: Phase division and transition modeling based on the dominant phase identification for multiphase batch process quality prediction
  publication-title: Trans. Inst. Meas. Control
  doi: 10.1177/0142331219881343
– volume: 357
  start-page: 8229
  issue: 12
  year: 2020
  ident: 10.1016/j.ces.2022.117556_b0180
  article-title: Conditional random field for monitoring multimode processes with stochastic perturbations
  publication-title: J. Franklin Inst.
  doi: 10.1016/j.jfranklin.2020.05.039
– volume: 55
  start-page: 2035
  issue: 7
  year: 2016
  ident: 10.1016/j.ces.2022.117556_b0070
  article-title: Phase partition and phase-based process monitoring methods for multiphase batch processes with uneven durations
  publication-title: Ind. Eng. Chem. Res.
  doi: 10.1021/acs.iecr.5b03993
– year: 2021
  ident: 10.1016/j.ces.2022.117556_b0115
  article-title: Data-driven modeling and analysis based on complex network for multimode recognition of industrial processes
  publication-title: Journal of Manufacturing Systems
– volume: 137
  start-page: 31
  year: 2021
  ident: 10.1016/j.ces.2022.117556_b0175
  article-title: Extracting and inserting knowledge into stacked denoising auto-encoders
  publication-title: Neural Networks
  doi: 10.1016/j.neunet.2021.01.010
– volume: 65
  start-page: 5961
  issue: 22
  year: 2010
  ident: 10.1016/j.ces.2022.117556_b0215
  article-title: Statistical analysis and online monitoring for multimode processes with between-mode transitions
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2010.08.024
– volume: 450
  start-page: 200
  year: 2018
  ident: 10.1016/j.ces.2022.117556_b0055
  article-title: Shared-nearest-neighbor-based clustering by fast search and find of density peaks
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2018.03.031
– volume: 136
  start-page: 106787
  year: 2020
  ident: 10.1016/j.ces.2022.117556_b0140
  article-title: Multimode process monitoring based on fault dependent variable selection and moving window-negative log likelihood probability
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2020.106787
– volume: 11
  start-page: 1133
  issue: 4
  year: 2014
  ident: 10.1016/j.ces.2022.117556_b0015
  article-title: Monitoring for nonlinear multiple modes process based on LL-SVDD-MRDA
  publication-title: IEEE Trans. Autom. Sci. Eng.
  doi: 10.1109/TASE.2013.2285571
– volume: 75
  start-page: 136
  year: 2019
  ident: 10.1016/j.ces.2022.117556_b0195
  article-title: Gaussian feature learning based on variational autoencoder for improving nonlinear process monitoring
  publication-title: J. Process Control
  doi: 10.1016/j.jprocont.2019.01.008
– volume: 20
  start-page: 1174
  issue: 6
  year: 2012
  ident: 10.1016/j.ces.2022.117556_b0155
  article-title: Multimode process monitoring based on fuzzy C-means in locality preserving projection subspace
  publication-title: Chin. J. Chem. Eng.
  doi: 10.1016/S1004-9541(12)60604-1
– volume: 133
  start-page: 208
  year: 2017
  ident: 10.1016/j.ces.2022.117556_b0060
  article-title: Adaptive density peak clustering based on K-nearest neighbors with aggregating strategy
  publication-title: Knowledge-Based Syst.
  doi: 10.1016/j.knosys.2017.07.010
– volume: 178
  start-page: 104
  year: 2018
  ident: 10.1016/j.ces.2022.117556_b0185
  article-title: Two-directional concurrent strategy of mode identification and sequential phase division for multimode and multiphase batch process monitoring with uneven lengths
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2017.12.025
SSID ssj0007710
Score 2.5060678
Snippet •A novel hierarchical mode identification strategy is proposed for multimode process.•An improved density peaks clustering algorithm called LDRSDPC is...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 117556
SubjectTerms Density peaks clustering
Gaussian mixture model
Industrial process
Mode identification
Multimode process monitoring
Stacked denoising autoencoder
Title Multimode process monitoring based on hierarchical mode identification and stacked denoising autoencoder
URI https://dx.doi.org/10.1016/j.ces.2022.117556
Volume 253
WOSCitedRecordID wos000788736700007&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
  issn: 0009-2509
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0007710
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELag5UAPqBSqvkA-cGKVKm_Hxwq12nKokGjF3iKvPVazarOrNkH9-YwfebClCJC4RJFjO9LM59fM-BtCPoBSch4BHlMZ50EqWRbwPFWBCudacii0hNQmm2AXF8Vsxr94R_u9TSfA6rp4eOCr_6pqLENlm6uzf6HuvlMswHdUOj5R7fj8I8XbK7Umwc1k5S4BTG7tuLWBdmbRUsZBYFJgWyeC0ZGtXSkfOOQgYQ3qjcBBrib4ZVlZo4Jom6WhvlQ-qLfjOOhoB2CgN5z4xbWP8BHWKjttq-u2GhxClXP6DzfSpq03YX-DelGtN5-1sPBk4d5WgcdcQ3NaDAa07hLNELHkJmUe4E6Mjyfl2FEIP5rgna1hcYziOzZ_ME7nLFsj07bL81fTr-k2ji2JUPKcbMYs4zj1bZ6cn84-9ws2Y1HYJdwzDTrntw0DXPvRr7cvoy3J5TZ55c8S9MRh4DV5BvUO2RoxTL4h1z0aqEcDHdBALRrosqZjNFBb-2c0UEQD9WigPRroCA1vydXZ6eWnaeCTawQy5qwJuAbA7aNUOcxVWEg8WapIax1LwfIIJORCJWGsFbeUPYXgIsSRm0CamZk-S3bJRr2sYY_QlEvQORYXCa4HOix4JCNhaF-BhZHI9knYyayUnnneJEC5KbsQw0WJAiiNmEsn5n3ysW-ycrQrv6ucdoooPbTdfrBE1Dzd7ODfmh2SlwO0j8hGc9fCO_JCfm-q-7v3Hls_ABTmlns
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=Multimode+process+monitoring+based+on+hierarchical+mode+identification+and+stacked+denoising+autoencoder&rft.jtitle=Chemical+engineering+science&rft.au=Gao%2C+Huihui&rft.au=Wei%2C+Chen&rft.au=Huang%2C+Wenjie&rft.au=Gao%2C+Xuejin&rft.date=2022-05-18&rft.pub=Elsevier+Ltd&rft.issn=0009-2509&rft.volume=253&rft_id=info:doi/10.1016%2Fj.ces.2022.117556&rft.externalDocID=S0009250922001403
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0009-2509&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0009-2509&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0009-2509&client=summon