One-dimensional decoupled convolutional autoencoder with sparse self-attention mechanism for process monitoring

Industrial processes are constantly disturbed by environmental and human factors during operation. Undifferentiated alarming of these disturbances will bring serious alarm disaster problems.Effectively distinguishing the disturbances that have different effects on the process operation state can hel...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Process safety and environmental protection Ročník 199; s. 107156
Hlavní autoři: Yang, Yuguo, Shi, Hongbo, Song, Bing, Tao, Yang, Guo, Lei
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.07.2025
Témata:
ISSN:0957-5820
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Industrial processes are constantly disturbed by environmental and human factors during operation. Undifferentiated alarming of these disturbances will bring serious alarm disaster problems.Effectively distinguishing the disturbances that have different effects on the process operation state can help the field operators to make a reasonable risk assessment.To achieve the above purposes, this paper proposes a one-dimensional decoupled convolutional autoencoder network with sparse self-attention mechanism under process knowledge constraints (PKC-SSAM-DCAE). Firstly, aiming at the change of data distribution caused by feedback control adjustment, the window normalization strategy is adopted for the standardized data. Realize data distribution alignment at the input end of the model. Subsequently, one-dimensional decoupled convolutional encoder (DCAE) is constructed to extract the features of each process variable. The sparse self-attention mechanism network (SSAM) is constructed under the constraint of process knowledge to realize the interaction between process variable features. Then the detection index is established according to the network prediction results. When the fault is detected, the variable oblivion contribution plot is given to locate the key fault variables.Finally, through the experiments on Tennessee Eastman process, it is verified that the proposed model can solve the problem of data distribution change caused by process feedback adjustment, and can accurately distinguish process normal adjustment from faults.
AbstractList Industrial processes are constantly disturbed by environmental and human factors during operation. Undifferentiated alarming of these disturbances will bring serious alarm disaster problems.Effectively distinguishing the disturbances that have different effects on the process operation state can help the field operators to make a reasonable risk assessment.To achieve the above purposes, this paper proposes a one-dimensional decoupled convolutional autoencoder network with sparse self-attention mechanism under process knowledge constraints (PKC-SSAM-DCAE). Firstly, aiming at the change of data distribution caused by feedback control adjustment, the window normalization strategy is adopted for the standardized data. Realize data distribution alignment at the input end of the model. Subsequently, one-dimensional decoupled convolutional encoder (DCAE) is constructed to extract the features of each process variable. The sparse self-attention mechanism network (SSAM) is constructed under the constraint of process knowledge to realize the interaction between process variable features. Then the detection index is established according to the network prediction results. When the fault is detected, the variable oblivion contribution plot is given to locate the key fault variables.Finally, through the experiments on Tennessee Eastman process, it is verified that the proposed model can solve the problem of data distribution change caused by process feedback adjustment, and can accurately distinguish process normal adjustment from faults.
ArticleNumber 107156
Author Yang, Yuguo
Shi, Hongbo
Guo, Lei
Tao, Yang
Song, Bing
Author_xml – sequence: 1
  givenname: Yuguo
  surname: Yang
  fullname: Yang, Yuguo
– sequence: 2
  givenname: Hongbo
  surname: Shi
  fullname: Shi, Hongbo
  email: hbshi@ecust.edu.cn
– sequence: 3
  givenname: Bing
  surname: Song
  fullname: Song, Bing
  email: songbing@ecust.edu.cn
– sequence: 4
  givenname: Yang
  surname: Tao
  fullname: Tao, Yang
– sequence: 5
  givenname: Lei
  surname: Guo
  fullname: Guo, Lei
BookMark eNp9kE1OwzAQhb0oEi1wAVa-QIrt1EkqsUEVf1KlbmBtOeMxdZXYke0WcXsShTWr0byZN3rzrcjCB4-E3HO25oxXD6f1kHBYCybkKNRcVguyZFtZF7IR7JqsUjoxxrio-ZKEg8fCuB59csHrjhqEcB46NBSCv4TunGddn3NAD8FgpN8uH2kadExIE3a20DmjnxZpj3DU3qWe2hDpEANgSrQP3uUQnf-6JVdWdwnv_uoN-Xx5_ti9FfvD6_vuaV-AkGUupGmwqaAcGwTJSwaStQDQbLVuq41pbD0OoBIt8LYuwVi7Ka3UpjUgrLDlDRHzXYghpYhWDdH1Ov4oztSESZ3UhElNmNSMaTQ9ziYck10cRpXAjU-jcREhKxPcf_ZfmV96OA
Cites_doi 10.1016/j.conengprac.2020.104692
10.1016/j.psep.2021.04.010
10.1016/j.psep.2021.08.022
10.1007/978-3-030-01234-2_1
10.1002/aic.14888
10.1016/j.jprocont.2020.01.004
10.1016/j.ress.2023.109863
10.1109/CVPR.2019.00060
10.1016/j.isatra.2022.10.031
10.1016/j.asoc.2021.107751
10.1016/j.jprocont.2017.03.005
10.1016/j.actaastro.2024.04.012
10.1016/j.chemolab.2022.104711
10.1016/j.compchemeng.2020.107197
10.1016/j.psep.2023.04.020
10.1109/TASE.2022.3230687
10.1109/TII.2020.2988208
10.1016/j.aei.2024.102837
10.1016/j.psep.2023.03.017
10.1016/j.neunet.2022.11.001
10.1016/j.conengprac.2021.104811
10.1109/TCST.2006.883234
10.1109/TII.2021.3124578
10.1016/j.psep.2024.02.075
10.1016/j.psep.2023.02.078
10.1109/CVPR42600.2020.01155
10.1016/j.jfranklin.2022.11.029
10.1214/aoms/1177704472
10.1109/CVPR.2018.00745
10.1016/j.jprocont.2023.103107
10.1109/TNNLS.2023.3313728
10.1016/j.csda.2003.10.013
10.1109/ICASSP39728.2021.9414265
10.1109/ACCESS.2019.2938227
10.1016/j.psep.2019.12.006
10.1016/j.psep.2023.10.066
10.1016/j.compchemeng.2021.107654
10.1016/j.knosys.2024.112182
10.1016/j.psep.2023.06.040
10.1016/j.ces.2023.118900
10.1016/j.compchemeng.2021.107609
ContentType Journal Article
Copyright 2025 The Institution of Chemical Engineers
Copyright_xml – notice: 2025 The Institution of Chemical Engineers
DBID AAYXX
CITATION
DOI 10.1016/j.psep.2025.107156
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Environmental Sciences
ExternalDocumentID 10_1016_j_psep_2025_107156
S0957582025004239
GroupedDBID --K
--M
-QF
.~1
0R~
123
1B1
1~.
1~5
3EH
4.4
457
4G.
4P2
53G
5VS
7-5
71M
8P~
8WZ
A6W
AAEDT
AAEDW
AAHCO
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AARJD
AATTM
AAXKI
AAXUO
AAYWO
ABFNM
ABFRF
ABFYP
ABJNI
ABLST
ABMAC
ABNUV
ABWVN
ABXDB
ACDAQ
ACGFO
ACRLP
ACRPL
ACVFH
ADBBV
ADCNI
ADEWK
ADEZE
ADMLS
ADMUD
ADNMO
AEBSH
AEFWE
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AFXIZ
AGCQF
AGHFR
AGQPQ
AGRNS
AGUBO
AGYEJ
AHEUO
AHIDL
AHPOS
AIAGR
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKIFW
AKRWK
AKURH
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BELTK
BKOJK
BLECG
BLXMC
BNPGV
CAG
COF
CS3
DU5
EBS
EDH
EFJIC
EFKBS
EJD
ENUVR
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
GBLVA
HVGLF
HZ~
I-F
IHE
J1W
JARJE
KCYFY
KOM
M41
ML.
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
ROL
RPZ
SDF
SDG
SES
SJN
SPC
SPCBC
SSG
SSJ
SSR
SSZ
T5K
UNMZH
ZE2
~G-
9DU
AAYXX
ACLOT
BANNL
CITATION
EFLBG
~HD
ID FETCH-LOGICAL-c253t-5d8e86c3253ec5130c50bccc89aab64d8f73ecc62bc1b73cdff43f5adbdc2f2f3
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001486311900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0957-5820
IngestDate Sat Nov 29 06:57:21 EST 2025
Tue Jul 29 20:15:12 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Process monitoring
Process knowledge embedding
Data distribution alignment
Convolutional autoencoder
Variable-level feature extraction and interaction
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c253t-5d8e86c3253ec5130c50bccc89aab64d8f73ecc62bc1b73cdff43f5adbdc2f2f3
ParticipantIDs crossref_primary_10_1016_j_psep_2025_107156
elsevier_sciencedirect_doi_10_1016_j_psep_2025_107156
PublicationCentury 2000
PublicationDate July 2025
2025-07-00
PublicationDateYYYYMMDD 2025-07-01
PublicationDate_xml – month: 07
  year: 2025
  text: July 2025
PublicationDecade 2020
PublicationTitle Process safety and environmental protection
PublicationYear 2025
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Y. Liu, Z. Shao, N. Hoffmann, Global Attention Mechanism: Retain Information to Enhance Channel-spatial Interactions, 2021.10.48550/arXiv.2112.05561.
Song, Zheng, Jin, Shi, Tao, Tan (bib37) 2024
Feng, Zhao (bib14) 2021; 17
Yu, Liu, Ye (bib43) 2021; 70
Fang, Qu, Chai, Liu (bib13) 2023; 136
S. Woo, J. Park, J.-Y. Lee, I.S. Kweon, Cbam: convolutional block attention module. In: Proceedings of the Computer Vision-ECCV 2018, 2018, 3-19.
Yin, Wang, Tian, Jiang (bib42) 2024; 185
Ghosh, Ahmed, Khan, Rusli (bib16) 2020; 135
Chu, Mo, Hao, Lu, Wang (bib11) 2024; 21
Shang, Yang, Gao, Huang, Suykens, Huang (bib36) 2015; 61
Bai, Qi, Shu, Reniers, Khan, Chen, Liu (bib5) 2023; 176
Zhang, Yu, Ye (bib45) 2021; 111
Chen, Yu, Wang (bib10) 2020; 87
G. Klambauer, T. Unterthiner, A. Mayr, S. Hochreiter, Self-normalizing neural networks. In: Proceedings of the Thirty First International Conference on Neural Information Processing Systems, 2017, 972-981.
Lin, Miao, Chen, Ye, Xu, Liu, Jiang, Lu (bib26) 2024; 300
Bi, Wu, Xie, Ye, Zhao (bib8) 2023; 173
Ma, Ji, Xu, Wang, Sun (bib29) 2023; 278
Mugdadi, Ahmad (bib30) 2004; 47
D. Kingma, A method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (2014).
X. Zhang, J. Shi, M. Yang, X. Huang, A.S. Usmani, G. Chen, J. Fu, J.-B. Huang, J.Y. Li, Real-time pipeline leak detection and localization using an attention-based lstm approach, Process Safety and Environmental Protection (2023).
Jahanshahi, Zhu (bib18) 2024; 220
Kopbayev, Khan, Yang, Halim (bib23) 2022; 158
Li, Peng, Zhang, Wang, Shen (bib24) 2024; 35
Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, Q. Hu, Eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, 11531-11539.
Chen, Wang (bib9) 2021; 107
Lin, Sun, Wang (bib27) 2023; 360
Yu, J., , 2024)102837.Mutual stacked autoencoder for unsupervised fault detection under complex multi-residual correlations. Adv. Eng. Inform., 62, 102837.
Thill, Konen, Wang, Bäck (bib39) 2021; 112
Parzen (bib31) 1962; 33
H. Phan, H.L. Nguyen, O.Y. Chén, P. Koch, N.Q.K. Duong, I. McLoughlin, A. Mertins, Self-attention generative adversarial network for speech enhancement. In: Proceedings of the ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, 7103-7107.
Zhu, Shi, Song, Tao, Tan (bib48) 2022; 18
Bauer, Cox, Caveness, Downs, Thornhill (bib7) 2007; 15
Arunthavanathan, Khan, Ahmed, Imtiaz (bib4) 2021; 145
Rani, Tripura, Kodamana, Chakraborty, Tamboli (bib34) 2023; 173
Ji, Hou, Wu (bib19) 2023; 131
Bathelt, Ricker, Jelali (bib6) 2015; 48
Saufi, Ahmad, Leong, Lim (bib35) 2019; 7
Deng, Li, Huang, Wu, Yang, Gui (bib12) 2023; 158
Amin, Khan, Ahmed, Imtiaz (bib2) 2021; 150
Su, Shi, Zhou, Bai, Wang (bib38) 2024; 244
T. Kim, J. Kim, Y. Tae, C. Park, J.-H. Choi, J. Choo, Reversible instance normalization for accurate time-series forecasting against distribution shift. In: Proceedings of the International Conference on Learning Representations, 2022.
X. Li, W. Wang, X. Hu, J. Yang, Selective kernel networks. In: Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 510-519.
Qian, Song, Yao, Zhu, Zhang (bib33) 2022; 231
Ali, Zhang, Gao (bib1) 2023; 180
Arunthavanathan, Khan, Ahmed, Imtiaz (bib3) 2021; 154
Gajjar, Kulahci, Palazoglu (bib15) 2018; 67
Zhang, Qiu (bib46) 2022; 158
J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, In: Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, 7132-7141.
Zhang (10.1016/j.psep.2025.107156_bib46) 2022; 158
Yin (10.1016/j.psep.2025.107156_bib42) 2024; 185
10.1016/j.psep.2025.107156_bib40
Shang (10.1016/j.psep.2025.107156_bib36) 2015; 61
Deng (10.1016/j.psep.2025.107156_bib12) 2023; 158
Su (10.1016/j.psep.2025.107156_bib38) 2024; 244
Arunthavanathan (10.1016/j.psep.2025.107156_bib3) 2021; 154
Lin (10.1016/j.psep.2025.107156_bib26) 2024; 300
Bathelt (10.1016/j.psep.2025.107156_bib6) 2015; 48
Gajjar (10.1016/j.psep.2025.107156_bib15) 2018; 67
Lin (10.1016/j.psep.2025.107156_bib27) 2023; 360
Kopbayev (10.1016/j.psep.2025.107156_bib23) 2022; 158
Thill (10.1016/j.psep.2025.107156_bib39) 2021; 112
Parzen (10.1016/j.psep.2025.107156_bib31) 1962; 33
Zhu (10.1016/j.psep.2025.107156_bib48) 2022; 18
10.1016/j.psep.2025.107156_bib17
Chen (10.1016/j.psep.2025.107156_bib10) 2020; 87
Rani (10.1016/j.psep.2025.107156_bib34) 2023; 173
Yu (10.1016/j.psep.2025.107156_bib43) 2021; 70
Fang (10.1016/j.psep.2025.107156_bib13) 2023; 136
Li (10.1016/j.psep.2025.107156_bib24) 2024; 35
Ali (10.1016/j.psep.2025.107156_bib1) 2023; 180
Arunthavanathan (10.1016/j.psep.2025.107156_bib4) 2021; 145
10.1016/j.psep.2025.107156_bib32
Saufi (10.1016/j.psep.2025.107156_bib35) 2019; 7
Bauer (10.1016/j.psep.2025.107156_bib7) 2007; 15
Jahanshahi (10.1016/j.psep.2025.107156_bib18) 2024; 220
Zhang (10.1016/j.psep.2025.107156_bib45) 2021; 111
Feng (10.1016/j.psep.2025.107156_bib14) 2021; 17
Ghosh (10.1016/j.psep.2025.107156_bib16) 2020; 135
Song (10.1016/j.psep.2025.107156_bib37) 2024
Chu (10.1016/j.psep.2025.107156_bib11) 2024; 21
Bai (10.1016/j.psep.2025.107156_bib5) 2023; 176
Amin (10.1016/j.psep.2025.107156_bib2) 2021; 150
Ji (10.1016/j.psep.2025.107156_bib19) 2023; 131
10.1016/j.psep.2025.107156_bib28
Bi (10.1016/j.psep.2025.107156_bib8) 2023; 173
Qian (10.1016/j.psep.2025.107156_bib33) 2022; 231
10.1016/j.psep.2025.107156_bib22
10.1016/j.psep.2025.107156_bib44
Chen (10.1016/j.psep.2025.107156_bib9) 2021; 107
10.1016/j.psep.2025.107156_bib21
10.1016/j.psep.2025.107156_bib20
Ma (10.1016/j.psep.2025.107156_bib29) 2023; 278
10.1016/j.psep.2025.107156_bib41
10.1016/j.psep.2025.107156_bib25
Mugdadi (10.1016/j.psep.2025.107156_bib30) 2004; 47
10.1016/j.psep.2025.107156_bib47
References_xml – volume: 150
  start-page: 123
  year: 2021
  end-page: 136
  ident: bib2
  article-title: Risk-based fault detection and diagnosis for nonlinear and non-gaussian process systems using r-vine copula
  publication-title: Process Saf. Environ. Prot.
– volume: 15
  start-page: 12
  year: 2007
  end-page: 21
  ident: bib7
  article-title: Finding the direction of disturbance propagation in a chemical process using transfer entropy
  publication-title: IEEE Trans. Control Syst. Technol.
– volume: 87
  start-page: 54
  year: 2020
  end-page: 67
  ident: bib10
  article-title: One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes
  publication-title: J. Process Control
– reference: G. Klambauer, T. Unterthiner, A. Mayr, S. Hochreiter, Self-normalizing neural networks. In: Proceedings of the Thirty First International Conference on Neural Information Processing Systems, 2017, 972-981.
– volume: 70
  start-page: 1
  year: 2021
  end-page: 15
  ident: bib43
  article-title: Convolutional long short-term memory autoencoder-based feature learning for fault detection in industrial processes
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 180
  start-page: 1053
  year: 2023
  end-page: 1075
  ident: bib1
  article-title: Multiscale monitoring of industrial chemical process using wavelet-entropy aided machine learning approach
  publication-title: Process Saf. Environ. Prot.
– volume: 61
  start-page: 3666
  year: 2015
  end-page: 3682
  ident: bib36
  article-title: Concurrent monitoring of operating condition deviations and process dynamics anomalies with slow feature analysis
  publication-title: AIChE J.
– volume: 135
  start-page: 70
  year: 2020
  end-page: 80
  ident: bib16
  article-title: Process safety assessment considering multivariate non-linear dependence among process variables
  publication-title: Process Saf. Environ. Prot.
– volume: 244
  year: 2024
  ident: bib38
  article-title: Knowledge-informed deep networks for robust fault diagnosis of rolling bearings
  publication-title: Reliab. Eng. Syst. Saf.
– reference: X. Zhang, J. Shi, M. Yang, X. Huang, A.S. Usmani, G. Chen, J. Fu, J.-B. Huang, J.Y. Li, Real-time pipeline leak detection and localization using an attention-based lstm approach, Process Safety and Environmental Protection (2023).
– volume: 18
  start-page: 4555
  year: 2022
  end-page: 4565
  ident: bib48
  article-title: Convolutional neural network based feature learning for large-scale quality-related process monitoring
  publication-title: IEEE Trans. Ind. Inform.
– reference: J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, In: Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, 7132-7141.
– volume: 185
  start-page: 492
  year: 2024
  end-page: 510
  ident: bib42
  article-title: Distributed incipient fault detection with causality-based multi-perspective subblock partitioning for large-scale nonlinear processes
  publication-title: Process Saf. Environ. Prot.
– volume: 111
  year: 2021
  ident: bib45
  article-title: Sparsity and manifold regularized convolutional auto-encoders-based feature learning for fault detection of multivariate processes
  publication-title: Control Eng. Pract.
– reference: T. Kim, J. Kim, Y. Tae, C. Park, J.-H. Choi, J. Choo, Reversible instance normalization for accurate time-series forecasting against distribution shift. In: Proceedings of the International Conference on Learning Representations, 2022.
– start-page: 1
  year: 2024
  end-page: 10
  ident: bib37
  article-title: A fault-targeted gated recurrent unit-canonical correlation analysis method for incipient fault detection
  publication-title: IEEE Trans. Ind. Inform.
– volume: 173
  start-page: 215
  year: 2023
  end-page: 228
  ident: bib34
  article-title: Fault detection and isolation using probabilistic wavelet neural operator auto-encoder with application to dynamic processes
  publication-title: Process Saf. Environ. Prot.
– volume: 47
  start-page: 49
  year: 2004
  end-page: 62
  ident: bib30
  article-title: A bandwidth selection for kernel density estimation of functions of random variables
  publication-title: Comput. Stat. Data Anal.
– reference: H. Phan, H.L. Nguyen, O.Y. Chén, P. Koch, N.Q.K. Duong, I. McLoughlin, A. Mertins, Self-attention generative adversarial network for speech enhancement. In: Proceedings of the ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, 7103-7107.
– volume: 48
  start-page: 309
  year: 2015
  end-page: 314
  ident: bib6
  article-title: Revision of the Tennessee Eastman process model
  publication-title: In: Proceedings of the IFAC Symposium on Advanced Control of Chemical Processes ADCHEM
– volume: 360
  start-page: 1
  year: 2023
  end-page: 17
  ident: bib27
  article-title: Improved key performance indicator-partial least squares method for nonlinear process fault detection based on just-in-time learning
  publication-title: J. Frankl. Inst.
– reference: D. Kingma, A method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (2014).
– reference: Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, Q. Hu, Eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, 11531-11539.
– volume: 112
  year: 2021
  ident: bib39
  article-title: Temporal convolutional autoencoder for unsupervised anomaly detection in time series
  publication-title: Appl. Soft Comput.
– volume: 35
  start-page: 6194
  year: 2024
  end-page: 6205
  ident: bib24
  article-title: Sccam: supervised contrastive convolutional attention mechanism for ante-hoc interpretable fault diagnosis with limited fault samples
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 131
  year: 2023
  ident: bib19
  article-title: Modified performance-enhanced pca for incipient fault detection of dynamic industrial processes
  publication-title: J. Process Control
– volume: 67
  start-page: 112
  year: 2018
  end-page: 128
  ident: bib15
  article-title: Real-time fault detection and diagnosis using sparse principal component analysis
  publication-title: J. Process Control
– volume: 300
  year: 2024
  ident: bib26
  article-title: Fault detection and isolation for multi-type sensors in nuclear power plants via a knowledge-guided spatial–temporal model
  publication-title: Knowl. Based Syst.
– volume: 220
  start-page: 37
  year: 2024
  end-page: 61
  ident: bib18
  article-title: Review of machine learning in robotic grasping control in space application
  publication-title: Acta Astronaut.
– volume: 176
  start-page: 411
  year: 2023
  end-page: 420
  ident: bib5
  article-title: Why do major chemical accidents still happen in China: analysis from a process safety management perspective
  publication-title: Process Saf. Environ. Prot.
– volume: 158
  start-page: 30
  year: 2023
  end-page: 41
  ident: bib12
  article-title: Lstmed: an uneven dynamic process monitoring method based on lstm and autoencoder neural network
  publication-title: Neural Netw.
– reference: Yu, J., , 2024)102837.Mutual stacked autoencoder for unsupervised fault detection under complex multi-residual correlations. Adv. Eng. Inform., 62, 102837.
– reference: X. Li, W. Wang, X. Hu, J. Yang, Selective kernel networks. In: Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 510-519.
– volume: 145
  year: 2021
  ident: bib4
  article-title: An analysis of process fault diagnosis methods from safety perspectives
  publication-title: Comput. Chem. Eng.
– volume: 107
  year: 2021
  ident: bib9
  article-title: Key-performance-indicator-related state monitoring based on kernel canonical correlation analysis
  publication-title: Control Eng. Pract.
– volume: 278
  year: 2023
  ident: bib29
  article-title: Spatial correlation extraction for chemical process fault detection using image enhancement technique aided convolutional autoencoder
  publication-title: Chem. Eng. Sci.
– reference: S. Woo, J. Park, J.-Y. Lee, I.S. Kweon, Cbam: convolutional block attention module. In: Proceedings of the Computer Vision-ECCV 2018, 2018, 3-19.
– volume: 173
  start-page: 163
  year: 2023
  end-page: 177
  ident: bib8
  article-title: Large-scale chemical process causal discovery from big data with transformer-based deep learning
  publication-title: Process Saf. Environ. Prot.
– volume: 158
  year: 2022
  ident: bib46
  article-title: A dynamic-inner convolutional autoencoder for process monitoring
  publication-title: Comput. Chem. Eng.
– volume: 17
  start-page: 1852
  year: 2021
  end-page: 1862
  ident: bib14
  article-title: Fault description based attribute transfer for zero-sample industrial fault diagnosis
  publication-title: IEEE Trans. Ind. Inform.
– volume: 33
  start-page: 1065
  year: 1962
  end-page: 1076
  ident: bib31
  article-title: On estimation of a probability density function and mode
  publication-title: Ann. Math. Stat.
– volume: 231
  year: 2022
  ident: bib33
  article-title: A review on autoencoder based representation learning for fault detection and diagnosis in industrial processes
  publication-title: Chemom. Intell. Lab. Syst.
– volume: 154
  start-page: 467
  year: 2021
  end-page: 479
  ident: bib3
  article-title: A deep learning model for process fault prognosis
  publication-title: Process Saf. Environ. Prot.
– volume: 21
  year: 2024
  ident: bib11
  article-title: Operating performance assessment of complex nonlinear industrial process based on kernel locally linear embedding pls
  publication-title: IEEE Trans. Autom. Sci. Eng.
– volume: 7
  start-page: 122644
  year: 2019
  end-page: 122662
  ident: bib35
  article-title: Challenges and opportunities of deep learning models for machinery fault detection and diagnosis: a review
  publication-title: IEEE Access
– volume: 158
  year: 2022
  ident: bib23
  article-title: Fault detection and diagnosis to enhance safety in digitalized process system
  publication-title: Comput. Chem. Eng.
– reference: Y. Liu, Z. Shao, N. Hoffmann, Global Attention Mechanism: Retain Information to Enhance Channel-spatial Interactions, 2021.10.48550/arXiv.2112.05561.
– volume: 136
  start-page: 428
  year: 2023
  end-page: 441
  ident: bib13
  article-title: Adaptive multiscale and dual subnet convolutional auto-encoder for intermittent fault detection of analog circuits in noise environment
  publication-title: ISA Trans.
– volume: 107
  year: 2021
  ident: 10.1016/j.psep.2025.107156_bib9
  article-title: Key-performance-indicator-related state monitoring based on kernel canonical correlation analysis
  publication-title: Control Eng. Pract.
  doi: 10.1016/j.conengprac.2020.104692
– volume: 150
  start-page: 123
  year: 2021
  ident: 10.1016/j.psep.2025.107156_bib2
  article-title: Risk-based fault detection and diagnosis for nonlinear and non-gaussian process systems using r-vine copula
  publication-title: Process Saf. Environ. Prot.
  doi: 10.1016/j.psep.2021.04.010
– volume: 154
  start-page: 467
  year: 2021
  ident: 10.1016/j.psep.2025.107156_bib3
  article-title: A deep learning model for process fault prognosis
  publication-title: Process Saf. Environ. Prot.
  doi: 10.1016/j.psep.2021.08.022
– ident: 10.1016/j.psep.2025.107156_bib41
  doi: 10.1007/978-3-030-01234-2_1
– volume: 61
  start-page: 3666
  year: 2015
  ident: 10.1016/j.psep.2025.107156_bib36
  article-title: Concurrent monitoring of operating condition deviations and process dynamics anomalies with slow feature analysis
  publication-title: AIChE J.
  doi: 10.1002/aic.14888
– volume: 87
  start-page: 54
  year: 2020
  ident: 10.1016/j.psep.2025.107156_bib10
  article-title: One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes
  publication-title: J. Process Control
  doi: 10.1016/j.jprocont.2020.01.004
– ident: 10.1016/j.psep.2025.107156_bib28
– volume: 244
  year: 2024
  ident: 10.1016/j.psep.2025.107156_bib38
  article-title: Knowledge-informed deep networks for robust fault diagnosis of rolling bearings
  publication-title: Reliab. Eng. Syst. Saf.
  doi: 10.1016/j.ress.2023.109863
– ident: 10.1016/j.psep.2025.107156_bib25
  doi: 10.1109/CVPR.2019.00060
– volume: 136
  start-page: 428
  year: 2023
  ident: 10.1016/j.psep.2025.107156_bib13
  article-title: Adaptive multiscale and dual subnet convolutional auto-encoder for intermittent fault detection of analog circuits in noise environment
  publication-title: ISA Trans.
  doi: 10.1016/j.isatra.2022.10.031
– volume: 112
  year: 2021
  ident: 10.1016/j.psep.2025.107156_bib39
  article-title: Temporal convolutional autoencoder for unsupervised anomaly detection in time series
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2021.107751
– volume: 67
  start-page: 112
  year: 2018
  ident: 10.1016/j.psep.2025.107156_bib15
  article-title: Real-time fault detection and diagnosis using sparse principal component analysis
  publication-title: J. Process Control
  doi: 10.1016/j.jprocont.2017.03.005
– volume: 220
  start-page: 37
  year: 2024
  ident: 10.1016/j.psep.2025.107156_bib18
  article-title: Review of machine learning in robotic grasping control in space application
  publication-title: Acta Astronaut.
  doi: 10.1016/j.actaastro.2024.04.012
– volume: 231
  year: 2022
  ident: 10.1016/j.psep.2025.107156_bib33
  article-title: A review on autoencoder based representation learning for fault detection and diagnosis in industrial processes
  publication-title: Chemom. Intell. Lab. Syst.
  doi: 10.1016/j.chemolab.2022.104711
– volume: 145
  year: 2021
  ident: 10.1016/j.psep.2025.107156_bib4
  article-title: An analysis of process fault diagnosis methods from safety perspectives
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2020.107197
– volume: 48
  start-page: 309
  year: 2015
  ident: 10.1016/j.psep.2025.107156_bib6
  article-title: Revision of the Tennessee Eastman process model
  publication-title: In: Proceedings of the IFAC Symposium on Advanced Control of Chemical Processes ADCHEM
– ident: 10.1016/j.psep.2025.107156_bib21
– start-page: 1
  year: 2024
  ident: 10.1016/j.psep.2025.107156_bib37
  article-title: A fault-targeted gated recurrent unit-canonical correlation analysis method for incipient fault detection
  publication-title: IEEE Trans. Ind. Inform.
– ident: 10.1016/j.psep.2025.107156_bib47
  doi: 10.1016/j.psep.2023.04.020
– volume: 21
  year: 2024
  ident: 10.1016/j.psep.2025.107156_bib11
  article-title: Operating performance assessment of complex nonlinear industrial process based on kernel locally linear embedding pls
  publication-title: IEEE Trans. Autom. Sci. Eng.
  doi: 10.1109/TASE.2022.3230687
– volume: 17
  start-page: 1852
  year: 2021
  ident: 10.1016/j.psep.2025.107156_bib14
  article-title: Fault description based attribute transfer for zero-sample industrial fault diagnosis
  publication-title: IEEE Trans. Ind. Inform.
  doi: 10.1109/TII.2020.2988208
– ident: 10.1016/j.psep.2025.107156_bib44
  doi: 10.1016/j.aei.2024.102837
– volume: 173
  start-page: 163
  year: 2023
  ident: 10.1016/j.psep.2025.107156_bib8
  article-title: Large-scale chemical process causal discovery from big data with transformer-based deep learning
  publication-title: Process Saf. Environ. Prot.
  doi: 10.1016/j.psep.2023.03.017
– volume: 158
  start-page: 30
  year: 2023
  ident: 10.1016/j.psep.2025.107156_bib12
  article-title: Lstmed: an uneven dynamic process monitoring method based on lstm and autoencoder neural network
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2022.11.001
– volume: 70
  start-page: 1
  year: 2021
  ident: 10.1016/j.psep.2025.107156_bib43
  article-title: Convolutional long short-term memory autoencoder-based feature learning for fault detection in industrial processes
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 111
  year: 2021
  ident: 10.1016/j.psep.2025.107156_bib45
  article-title: Sparsity and manifold regularized convolutional auto-encoders-based feature learning for fault detection of multivariate processes
  publication-title: Control Eng. Pract.
  doi: 10.1016/j.conengprac.2021.104811
– volume: 15
  start-page: 12
  year: 2007
  ident: 10.1016/j.psep.2025.107156_bib7
  article-title: Finding the direction of disturbance propagation in a chemical process using transfer entropy
  publication-title: IEEE Trans. Control Syst. Technol.
  doi: 10.1109/TCST.2006.883234
– volume: 18
  start-page: 4555
  year: 2022
  ident: 10.1016/j.psep.2025.107156_bib48
  article-title: Convolutional neural network based feature learning for large-scale quality-related process monitoring
  publication-title: IEEE Trans. Ind. Inform.
  doi: 10.1109/TII.2021.3124578
– volume: 185
  start-page: 492
  year: 2024
  ident: 10.1016/j.psep.2025.107156_bib42
  article-title: Distributed incipient fault detection with causality-based multi-perspective subblock partitioning for large-scale nonlinear processes
  publication-title: Process Saf. Environ. Prot.
  doi: 10.1016/j.psep.2024.02.075
– volume: 173
  start-page: 215
  year: 2023
  ident: 10.1016/j.psep.2025.107156_bib34
  article-title: Fault detection and isolation using probabilistic wavelet neural operator auto-encoder with application to dynamic processes
  publication-title: Process Saf. Environ. Prot.
  doi: 10.1016/j.psep.2023.02.078
– ident: 10.1016/j.psep.2025.107156_bib40
  doi: 10.1109/CVPR42600.2020.01155
– volume: 360
  start-page: 1
  year: 2023
  ident: 10.1016/j.psep.2025.107156_bib27
  article-title: Improved key performance indicator-partial least squares method for nonlinear process fault detection based on just-in-time learning
  publication-title: J. Frankl. Inst.
  doi: 10.1016/j.jfranklin.2022.11.029
– volume: 33
  start-page: 1065
  year: 1962
  ident: 10.1016/j.psep.2025.107156_bib31
  article-title: On estimation of a probability density function and mode
  publication-title: Ann. Math. Stat.
  doi: 10.1214/aoms/1177704472
– ident: 10.1016/j.psep.2025.107156_bib17
  doi: 10.1109/CVPR.2018.00745
– ident: 10.1016/j.psep.2025.107156_bib20
– volume: 131
  year: 2023
  ident: 10.1016/j.psep.2025.107156_bib19
  article-title: Modified performance-enhanced pca for incipient fault detection of dynamic industrial processes
  publication-title: J. Process Control
  doi: 10.1016/j.jprocont.2023.103107
– volume: 35
  start-page: 6194
  year: 2024
  ident: 10.1016/j.psep.2025.107156_bib24
  article-title: Sccam: supervised contrastive convolutional attention mechanism for ante-hoc interpretable fault diagnosis with limited fault samples
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2023.3313728
– volume: 47
  start-page: 49
  year: 2004
  ident: 10.1016/j.psep.2025.107156_bib30
  article-title: A bandwidth selection for kernel density estimation of functions of random variables
  publication-title: Comput. Stat. Data Anal.
  doi: 10.1016/j.csda.2003.10.013
– ident: 10.1016/j.psep.2025.107156_bib22
– ident: 10.1016/j.psep.2025.107156_bib32
  doi: 10.1109/ICASSP39728.2021.9414265
– volume: 7
  start-page: 122644
  year: 2019
  ident: 10.1016/j.psep.2025.107156_bib35
  article-title: Challenges and opportunities of deep learning models for machinery fault detection and diagnosis: a review
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2938227
– volume: 135
  start-page: 70
  year: 2020
  ident: 10.1016/j.psep.2025.107156_bib16
  article-title: Process safety assessment considering multivariate non-linear dependence among process variables
  publication-title: Process Saf. Environ. Prot.
  doi: 10.1016/j.psep.2019.12.006
– volume: 180
  start-page: 1053
  year: 2023
  ident: 10.1016/j.psep.2025.107156_bib1
  article-title: Multiscale monitoring of industrial chemical process using wavelet-entropy aided machine learning approach
  publication-title: Process Saf. Environ. Prot.
  doi: 10.1016/j.psep.2023.10.066
– volume: 158
  year: 2022
  ident: 10.1016/j.psep.2025.107156_bib46
  article-title: A dynamic-inner convolutional autoencoder for process monitoring
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2021.107654
– volume: 300
  year: 2024
  ident: 10.1016/j.psep.2025.107156_bib26
  article-title: Fault detection and isolation for multi-type sensors in nuclear power plants via a knowledge-guided spatial–temporal model
  publication-title: Knowl. Based Syst.
  doi: 10.1016/j.knosys.2024.112182
– volume: 176
  start-page: 411
  year: 2023
  ident: 10.1016/j.psep.2025.107156_bib5
  article-title: Why do major chemical accidents still happen in China: analysis from a process safety management perspective
  publication-title: Process Saf. Environ. Prot.
  doi: 10.1016/j.psep.2023.06.040
– volume: 278
  year: 2023
  ident: 10.1016/j.psep.2025.107156_bib29
  article-title: Spatial correlation extraction for chemical process fault detection using image enhancement technique aided convolutional autoencoder
  publication-title: Chem. Eng. Sci.
  doi: 10.1016/j.ces.2023.118900
– volume: 158
  year: 2022
  ident: 10.1016/j.psep.2025.107156_bib23
  article-title: Fault detection and diagnosis to enhance safety in digitalized process system
  publication-title: Comput. Chem. Eng.
  doi: 10.1016/j.compchemeng.2021.107609
SSID ssj0001271
Score 2.3928468
Snippet Industrial processes are constantly disturbed by environmental and human factors during operation. Undifferentiated alarming of these disturbances will bring...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 107156
SubjectTerms Convolutional autoencoder
Data distribution alignment
Process knowledge embedding
Process monitoring
Variable-level feature extraction and interaction
Title One-dimensional decoupled convolutional autoencoder with sparse self-attention mechanism for process monitoring
URI https://dx.doi.org/10.1016/j.psep.2025.107156
Volume 199
WOSCitedRecordID wos001486311900001&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: ScienceDirect
  issn: 0957-5820
  databaseCode: AIEXJ
  dateStart: 19961101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0001271
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Nb9MwFLfKxgEOaAwmNhjygVvkqXHixjkOVAQIDQ5D6k6R44_B1CVR00z7P_YP8xw7Hy0fYgcuUeu2dpT30_N7r7_3M0JvmAarsqkiOVMpiRnlRFAVklTKNJXtHtRa-nNydsYXi_TrZHLX9cLcLJOi4Le3afVfTQ1jYGzbOnsPc_eTwgC8BqPDFcwO138y_JdCE2U1-53eRqAgwWyqpVYtw9wvbRUCmnVpVSytmIQjqleQ5Oqg1ktDrOqm40Fea9sbbI_SsITEyvUVBNetK1h1-56Pbn3XQVALY5mgtiY_aqSzPV9OFWL03_-Fr1dfNJdN2Zd7vruztMviMh8GPXn4bbdoW29oK712knH5grKe6jrUIRPCOJ1uuGR3aJJ3qpChhk59_Bd_70oPVydVra34KGUnw5c3xbW3Nr2eitix3K4yO0dm58jcHA_QLk1YCt5-9_TjfPGp3-BD2ubx_Z37XixHG9y-k9_HO6MY5nwPPfHJBz51oHmKJrrYR49HkpT76GA-Nhj2rr9-hsotXOEeV3gDV3iEK2xxhR2u8CaucI8rDLjCHld4wNVz9O39_PzdB-JP6yCSsmhNmOKaz2QEb7RkEBpJNs2llDwVIp_FipsEPpAzmsswTyKpjIkjw4TKlaSGmugA7RRloV8gnAgBafEsoVzrOFZKGAj7VSimVAtqFDtEQfdMs8qJsmR_tuMhYt1jz3xY6cLFDFD0l98d3WuVl-jRAO9XaGe9avQxeihv1j_q1WsPoZ_1ZaKQ
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=One-dimensional+decoupled+convolutional+autoencoder+with+sparse+self-attention+mechanism+for+process+monitoring&rft.jtitle=Process+safety+and+environmental+protection&rft.au=Yang%2C+Yuguo&rft.au=Shi%2C+Hongbo&rft.au=Song%2C+Bing&rft.au=Tao%2C+Yang&rft.date=2025-07-01&rft.issn=0957-5820&rft.volume=199&rft.spage=107156&rft_id=info:doi/10.1016%2Fj.psep.2025.107156&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_psep_2025_107156
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0957-5820&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0957-5820&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0957-5820&client=summon