Enhancing equipment safeguarding in IIoT: A self-supervised fault diagnosis paradigm based on asymmetric graph autoencoder

Thanks to the sufficient monitoring data provided by Industrial Internet of Things (IIoT), intelligent fault diagnosis technology has demonstrated remarkable performance in safeguarding equipment. However, the effectiveness of existing methods heavily relies on manually labeled data. Unfortunately,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Knowledge-based systems Jg. 296; S. 111922
Hauptverfasser: Chen, Zhuohang, Liu, Shen, Li, Chao, Chang, Yuanhong, Chen, Jinglong, Feng, Gaoshan, He, Shuilong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 19.07.2024
Schlagworte:
ISSN:0950-7051, 1872-7409
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Thanks to the sufficient monitoring data provided by Industrial Internet of Things (IIoT), intelligent fault diagnosis technology has demonstrated remarkable performance in safeguarding equipment. However, the effectiveness of existing methods heavily relies on manually labeled data. Unfortunately, data collected from equipment often lacks labels, leading to a scarcity of fault data. Furthermore, an additional significant challenge is the feature domain shift resulting from speed variation. To address this, we propose a self-supervised paradigm based on an asymmetric graph autoencoder for fault diagnosis under domain shift, aiming to mine valuable health information from unlabeled data. Unlike Euclidean-based methods, the proposed method transforms time series samples into graphs and extracts domain invariant features through information interaction between nodes. To efficiently mine unlabeled data and enhance generalization, the self-supervised learning paradigm utilizes an asymmetric graph autoencoder architecture. This architecture includes an encoder that learns self-supervised representations from unlabeled samples and a lightweight decoder that predicts the original input. Specifically, we mask a portion of input samples and predict the original input from learned self-supervised representations. In downstream task, the pre-trained encoder is fine-tuned using limited labeled data for specific fault diagnosis task. The proposed method is evaluated on three mechanical fault simulation experiments, and the results demonstrate the its superiority and potential.
AbstractList Thanks to the sufficient monitoring data provided by Industrial Internet of Things (IIoT), intelligent fault diagnosis technology has demonstrated remarkable performance in safeguarding equipment. However, the effectiveness of existing methods heavily relies on manually labeled data. Unfortunately, data collected from equipment often lacks labels, leading to a scarcity of fault data. Furthermore, an additional significant challenge is the feature domain shift resulting from speed variation. To address this, we propose a self-supervised paradigm based on an asymmetric graph autoencoder for fault diagnosis under domain shift, aiming to mine valuable health information from unlabeled data. Unlike Euclidean-based methods, the proposed method transforms time series samples into graphs and extracts domain invariant features through information interaction between nodes. To efficiently mine unlabeled data and enhance generalization, the self-supervised learning paradigm utilizes an asymmetric graph autoencoder architecture. This architecture includes an encoder that learns self-supervised representations from unlabeled samples and a lightweight decoder that predicts the original input. Specifically, we mask a portion of input samples and predict the original input from learned self-supervised representations. In downstream task, the pre-trained encoder is fine-tuned using limited labeled data for specific fault diagnosis task. The proposed method is evaluated on three mechanical fault simulation experiments, and the results demonstrate the its superiority and potential.
ArticleNumber 111922
Author Chen, Jinglong
Chen, Zhuohang
Li, Chao
Chang, Yuanhong
Feng, Gaoshan
Liu, Shen
He, Shuilong
Author_xml – sequence: 1
  givenname: Zhuohang
  orcidid: 0000-0002-6721-8640
  surname: Chen
  fullname: Chen, Zhuohang
  organization: State Key Laboratory for Manufacturing and Systems Engineering, Xi'an Jiaotong University, Xi'an 710049, PR China
– sequence: 2
  givenname: Shen
  surname: Liu
  fullname: Liu, Shen
  organization: State Key Laboratory for Manufacturing and Systems Engineering, Xi'an Jiaotong University, Xi'an 710049, PR China
– sequence: 3
  givenname: Chao
  surname: Li
  fullname: Li, Chao
  organization: State Key Laboratory for Manufacturing and Systems Engineering, Xi'an Jiaotong University, Xi'an 710049, PR China
– sequence: 4
  givenname: Yuanhong
  orcidid: 0000-0003-4655-9400
  surname: Chang
  fullname: Chang, Yuanhong
  organization: State Key Laboratory for Manufacturing and Systems Engineering, Xi'an Jiaotong University, Xi'an 710049, PR China
– sequence: 5
  givenname: Jinglong
  orcidid: 0000-0002-9805-9849
  surname: Chen
  fullname: Chen, Jinglong
  email: jlstrive2008@mail.xjtu.edu.cn
  organization: State Key Laboratory for Manufacturing and Systems Engineering, Xi'an Jiaotong University, Xi'an 710049, PR China
– sequence: 6
  givenname: Gaoshan
  surname: Feng
  fullname: Feng, Gaoshan
  organization: Dongfeng Liuzhou Motor Co., Ltd., Liuzhou 545005, China
– sequence: 7
  givenname: Shuilong
  surname: He
  fullname: He, Shuilong
  organization: School of Mechanical and Electrical Engineering, Guilin University of Electronic Technology, Guilin 541004, China
BookMark eNqFkE1LAzEQhoMoWD_-gYf8ga1JdrvZ7UEQ8aMgeNFzmCaTbWo3WZOsUH-9LfXkQU8DMzzv8D5n5NgHj4RccTbljNfX6-m7D2mbpoKJaso5b4U4IhPeSFHIirXHZMLaGSskm_FTcpbSmjEmBG8m5Over8Br5zuKH6MbevSZJrDYjRDNfu08XSzC65ze0oQbW6RxwPjpEhpqYdxkahx0u_cu0QEiGNf1dAn7c_AU0rbvMUenaRdhWFEYc0Cvg8F4QU4sbBJe_sxz8vZw_3r3VDy_PC7ubp8LXbI6F0aIZQto9VJXupGltnUJ0iDjyBrBTcXqGlCCLEWrZ6XkZS1NCw3XzJTW2vKczA-5OoaUIlqlXYbsgs8R3EZxpvYW1VodLKq9RXWwuIOrX_AQXQ9x-x92c8BwV-zTYVRJu11vNC6izsoE93fANyyklAg
CitedBy_id crossref_primary_10_1016_j_knosys_2025_113278
crossref_primary_10_1063_5_0255451
crossref_primary_10_1177_14759217251343339
crossref_primary_10_1109_JIOT_2024_3464854
crossref_primary_10_1088_1361_6501_adf7c9
crossref_primary_10_32604_cmes_2024_055633
crossref_primary_10_1016_j_knosys_2025_113275
Cites_doi 10.1109/JIOT.2022.3163606
10.1016/j.ymssp.2017.03.034
10.1016/j.ymssp.2023.110462
10.1016/j.knosys.2022.109393
10.1016/j.compind.2021.103557
10.1016/j.jsv.2015.03.018
10.1109/TIM.2021.3127634
10.1016/j.eswa.2023.120696
10.1016/j.aiopen.2021.01.001
10.1016/j.isatra.2021.10.025
10.1016/j.knosys.2021.107978
10.1016/j.knosys.2022.109846
10.1109/JIOT.2022.3181737
10.1016/j.ymssp.2022.109174
10.1016/j.compind.2022.103810
10.1016/j.ymssp.2022.110071
10.1016/j.ress.2021.108126
10.1016/j.isatra.2021.02.042
10.1016/j.jmsy.2022.08.007
10.1016/j.isatra.2022.04.043
10.1109/TPAMI.2020.2992393
10.1109/TNNLS.2020.2978386
10.1016/j.knosys.2022.110008
10.1109/TPAMI.2022.3152247
ContentType Journal Article
Copyright 2024 Elsevier B.V.
Copyright_xml – notice: 2024 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.knosys.2024.111922
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-7409
ExternalDocumentID 10_1016_j_knosys_2024_111922
S0950705124005562
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
4.4
457
4G.
5VS
7-5
71M
77K
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
AAYFN
ABAOU
ABBOA
ABIVO
ABJNI
ABMAC
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
ADGUI
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ARUGR
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
JJJVA
KOM
LG9
LY7
M41
MHUIS
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
RIG
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SST
SSV
SSW
SSZ
T5K
WH7
XPP
ZMT
~02
~G-
29L
77I
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EFLBG
EJD
FEDTE
FGOYB
G-2
HLZ
HVGLF
HZ~
R2-
SBC
SET
UHS
WUQ
~HD
ID FETCH-LOGICAL-c306t-d22b9aefcbc4c873cf63a7de01e0821d4066ae7a7329c5371367d9a81c0d3fff3
ISICitedReferencesCount 8
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001241868900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0950-7051
IngestDate Tue Nov 18 22:20:17 EST 2025
Sat Nov 29 01:33:40 EST 2025
Tue Jun 18 08:50:48 EDT 2024
IsPeerReviewed true
IsScholarly true
Keywords Fault diagnosis
Domain shift
Graph autoencoder
Self-supervised learning
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-d22b9aefcbc4c873cf63a7de01e0821d4066ae7a7329c5371367d9a81c0d3fff3
ORCID 0000-0003-4655-9400
0000-0002-6721-8640
0000-0002-9805-9849
ParticipantIDs crossref_citationtrail_10_1016_j_knosys_2024_111922
crossref_primary_10_1016_j_knosys_2024_111922
elsevier_sciencedirect_doi_10_1016_j_knosys_2024_111922
PublicationCentury 2000
PublicationDate 2024-07-19
PublicationDateYYYYMMDD 2024-07-19
PublicationDate_xml – month: 07
  year: 2024
  text: 2024-07-19
  day: 19
PublicationDecade 2020
PublicationTitle Knowledge-based systems
PublicationYear 2024
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Meng, Zhao, Cui, Zhang, Zhong (bib0002) 2022; 134
Liu, Chen, He, Shi, Zhou (bib0012) 2022; 128
Shi, Chen, Zi, Zhou (bib0013) 2021; 70
Liu (bib0024) 2021; 35
Xu, Hu, Leskovec, Jegelka (bib0038) 2018
Zhang (bib0020) 2022; 119
Ding, Zhuang, Ding, Jia (bib0035) 2022; 218
Han (bib0016) 2022; 45
Chang, Chen, Zheng, He, Xu (bib0019) 2023; 199
Feng, Liu, Chen, Lv, Wang, Zhang (bib0004) 2022
Hendrycks, Gimpel (bib0040) 2016
Chen, Kornblith, Norouzi, Hinton (bib0045) 2020
Chen, Chen, Xie, Xu, Feng, Liu (bib0010) 2022; 252
Chen (bib0022) 2022; 258
Chen, Kornblith, Swersky, Norouzi, Hinton (bib0025) 2020; 33
Lin, Shao, Zhou, Cai, Liu (bib0005) 2023
Chi, Dong, Wang, Yu, Leung (bib0006) 2022; 9
Feng, Chen, Liu, Lv, Wang (bib0018) 2022; 9
Liu (bib0043) 2021
Chen, Fan, Girshick, He (bib0026) 2020
Wang, Xu, Zhang, Liu, Jiang (bib0011) 2015; 348
Gulati (bib0015) 2020
Hou, Chen, Feng, Liu, He, Zhou (bib0036) 2022; 177
Liu, Chen, He, Shi, Zhou (bib0029) 2023; 189
Bao, Dong, Piao, Wei (bib0030) 2021
Wan, Chen, Zhou, Shi (bib0028) 2022
Zhou (bib0017) 2021
Chen, Chen, Liu, Feng, He, Xu (bib0014) 2022; 131
Jing, Tian (bib0023) 2020; 43
He, Xiang, Zhou, Chen (bib0007) 2023; 145
Zhou (bib0032) 2020; 1
Devlin, Chang, Lee, Toutanova (bib0037) 2018
Luo, Huang, Wang, Luo, Zhou (bib0003) 2022; 256
Hamilton, Ying, Leskovec (bib0034) 2017; 30
He, Fan, Wu, Xie, Girshick (bib0027) 2020
Xie (bib0031) 2022
Kipf, Welling (bib0044) 2016
He, Zhang, Ren, Sun (bib0041) 2016
Wang, Liu, Ge, Peng (bib0021) 2022; 239
Xie, Chen, Feng, He (bib0009) 2022; 64
Wu, Pan, Chen, Long, Zhang, Philip (bib0033) 2020; 32
Fan (bib0046) 2021
Feng, Chen, He, Pan, Zhou (bib0001) 2021
Vaswani (bib0039) 2017; 30
Shao, Jiang, Zhao, Wang (bib0008) 2017; 95
Dosovitskiy (bib0042) 2020
Kipf (10.1016/j.knosys.2024.111922_bib0044) 2016
He (10.1016/j.knosys.2024.111922_bib0007) 2023; 145
Chen (10.1016/j.knosys.2024.111922_bib0026) 2020
Bao (10.1016/j.knosys.2024.111922_bib0030) 2021
Liu (10.1016/j.knosys.2024.111922_bib0024) 2021; 35
Gulati (10.1016/j.knosys.2024.111922_bib0015) 2020
Jing (10.1016/j.knosys.2024.111922_bib0023) 2020; 43
Liu (10.1016/j.knosys.2024.111922_bib0029) 2023; 189
Luo (10.1016/j.knosys.2024.111922_bib0003) 2022; 256
Hamilton (10.1016/j.knosys.2024.111922_bib0034) 2017; 30
Wan (10.1016/j.knosys.2024.111922_bib0028) 2022
Wang (10.1016/j.knosys.2024.111922_bib0011) 2015; 348
Zhou (10.1016/j.knosys.2024.111922_bib0017) 2021
Liu (10.1016/j.knosys.2024.111922_bib0043) 2021
He (10.1016/j.knosys.2024.111922_bib0041) 2016
Hou (10.1016/j.knosys.2024.111922_bib0036) 2022; 177
Wang (10.1016/j.knosys.2024.111922_bib0021) 2022; 239
He (10.1016/j.knosys.2024.111922_bib0027) 2020
Liu (10.1016/j.knosys.2024.111922_bib0012) 2022; 128
Chen (10.1016/j.knosys.2024.111922_bib0014) 2022; 131
Shao (10.1016/j.knosys.2024.111922_bib0008) 2017; 95
Wu (10.1016/j.knosys.2024.111922_bib0033) 2020; 32
Shi (10.1016/j.knosys.2024.111922_bib0013) 2021; 70
Feng (10.1016/j.knosys.2024.111922_bib0001) 2021
Fan (10.1016/j.knosys.2024.111922_bib0046) 2021
Feng (10.1016/j.knosys.2024.111922_bib0018) 2022; 9
Chen (10.1016/j.knosys.2024.111922_bib0025) 2020; 33
Ding (10.1016/j.knosys.2024.111922_bib0035) 2022; 218
Han (10.1016/j.knosys.2024.111922_bib0016) 2022; 45
Zhang (10.1016/j.knosys.2024.111922_bib0020) 2022; 119
Xie (10.1016/j.knosys.2024.111922_bib0009) 2022; 64
Chen (10.1016/j.knosys.2024.111922_bib0022) 2022; 258
Lin (10.1016/j.knosys.2024.111922_bib0005) 2023
Chen (10.1016/j.knosys.2024.111922_bib0010) 2022; 252
Xie (10.1016/j.knosys.2024.111922_bib0031) 2022
Chang (10.1016/j.knosys.2024.111922_bib0019) 2023; 199
Meng (10.1016/j.knosys.2024.111922_bib0002) 2022; 134
Devlin (10.1016/j.knosys.2024.111922_bib0037) 2018
Feng (10.1016/j.knosys.2024.111922_bib0004) 2022
Chi (10.1016/j.knosys.2024.111922_bib0006) 2022; 9
Xu (10.1016/j.knosys.2024.111922_bib0038) 2018
Chen (10.1016/j.knosys.2024.111922_bib0045) 2020
Vaswani (10.1016/j.knosys.2024.111922_bib0039) 2017; 30
Zhou (10.1016/j.knosys.2024.111922_bib0032) 2020; 1
Hendrycks (10.1016/j.knosys.2024.111922_bib0040) 2016
Dosovitskiy (10.1016/j.knosys.2024.111922_bib0042) 2020
References_xml – start-page: 9653
  year: 2022
  end-page: 9663
  ident: bib0031
  article-title: Simmim: a simple framework for masked image modeling
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 9
  start-page: 21886
  year: 2022
  end-page: 21898
  ident: bib0018
  article-title: Full graph autoencoder for one-class group anomaly detection of IIoT system
  publication-title: IEEE Internet Things J.
– volume: 9
  start-page: 12886
  year: 2022
  end-page: 12900
  ident: bib0006
  article-title: Knowledge-based fault diagnosis in industrial internet of things: a survey
  publication-title: IEEE Int. Things J.
– volume: 131
  start-page: 501
  year: 2022
  end-page: 515
  ident: bib0014
  article-title: Multi-channel Calibrated Transformer with Shifted Windows for few-shot fault diagnosis under sharp speed variation
  publication-title: ISA Trans.
– volume: 218
  year: 2022
  ident: bib0035
  article-title: Self-supervised pretraining via contrast learning for intelligent incipient fault detection of bearings
  publication-title: Reliab. Eng. Syst. Saf.
– start-page: 6824
  year: 2021
  end-page: 6835
  ident: bib0046
  article-title: Multiscale vision transformers
  publication-title: Proceedings of the IEEE/CVF international conference on computer vision
– start-page: 1597
  year: 2020
  end-page: 1607
  ident: bib0045
  article-title: A simple framework for contrastive learning of visual representations
  publication-title: International conference on machine learning
– volume: 95
  start-page: 187
  year: 2017
  end-page: 204
  ident: bib0008
  article-title: A novel deep autoencoder feature learning method for rotating machinery fault diagnosis
  publication-title: Mech. Syst. Signal Process.
– volume: 1
  start-page: 57
  year: 2020
  end-page: 81
  ident: bib0032
  article-title: Graph neural networks: a review of methods and applications
  publication-title: AI Open
– volume: 252
  year: 2022
  ident: bib0010
  article-title: Multi-expert Attention Network with Unsupervised Aggregation for long-tailed fault diagnosis under speed variation
  publication-title: Knowl. Based Syst.
– volume: 189
  year: 2023
  ident: bib0029
  article-title: Few-shot learning under domain shift: attentional contrastive calibrated transformer of time series for fault diagnosis under sharp speed variation
  publication-title: Mech. Syst. Signal Process.
– volume: 70
  start-page: 1
  year: 2021
  end-page: 10
  ident: bib0013
  article-title: A novel multitask adversarial network via redundant lifting for multicomponent intelligent fault detection under sharp speed variation
  publication-title: IEEE Trans. Instrum. Meas.
– year: 2022
  ident: bib0028
  article-title: Self-supervised simple Siamese framework for fault diagnosis of rotating machinery with unlabeled samples
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– year: 2021
  ident: bib0030
  article-title: Beit: bert pre-training of image transformers
  publication-title: arXiv preprint
– year: 2021
  ident: bib0017
  article-title: Deepvit: towards deeper vision transformer
  publication-title: arXiv preprint
– volume: 128
  start-page: 531
  year: 2022
  end-page: 544
  ident: bib0012
  article-title: Subspace network with shared representation learning for intelligent fault diagnosis of machine under speed transient conditions with few samples
  publication-title: ISA Trans.
– year: 2016
  ident: bib0044
  article-title: Semi-supervised classification with graph convolutional networks
  publication-title: arXiv preprint
– volume: 32
  start-page: 4
  year: 2020
  end-page: 24
  ident: bib0033
  article-title: A comprehensive survey on graph neural networks
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– year: 2021
  ident: bib0001
  article-title: Globally localized multisource domain adaptation for cross-domain fault diagnosis with category shift
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 45
  start-page: 87
  year: 2022
  end-page: 110
  ident: bib0016
  article-title: A survey on vision transformer
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 9729
  year: 2020
  end-page: 9738
  ident: bib0027
  article-title: Momentum contrast for unsupervised visual representation learning
  publication-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
– year: 2020
  ident: bib0015
  article-title: Conformer: convolution-augmented transformer for speech recognition
  publication-title: arXiv preprint
– volume: 348
  start-page: 381
  year: 2015
  end-page: 396
  ident: bib0011
  article-title: Rotating speed isolation and its application to rolling element bearing fault diagnosis under large speed variation conditions
  publication-title: J. Sound Vib.
– volume: 30
  year: 2017
  ident: bib0034
  article-title: Inductive representation learning on large graphs
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2022
  ident: bib0004
  article-title: Unsupervised Multimodal Anomaly Detection With Missing Sources for Liquid Rocket Engine
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 119
  start-page: 152
  year: 2022
  end-page: 171
  ident: bib0020
  article-title: Intelligent fault diagnosis of machines with small & imbalanced data: a state-of-the-art review and possible extensions
  publication-title: ISA Trans.
– volume: 239
  year: 2022
  ident: bib0021
  article-title: Self-supervised signal representation learning for machinery fault diagnosis under limited annotation data
  publication-title: Knowl. Based Syst.
– year: 2018
  ident: bib0037
  article-title: Bert: pre-training of deep bidirectional transformers for language understanding
  publication-title: arXiv preprint
– year: 2020
  ident: bib0026
  article-title: Improved baselines with momentum contrastive learning
  publication-title: arXiv preprint
– volume: 64
  start-page: 561
  year: 2022
  end-page: 577
  ident: bib0009
  article-title: Semi-supervised multi-scale attention-aware graph convolution network for intelligent fault diagnosis of machine under extremely-limited labeled samples
  publication-title: J. Manuf. Syst.
– volume: 43
  start-page: 4037
  year: 2020
  end-page: 4058
  ident: bib0023
  article-title: Self-supervised visual feature learning with deep neural networks: a survey
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– year: 2016
  ident: bib0040
  article-title: Gaussian error linear units (Gelus)
  publication-title: arXiv preprint
– volume: 30
  year: 2017
  ident: bib0039
  article-title: Attention is all you need
  publication-title: Adv Neural Inf Process Syst
– start-page: 10012
  year: 2021
  end-page: 10022
  ident: bib0043
  article-title: Swin transformer: hierarchical vision transformer using shifted windows
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– volume: 145
  year: 2023
  ident: bib0007
  article-title: In-situ fault detection for the spindle motor of CNC machines via multi-stage residual fusion convolution neural networks
  publication-title: Comput. Ind.
– volume: 35
  start-page: 857
  year: 2021
  end-page: 876
  ident: bib0024
  article-title: Self-supervised learning: generative or contrastive
  publication-title: IEEE Trans. Knowl. Data Eng.
– volume: 256
  year: 2022
  ident: bib0003
  article-title: Transfer learning based on improved stacked autoencoder for bearing fault diagnosis
  publication-title: Knowl. Based Syst.
– year: 2020
  ident: bib0042
  article-title: An image is worth 16×16 words: transformers for image recognition at scale
  publication-title: arXiv preprint
– volume: 199
  year: 2023
  ident: bib0019
  article-title: Triplet adversarial Learning-driven graph architecture search network augmented with Probsparse-attention mechanism for fault diagnosis under Few-shot & Domain-shift
  publication-title: Mech. Syst. Signal Process.
– year: 2018
  ident: bib0038
  article-title: How powerful are graph neural networks?
  publication-title: arXiv preprint
– volume: 134
  year: 2022
  ident: bib0002
  article-title: Empirical mode reconstruction: preserving intrinsic components in data augmentation for intelligent fault diagnosis of civil aviation hydraulic pumps
  publication-title: Comput. Ind.
– volume: 33
  start-page: 22243
  year: 2020
  end-page: 22255
  ident: bib0025
  article-title: Big self-supervised models are strong semi-supervised learners
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 177
  year: 2022
  ident: bib0036
  article-title: Contrastive-weighted self-supervised model for long-tailed data classification with vision transformer augmented
  publication-title: Mech. Syst. Signal Process.
– year: 2023
  ident: bib0005
  article-title: Generalized MAML for few-shot cross-domain fault diagnosis of bearing driven by heterogeneous signals
  publication-title: Expert Syst. Appl.
– volume: 258
  year: 2022
  ident: bib0022
  article-title: Imbalance fault diagnosis under long-tailed distribution: challenges, solutions and prospects
  publication-title: Knowl. Based Syst.
– start-page: 770
  year: 2016
  end-page: 778
  ident: bib0041
  article-title: Deep residual learning for image recognition
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– volume: 9
  start-page: 12886
  issue: 15
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0006
  article-title: Knowledge-based fault diagnosis in industrial internet of things: a survey
  publication-title: IEEE Int. Things J.
  doi: 10.1109/JIOT.2022.3163606
– volume: 95
  start-page: 187
  year: 2017
  ident: 10.1016/j.knosys.2024.111922_bib0008
  article-title: A novel deep autoencoder feature learning method for rotating machinery fault diagnosis
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2017.03.034
– start-page: 770
  year: 2016
  ident: 10.1016/j.knosys.2024.111922_bib0041
  article-title: Deep residual learning for image recognition
– volume: 30
  year: 2017
  ident: 10.1016/j.knosys.2024.111922_bib0034
  article-title: Inductive representation learning on large graphs
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 199
  year: 2023
  ident: 10.1016/j.knosys.2024.111922_bib0019
  article-title: Triplet adversarial Learning-driven graph architecture search network augmented with Probsparse-attention mechanism for fault diagnosis under Few-shot & Domain-shift
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2023.110462
– volume: 252
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0010
  article-title: Multi-expert Attention Network with Unsupervised Aggregation for long-tailed fault diagnosis under speed variation
  publication-title: Knowl. Based Syst.
  doi: 10.1016/j.knosys.2022.109393
– volume: 134
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0002
  article-title: Empirical mode reconstruction: preserving intrinsic components in data augmentation for intelligent fault diagnosis of civil aviation hydraulic pumps
  publication-title: Comput. Ind.
  doi: 10.1016/j.compind.2021.103557
– volume: 348
  start-page: 381
  year: 2015
  ident: 10.1016/j.knosys.2024.111922_bib0011
  article-title: Rotating speed isolation and its application to rolling element bearing fault diagnosis under large speed variation conditions
  publication-title: J. Sound Vib.
  doi: 10.1016/j.jsv.2015.03.018
– year: 2021
  ident: 10.1016/j.knosys.2024.111922_bib0001
  article-title: Globally localized multisource domain adaptation for cross-domain fault diagnosis with category shift
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 70
  start-page: 1
  year: 2021
  ident: 10.1016/j.knosys.2024.111922_bib0013
  article-title: A novel multitask adversarial network via redundant lifting for multicomponent intelligent fault detection under sharp speed variation
  publication-title: IEEE Trans. Instrum. Meas.
  doi: 10.1109/TIM.2021.3127634
– volume: 30
  year: 2017
  ident: 10.1016/j.knosys.2024.111922_bib0039
  article-title: Attention is all you need
  publication-title: Adv Neural Inf Process Syst
– year: 2023
  ident: 10.1016/j.knosys.2024.111922_bib0005
  article-title: Generalized MAML for few-shot cross-domain fault diagnosis of bearing driven by heterogeneous signals
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2023.120696
– start-page: 9729
  year: 2020
  ident: 10.1016/j.knosys.2024.111922_bib0027
  article-title: Momentum contrast for unsupervised visual representation learning
– volume: 1
  start-page: 57
  year: 2020
  ident: 10.1016/j.knosys.2024.111922_bib0032
  article-title: Graph neural networks: a review of methods and applications
  publication-title: AI Open
  doi: 10.1016/j.aiopen.2021.01.001
– volume: 128
  start-page: 531
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0012
  article-title: Subspace network with shared representation learning for intelligent fault diagnosis of machine under speed transient conditions with few samples
  publication-title: ISA Trans.
  doi: 10.1016/j.isatra.2021.10.025
– volume: 35
  start-page: 857
  issue: 1
  year: 2021
  ident: 10.1016/j.knosys.2024.111922_bib0024
  article-title: Self-supervised learning: generative or contrastive
  publication-title: IEEE Trans. Knowl. Data Eng.
– volume: 239
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0021
  article-title: Self-supervised signal representation learning for machinery fault diagnosis under limited annotation data
  publication-title: Knowl. Based Syst.
  doi: 10.1016/j.knosys.2021.107978
– year: 2020
  ident: 10.1016/j.knosys.2024.111922_bib0042
  article-title: An image is worth 16×16 words: transformers for image recognition at scale
  publication-title: arXiv preprint
– volume: 256
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0003
  article-title: Transfer learning based on improved stacked autoencoder for bearing fault diagnosis
  publication-title: Knowl. Based Syst.
  doi: 10.1016/j.knosys.2022.109846
– volume: 33
  start-page: 22243
  year: 2020
  ident: 10.1016/j.knosys.2024.111922_bib0025
  article-title: Big self-supervised models are strong semi-supervised learners
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 9
  start-page: 21886
  issue: 21
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0018
  article-title: Full graph autoencoder for one-class group anomaly detection of IIoT system
  publication-title: IEEE Internet Things J.
  doi: 10.1109/JIOT.2022.3181737
– volume: 177
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0036
  article-title: Contrastive-weighted self-supervised model for long-tailed data classification with vision transformer augmented
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2022.109174
– year: 2018
  ident: 10.1016/j.knosys.2024.111922_bib0037
  article-title: Bert: pre-training of deep bidirectional transformers for language understanding
  publication-title: arXiv preprint
– start-page: 9653
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0031
  article-title: Simmim: a simple framework for masked image modeling
– volume: 145
  year: 2023
  ident: 10.1016/j.knosys.2024.111922_bib0007
  article-title: In-situ fault detection for the spindle motor of CNC machines via multi-stage residual fusion convolution neural networks
  publication-title: Comput. Ind.
  doi: 10.1016/j.compind.2022.103810
– volume: 189
  year: 2023
  ident: 10.1016/j.knosys.2024.111922_bib0029
  article-title: Few-shot learning under domain shift: attentional contrastive calibrated transformer of time series for fault diagnosis under sharp speed variation
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2022.110071
– year: 2021
  ident: 10.1016/j.knosys.2024.111922_bib0030
  article-title: Beit: bert pre-training of image transformers
  publication-title: arXiv preprint
– year: 2020
  ident: 10.1016/j.knosys.2024.111922_bib0026
  article-title: Improved baselines with momentum contrastive learning
  publication-title: arXiv preprint
– year: 2016
  ident: 10.1016/j.knosys.2024.111922_bib0044
  article-title: Semi-supervised classification with graph convolutional networks
  publication-title: arXiv preprint
– volume: 218
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0035
  article-title: Self-supervised pretraining via contrast learning for intelligent incipient fault detection of bearings
  publication-title: Reliab. Eng. Syst. Saf.
  doi: 10.1016/j.ress.2021.108126
– year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0004
  article-title: Unsupervised Multimodal Anomaly Detection With Missing Sources for Liquid Rocket Engine
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– year: 2018
  ident: 10.1016/j.knosys.2024.111922_bib0038
  article-title: How powerful are graph neural networks?
  publication-title: arXiv preprint
– start-page: 6824
  year: 2021
  ident: 10.1016/j.knosys.2024.111922_bib0046
  article-title: Multiscale vision transformers
– volume: 119
  start-page: 152
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0020
  article-title: Intelligent fault diagnosis of machines with small & imbalanced data: a state-of-the-art review and possible extensions
  publication-title: ISA Trans.
  doi: 10.1016/j.isatra.2021.02.042
– year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0028
  article-title: Self-supervised simple Siamese framework for fault diagnosis of rotating machinery with unlabeled samples
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– start-page: 1597
  year: 2020
  ident: 10.1016/j.knosys.2024.111922_bib0045
  article-title: A simple framework for contrastive learning of visual representations
– volume: 64
  start-page: 561
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0009
  article-title: Semi-supervised multi-scale attention-aware graph convolution network for intelligent fault diagnosis of machine under extremely-limited labeled samples
  publication-title: J. Manuf. Syst.
  doi: 10.1016/j.jmsy.2022.08.007
– volume: 131
  start-page: 501
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0014
  article-title: Multi-channel Calibrated Transformer with Shifted Windows for few-shot fault diagnosis under sharp speed variation
  publication-title: ISA Trans.
  doi: 10.1016/j.isatra.2022.04.043
– year: 2021
  ident: 10.1016/j.knosys.2024.111922_bib0017
  article-title: Deepvit: towards deeper vision transformer
  publication-title: arXiv preprint
– year: 2016
  ident: 10.1016/j.knosys.2024.111922_bib0040
  article-title: Gaussian error linear units (Gelus)
  publication-title: arXiv preprint
– start-page: 10012
  year: 2021
  ident: 10.1016/j.knosys.2024.111922_bib0043
  article-title: Swin transformer: hierarchical vision transformer using shifted windows
– volume: 43
  start-page: 4037
  issue: 11
  year: 2020
  ident: 10.1016/j.knosys.2024.111922_bib0023
  article-title: Self-supervised visual feature learning with deep neural networks: a survey
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2020.2992393
– year: 2020
  ident: 10.1016/j.knosys.2024.111922_bib0015
  article-title: Conformer: convolution-augmented transformer for speech recognition
  publication-title: arXiv preprint
– volume: 32
  start-page: 4
  issue: 1
  year: 2020
  ident: 10.1016/j.knosys.2024.111922_bib0033
  article-title: A comprehensive survey on graph neural networks
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2020.2978386
– volume: 258
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0022
  article-title: Imbalance fault diagnosis under long-tailed distribution: challenges, solutions and prospects
  publication-title: Knowl. Based Syst.
  doi: 10.1016/j.knosys.2022.110008
– volume: 45
  start-page: 87
  issue: 1
  year: 2022
  ident: 10.1016/j.knosys.2024.111922_bib0016
  article-title: A survey on vision transformer
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2022.3152247
SSID ssj0002218
Score 2.4436026
Snippet Thanks to the sufficient monitoring data provided by Industrial Internet of Things (IIoT), intelligent fault diagnosis technology has demonstrated remarkable...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 111922
SubjectTerms Domain shift
Fault diagnosis
Graph autoencoder
Self-supervised learning
Title Enhancing equipment safeguarding in IIoT: A self-supervised fault diagnosis paradigm based on asymmetric graph autoencoder
URI https://dx.doi.org/10.1016/j.knosys.2024.111922
Volume 296
WOSCitedRecordID wos001241868900001&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: 1872-7409
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002218
  issn: 0950-7051
  databaseCode: AIEXJ
  dateStart: 19950201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Pb9MwFLZKx4ELvxFjgHzgFnlKnB92dqtQEQU0cShS4RI5ttNma5OyJNPG_8H_ix07adjQYAcuUZXGTpT39fn59XvfA-ANw576KgqQWnwFCijmKOWeRDgOKY8Z4QExzSbI8TFdLOLPo9HPrhbmfE2Kgl5cxNv_amp1Thlbl87ewtz9pOqE-qyMro7K7Or4T4afFiutoVEsHfm9yVs6kFOxTC5bMJgKltmsnJua9EquM1Q1W-0yKhV8ZqxZ1zojqwl4eeVoaXCRLzeOXu6E_muBVZebje7DxZ1W7dphTV1qOUxhib421P3YZeuQGVoNtNFbPoFxeN9WTamT1j0zKG_ajOxqV6P2KbfEgHJARjA-6mvDilVpR9vkBQ50VtS6yC4L6SLiWs1Z65BxPHSpyhnHpnT5mrc3iYeTw1P1Ri619joODneX_y6ufWXR66mIHcvtJDGzJHqWxMxyB-xhEsZ0DPYms-niQ7_EY9wmjvun72oyW-Lg9af5c8wziGPmD8F9uwGBEwOcR2Aki8fgQdfcA1pf_wT86HEEexzBIY5gXkCNoyM4gVdQBFsUwR5FsEMRbKEAywLuUARbFMEBip6CL--m87fvkW3UgbjacdZIYJzGTGY85QGnxOdZ5DMipOtJFWF6QgWNEZOEER_HPPSJlgkUMaMed4WfZZn_DIyLspDPAaSRkFRwP-NqXxJFYar2Lz6VkQhFKgLq7gO_e5UJtyr2upnKOrnJkPsA9aO2RsXlL9eTzkqJjURNhJko6N048sUt73QA7u1-Fy_BuD5r5Ctwl5_XeXX22uLuF-oasbw
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=Enhancing+equipment+safeguarding+in+IIoT%3A+A+self-supervised+fault+diagnosis+paradigm+based+on+asymmetric+graph+autoencoder&rft.jtitle=Knowledge-based+systems&rft.au=Chen%2C+Zhuohang&rft.au=Liu%2C+Shen&rft.au=Li%2C+Chao&rft.au=Chang%2C+Yuanhong&rft.date=2024-07-19&rft.issn=0950-7051&rft.volume=296&rft.spage=111922&rft_id=info:doi/10.1016%2Fj.knosys.2024.111922&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_knosys_2024_111922
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0950-7051&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0950-7051&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0950-7051&client=summon