SCG-GFFE: A Self-Constructed graph fault feature extractor based on graph Auto-encoder algorithm for unlabeled single-variable vibration signals of harmonic reducer

As a pivotal component in robotic systems, harmonic reducer fault diagnosis plays a crucial role in safe and stable operation; however, the lack of labelled fault samples hampers its effectiveness. This study introduces a self-constructed graph graph-autoencoder fault feature extractor (SCG-GFFE), a...

Full description

Saved in:
Bibliographic Details
Published inAdvanced engineering informatics Vol. 62; p. 102579
Main Authors Sun, Shilong, Ding, Hao, Zhao, Zida, Xu, Wenfu, Wang, Dong
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.10.2024
Subjects
Online AccessGet full text
ISSN1474-0346
DOI10.1016/j.aei.2024.102579

Cover

Abstract As a pivotal component in robotic systems, harmonic reducer fault diagnosis plays a crucial role in safe and stable operation; however, the lack of labelled fault samples hampers its effectiveness. This study introduces a self-constructed graph graph-autoencoder fault feature extractor (SCG-GFFE), a novel method that uses the Graph Auto-encoder (GAE) algorithm. SCG-GFFE leverages Graph Neural Networks (GNNs) for the unsupervised extraction of fault features, enhancing fault diagnosis in scenarios with limited labelled data. This approach overcomes the challenges of graph construction for fault diagnosis, particularly for single-sensor vibration signals. First, we developed the SCG-GFFE method for efficient fault feature extraction, which does not require complex domain expertise and is capable of generating graph structures. Second, we designed a suitably structured subgraph for dealing with single, unlabelled, non-multisource vibration signals. Third, a real-world harmonic reducer’s vibrational signal is utilised to build an experimental study and demonstrate the effectiveness of the SCG-GFFE method. The results of SCG-GFFE demonstrate remarkable accuracy in fault diagnosis, consistently exceeding 98% across various classifiers, and indicate that the proposed method can solve the problem of limited labelled data in harmonic reducer diagnosis.
AbstractList As a pivotal component in robotic systems, harmonic reducer fault diagnosis plays a crucial role in safe and stable operation; however, the lack of labelled fault samples hampers its effectiveness. This study introduces a self-constructed graph graph-autoencoder fault feature extractor (SCG-GFFE), a novel method that uses the Graph Auto-encoder (GAE) algorithm. SCG-GFFE leverages Graph Neural Networks (GNNs) for the unsupervised extraction of fault features, enhancing fault diagnosis in scenarios with limited labelled data. This approach overcomes the challenges of graph construction for fault diagnosis, particularly for single-sensor vibration signals. First, we developed the SCG-GFFE method for efficient fault feature extraction, which does not require complex domain expertise and is capable of generating graph structures. Second, we designed a suitably structured subgraph for dealing with single, unlabelled, non-multisource vibration signals. Third, a real-world harmonic reducer’s vibrational signal is utilised to build an experimental study and demonstrate the effectiveness of the SCG-GFFE method. The results of SCG-GFFE demonstrate remarkable accuracy in fault diagnosis, consistently exceeding 98% across various classifiers, and indicate that the proposed method can solve the problem of limited labelled data in harmonic reducer diagnosis.
ArticleNumber 102579
Author Xu, Wenfu
Ding, Hao
Zhao, Zida
Wang, Dong
Sun, Shilong
Author_xml – sequence: 1
  givenname: Shilong
  orcidid: 0000-0003-0460-4592
  surname: Sun
  fullname: Sun, Shilong
  email: sslmy526@gmail.com, sunshilong@hit.edu.cn, shilosun-c@my.cityu.edu.hk
  organization: School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, 518055, China
– sequence: 2
  givenname: Hao
  surname: Ding
  fullname: Ding, Hao
  organization: School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, 518055, China
– sequence: 3
  givenname: Zida
  surname: Zhao
  fullname: Zhao, Zida
  organization: School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, 518055, China
– sequence: 4
  givenname: Wenfu
  surname: Xu
  fullname: Xu, Wenfu
  organization: School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, 518055, China
– sequence: 5
  givenname: Dong
  surname: Wang
  fullname: Wang, Dong
  organization: The State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240, China
BookMark eNp9kE1uGzEMRrVIgeanB-hOFxh3pBnPyO3KMGKnQIAukq4FSuLYMmQpoDRGe58etEqdVRdZEQS_R5Dvhl3FFJGxz6JdiFYMX44LQL-QrexrL5fj6opdi37sm7brh4_sJudjW3NqNV6zP0-bXbPbbu-_8jV_wjA1mxRzodkWdHxP8HLgE8yh8AmhzIQcfxUCWxJxA7lmUnyLreeSGow2OSQOYZ_Il8OJTzU5xwAGQ01nH_cBmzOQBxOQn70hKL4uyX4fIWSeJn4AOqXoLSd0s0W6Yx-mOsJPb_WW_dzeP28emscfu--b9WNj5WosDRopjDKjWkpQzowgleqxXRozKNspAVYobAfV9W4FnZSoBuEcSGOWdaC67paNl72WUs6Ek7a-_LuuvuyDFq1-FayPugrWr4L1RXAlxX_kC_kT0O93mW8XButLZ4-ks_XVHzpPaIt2yb9D_wUgUpqd
CitedBy_id crossref_primary_10_1016_j_aei_2024_102958
crossref_primary_10_1016_j_measurement_2024_116275
crossref_primary_10_1109_TIM_2024_3472781
crossref_primary_10_1109_JSEN_2024_3492041
crossref_primary_10_1016_j_aei_2024_102602
Cites_doi 10.1016/j.isatra.2021.11.024
10.1016/j.aei.2022.101682
10.1109/TIE.2020.3040669
10.1109/JSEN.2021.3137992
10.1109/TIM.2022.3218574
10.1109/TIE.2022.3176280
10.1016/j.jmsy.2022.12.001
10.1109/LRA.2019.2896465
10.1016/j.measurement.2024.114171
10.1016/j.aei.2022.101815
10.1007/s11431-022-2129-9
10.1109/TPAMI.2022.3202158
10.1016/j.knosys.2023.110891
10.1016/j.isatra.2023.04.033
10.1016/j.ymssp.2023.110534
10.1016/j.jmsy.2021.10.014
10.1109/TIE.2021.3111567
10.1016/j.knosys.2022.109340
10.1109/TIE.2020.2978690
10.1016/j.ymssp.2020.106683
10.1109/TIM.2021.3126366
10.1016/j.aei.2023.102304
10.1016/j.knosys.2021.107374
10.1109/TII.2022.3230669
10.1016/j.knosys.2022.109069
10.1016/j.ymssp.2020.107327
10.1016/j.isatra.2023.07.036
10.1016/j.engappai.2022.104932
10.1016/j.knosys.2022.110172
10.1109/TCYB.2021.3059002
10.1109/TNNLS.2021.3132376
ContentType Journal Article
Copyright 2024 Elsevier Ltd
Copyright_xml – notice: 2024 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.aei.2024.102579
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
ExternalDocumentID 10_1016_j_aei_2024_102579
S1474034624002271
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1~.
1~5
23M
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
AAAKF
AAAKG
AACTN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARIN
AAXKI
AAXUO
AAYFN
ABBOA
ABFNM
ABMAC
ABUCO
ABWVN
ABXDB
ACDAQ
ACGFS
ACNNM
ACRLP
ACRPL
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFJKZ
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
APLSM
AXJTR
BJAXD
BKOJK
BLXMC
CS3
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HAMUX
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
PC.
Q38
RIG
RNS
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSB
SSD
SST
SSV
SSZ
T5K
UHS
XPP
ZMT
~G-
AATTM
AAYWO
AAYXX
ABJNI
ACLOT
ACVFH
ADCNI
AEIPS
AEUPX
AFPUW
AIGII
AIIUN
AKBMS
AKYEP
ANKPU
APXCP
CITATION
EFKBS
EFLBG
~HD
ID FETCH-LOGICAL-c297t-eb21b8b7852a8db7a2884e05bb68c381ac18e06834d9a322e861dda2bb518e833
IEDL.DBID .~1
ISSN 1474-0346
IngestDate Wed Oct 01 02:44:35 EDT 2025
Thu Apr 24 23:04:01 EDT 2025
Sat Dec 14 16:15:11 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Graph autoencoder
Self-constructed graph
Unsupervised fault feature extractor
Single-variable vibration signals
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c297t-eb21b8b7852a8db7a2884e05bb68c381ac18e06834d9a322e861dda2bb518e833
ORCID 0000-0003-0460-4592
ParticipantIDs crossref_citationtrail_10_1016_j_aei_2024_102579
crossref_primary_10_1016_j_aei_2024_102579
elsevier_sciencedirect_doi_10_1016_j_aei_2024_102579
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate October 2024
2024-10-00
PublicationDateYYYYMMDD 2024-10-01
PublicationDate_xml – month: 10
  year: 2024
  text: October 2024
PublicationDecade 2020
PublicationTitle Advanced engineering informatics
PublicationYear 2024
Publisher Elsevier Ltd
Publisher_xml – sequence: 0
  name: Elsevier Ltd
References Sun, Huang, Peng, Shen, Wang (b0175) 2023; 72
Yu, Zhang, Deng (b0100) 2023; 200
Chen, Liu, Hu, Ding (b0115) 2023; 34
Graph neural network-based fault diagnosis: a review
Zhang, Zhang, Lu, Li (b0150) 2023; 45
Wang, Yang, Zhang (b0040) 2024; 226
2021.
Yang, Xiang, Long, Ma, Ding, Jia (b0070) 2023; 72
Yang, Zhong, Yang, Tao, Li, Du (b0075) 2021; 70
An, Jiang, Cao, Yang, Li (b0125) 2021; 230
Zhi, Liu, Liu, Hu (b0050) 2022; 22
He, Chen, Zhou, Huang (b0060) 2023.; 66
Li, Zhao, Sun, Yan, Chen (b0190) 2021; 68
Pang, Liu, Sun, Xu, Hao (b0140) 2024; 59
Tang (b0105) 2021; 70
Sun, Huang, Peng, Wang (b0180) 2023; 72
Chen, Mauricio, Li, Gryllias (b0010) 2020; 140
Wang, Cao, Xu, Liu (b0160) 2022; 252
Chen, Xu, Peng, Yang (b0195) 2022; 52
Zhou, Qin, Chen, Liu, Qian (b0205) 2022; 53
Zhi, Liu, Liu, Hu (b0215) 2021; 22
Yang, Tao, Du, Zhong (b0110) 2023; 70
Niepert, Ahmed, Kutzkov (b0200) 2016
Zhang, Chen, He, Li, Feng, Zhou (b0095) 2022; 62
Gao, Xu, Zhang, Pei (b0025) 2022; 128
T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,”
Jin (b0090) 2023
Li, Huang, Chen, Xia, Chen, Li (b0130) 2022; 71
Peng, Shen, Sun, Wang (b0210) 2022; 69
Z. Chen
Liu, Zhi, Yang, Shirmohammadi, Liu (b0055) 2023; 72
Shi (b0145) 2023; 260
Lee, Jeong, Koo, Ban, Kim (b0015) 2021; 68
Yang, Liu, Zhou, Ge, Jiang (b0185) 2022; 250
Zhou, Dong, Tang (b0135) 2023; 19
Wang, Wu, Li, Shao, Han, Xie (b0155) 2023; 278
Kaneko (b0005) 2019; 4
Yang, Wang, Wei (b0045) 2022; 54
T. N. Kipf and M. Welling, “Variational graph auto-encoders,”
Wu, Zhang, Cheng, Peng (b0020) 2021; 149
2016.
Wan, Chen, Xie (b0165) 2023; 139
Zhou, Zhou, He, Huang, Zhu, Chen (b0065) 2022; 65
Wu, Jiang, Wang, Zhu (b0170) 2023
Sun, Peng, Zhou, Zhang, Wang (b0030) 2023
Yao, Qian, Qin, Guo, Wu (b0035) 2022; 113
Peng (10.1016/j.aei.2024.102579_b0210) 2022; 69
Yang (10.1016/j.aei.2024.102579_b0070) 2023; 72
An (10.1016/j.aei.2024.102579_b0125) 2021; 230
Niepert (10.1016/j.aei.2024.102579_b0200) 2016
Chen (10.1016/j.aei.2024.102579_b0010) 2020; 140
Zhi (10.1016/j.aei.2024.102579_b0050) 2022; 22
Tang (10.1016/j.aei.2024.102579_b0105) 2021; 70
Sun (10.1016/j.aei.2024.102579_b0175) 2023; 72
Shi (10.1016/j.aei.2024.102579_b0145) 2023; 260
Liu (10.1016/j.aei.2024.102579_b0055) 2023; 72
Chen (10.1016/j.aei.2024.102579_b0115) 2023; 34
Gao (10.1016/j.aei.2024.102579_b0025) 2022; 128
Wang (10.1016/j.aei.2024.102579_b0040) 2024; 226
Chen (10.1016/j.aei.2024.102579_b0195) 2022; 52
Wu (10.1016/j.aei.2024.102579_b0020) 2021; 149
Wan (10.1016/j.aei.2024.102579_b0165) 2023; 139
Yang (10.1016/j.aei.2024.102579_b0045) 2022; 54
Wu (10.1016/j.aei.2024.102579_b0170) 2023
Wang (10.1016/j.aei.2024.102579_b0160) 2022; 252
10.1016/j.aei.2024.102579_b0080
Zhou (10.1016/j.aei.2024.102579_b0135) 2023; 19
Li (10.1016/j.aei.2024.102579_b0190) 2021; 68
Yao (10.1016/j.aei.2024.102579_b0035) 2022; 113
Sun (10.1016/j.aei.2024.102579_b0180) 2023; 72
Li (10.1016/j.aei.2024.102579_b0130) 2022; 71
Wang (10.1016/j.aei.2024.102579_b0155) 2023; 278
Lee (10.1016/j.aei.2024.102579_b0015) 2021; 68
Zhang (10.1016/j.aei.2024.102579_b0150) 2023; 45
Yang (10.1016/j.aei.2024.102579_b0185) 2022; 250
Zhi (10.1016/j.aei.2024.102579_b0215) 2021; 22
Kaneko (10.1016/j.aei.2024.102579_b0005) 2019; 4
10.1016/j.aei.2024.102579_b0085
Sun (10.1016/j.aei.2024.102579_b0030) 2023
Yu (10.1016/j.aei.2024.102579_b0100) 2023; 200
Zhang (10.1016/j.aei.2024.102579_b0095) 2022; 62
10.1016/j.aei.2024.102579_b0120
Zhou (10.1016/j.aei.2024.102579_b0065) 2022; 65
Pang (10.1016/j.aei.2024.102579_b0140) 2024; 59
He (10.1016/j.aei.2024.102579_b0060) 2023; 66
Jin (10.1016/j.aei.2024.102579_b0090) 2023
Yang (10.1016/j.aei.2024.102579_b0110) 2023; 70
Zhou (10.1016/j.aei.2024.102579_b0205) 2022; 53
Yang (10.1016/j.aei.2024.102579_b0075) 2021; 70
References_xml – volume: 260
  year: 2023
  ident: b0145
  article-title: Deep hypergraph autoencoder embedding: An efficient intelligent approach for rotating machinery fault diagnosis
  publication-title: Knowl.-Based Syst.
– volume: 250
  year: 2022
  ident: b0185
  article-title: Transferable graph features-driven cross-domain rotating machinery fault diagnosis
  publication-title: Knowl.-Based Syst.
– volume: 4
  start-page: 1431
  year: 2019
  end-page: 1438
  ident: b0005
  article-title: Humanoid robot HRP-5P: An electrically actuated humanoid robot with high-power and wide-range joints
  publication-title: IEEE Rob. Autom. Lett.
– volume: 70
  start-page: 4186
  year: 2023
  end-page: 4195
  ident: b0110
  article-title: Compound fault diagnosis of harmonic drives using deep capsule graph convolutional network
  publication-title: IEEE Trans. Ind. Electron.
– volume: 70
  start-page: 1
  year: 2021
  end-page: 10
  ident: b0105
  article-title: Rotating machine systems fault diagnosis using semisupervised conditional random field-based graph attention network
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 113
  year: 2022
  ident: b0035
  article-title: Adversarial domain adaptation network with pseudo-siamese feature extractors for cross-bearing fault transfer diagnosis
  publication-title: Eng. Appl. Artif. Intel.
– volume: 19
  start-page: 7733
  year: 2023
  end-page: 7741
  ident: b0135
  article-title: Time-varying online transfer learning for intelligent bearing fault diagnosis with incomplete unlabeled target data
  publication-title: IEEE Trans. Ind. Inf.
– volume: 65
  start-page: 2116
  year: 2022
  end-page: 2126
  ident: b0065
  article-title: Harmonic reducer in-situ fault diagnosis for industrial robots based on deep learning
  publication-title: Sci. China Technol. Sci.
– volume: 71
  start-page: 1
  year: 2022
  end-page: 9
  ident: b0130
  article-title: Deep self-supervised domain adaptation network for fault diagnosis of rotating machine with unlabeled data
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 139
  start-page: 574
  year: 2023
  end-page: 585
  ident: b0165
  article-title: MIM-Graph: A multi-sensor network approach for fault diagnosis of HSR Bogie bearings at the IoT edge via mutual information maximization
  publication-title: ISA Trans.
– volume: 59
  year: 2024
  ident: b0140
  article-title: Time-frequency supervised contrastive learning via pseudo-labeling: An unsupervised domain adaptation network for rolling bearing fault diagnosis under time-varying speeds
  publication-title: Adv. Eng. Inf.
– volume: 128
  start-page: 485
  year: 2022
  end-page: 502
  ident: b0025
  article-title: Rolling bearing fault diagnosis based on SSA optimized self-adaptive DBN
  publication-title: ISA Trans.
– volume: 72
  start-page: 1
  year: 2023
  end-page: 9
  ident: b0175
  article-title: A data privacy protection diagnosis framework for multiple machines vibration signals based on a swarm learning algorithm
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 54
  year: 2022
  ident: b0045
  article-title: A novel Brownian correlation metric prototypical network for rotating machinery fault diagnosis with few and zero shot learners
  publication-title: Adv. Eng. Inf.
– volume: 72
  start-page: 1
  year: 2023
  end-page: 8
  ident: b0070
  article-title: Fault diagnosis of harmonic drives based on an SDP-ConvNeXt joint methodology
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 34
  start-page: 6015
  year: 2023
  end-page: 6028
  ident: b0115
  article-title: Interaction-aware graph neural networks for fault diagnosis of complex industrial processes
  publication-title: IEEE Trans. Neural Networks Learn. Syst.
– volume: 140
  year: 2020
  ident: b0010
  article-title: A deep learning method for bearing fault diagnosis based on cyclic spectral coherence and convolutional neural networks
  publication-title: Mech. Syst. Sig. Process.
– start-page: 1
  year: 2023
  end-page: 20
  ident: b0090
  article-title: Spatio-temporal graph neural networks for predictive learning in urban computing: A survey
  publication-title: IEEE Trans. Knowl. Data Eng.
– volume: 45
  start-page: 5329
  year: 2023
  end-page: 5336
  ident: b0150
  article-title: Unsupervised graph embedding via adaptive graph learning
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– reference: T. N. Kipf and M. Welling, “Variational graph auto-encoders,”
– volume: 278
  year: 2023
  ident: b0155
  article-title: “Attention-aware temporal–spatial graph neural network with multi-sensor information fusion for fault diagnosis,”
  publication-title: Knowl.-Based Syst.
– reference: , “Graph neural network-based fault diagnosis: a review,”
– reference: 2021.
– volume: 72
  start-page: 1
  year: 2023
  end-page: 9
  ident: b0180
  article-title: An improved data privacy diagnostic framework for multiple machinery components data based on swarm learning algorithm
  publication-title: IEEE Trans. Instrum. Meas.
– reference: 2016.
– volume: 53
  year: 2022
  ident: b0205
  article-title: Remaining useful life prediction of bearings by a new reinforced memory GRU network
  publication-title: Adv. Eng. Inf.
– volume: 66
  start-page: 233
  year: 2023.
  end-page: 247
  ident: b0060
  article-title: In-situ fault diagnosis for the harmonic reducer of industrial robots via multi-scale mixed convolutional neural networks
  publication-title: J. Manuf. Syst.
– volume: 62
  start-page: 1
  year: 2022
  end-page: 16
  ident: b0095
  article-title: Triplet metric driven multi-head GNN augmented with decoupling adversarial learning for intelligent fault diagnosis of machines under varying working condition
  publication-title: J. Manuf. Syst.
– volume: 149
  year: 2021
  ident: b0020
  article-title: A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery
  publication-title: Mech. Syst. Sig. Process.
– volume: 22
  start-page: 2572
  year: 2022
  end-page: 2581
  ident: b0050
  article-title: Fault detection of the harmonic reducer based on CNN-LSTM with a novel denoising algorithm
  publication-title: IEEE Sens. J.
– volume: 68
  start-page: 12739
  year: 2021
  end-page: 12749
  ident: b0190
  article-title: Multireceptive field graph convolutional networks for machine fault diagnosis
  publication-title: IEEE Trans. Ind. Electron.
– volume: 68
  start-page: 3445
  year: 2021
  end-page: 3453
  ident: b0015
  article-title: Attention recurrent neural network-based severity estimation method for interturn short-circuit fault in permanent magnet synchronous machines
  publication-title: IEEE Trans. Ind. Electron.
– volume: 226
  year: 2024
  ident: b0040
  article-title: A fault diagnosis method using improved prototypical network and weighting similarity-Manhattan distance with insufficient noisy data
  publication-title: Measurement
– volume: 230
  year: 2021
  ident: b0125
  article-title: Self-learning transferable neural network for intelligent fault diagnosis of rotating machinery with unlabeled and imbalanced data
  publication-title: Knowl.-Based Syst.
– volume: 52
  start-page: 9157
  year: 2022
  end-page: 9169
  ident: b0195
  article-title: Graph convolutional network-based method for fault diagnosis using a hybrid of measurement and prior knowledge
  publication-title: IEEE Trans. Cybern.
– volume: 22
  start-page: 2572
  year: 2021
  end-page: 2581
  ident: b0215
  article-title: Fault detection of the harmonic reducer based on CNN-LSTM with a novel denoising algorithm
  publication-title: IEEE Sens. J.
– volume: 252
  year: 2022
  ident: b0160
  article-title: A gated graph convolutional network with multi-sensor signals for remaining useful life prediction
  publication-title: Knowl.-Based Syst.
– volume: 200
  year: 2023
  ident: b0100
  article-title: An improved GNN using dynamic graph embedding mechanism: A novel end-to-end framework for rolling bearing fault diagnosis under variable working conditions
  publication-title: Mech. Syst. Sig. Process.
– reference: Z. Chen
– volume: 72
  start-page: 1
  year: 2023
  end-page: 12
  ident: b0055
  article-title: Harmonic reducer fault detection with acoustic emission
  publication-title: IEEE Trans. Instrum. Meas.
– year: 2023
  ident: b0030
  article-title: Contrastive learning and dynamics embedding neural network for label-free interpretable machine fault diagnosis
  publication-title: ISA Trans.
– reference: T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,”
– year: 2016
  ident: b0200
  article-title: Learning convolutional neural networks for graphs
– volume: 69
  start-page: 9547
  year: 2022
  end-page: 9555
  ident: b0210
  article-title: Fault Feature Extractor Based on Bootstrap Your Own Latent and Data Augmentation Algorithm for Unlabeled Vibration Signals
  publication-title: IEEE Trans. Ind. Electron.
– year: 2023
  ident: b0170
  article-title: Knowledge correlation graph-guided multi-source interaction domain adaptation network for rotating machinery fault diagnosis
  publication-title: ISA Trans.
– volume: 70
  start-page: 1
  year: 2021
  end-page: 11
  ident: b0075
  article-title: Fault diagnosis of harmonic drive with imbalanced data using generative adversarial network
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 128
  start-page: 485
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0025
  article-title: Rolling bearing fault diagnosis based on SSA optimized self-adaptive DBN
  publication-title: ISA Trans.
  doi: 10.1016/j.isatra.2021.11.024
– volume: 53
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0205
  article-title: Remaining useful life prediction of bearings by a new reinforced memory GRU network
  publication-title: Adv. Eng. Inf.
  doi: 10.1016/j.aei.2022.101682
– volume: 68
  start-page: 12739
  issue: 12
  year: 2021
  ident: 10.1016/j.aei.2024.102579_b0190
  article-title: Multireceptive field graph convolutional networks for machine fault diagnosis
  publication-title: IEEE Trans. Ind. Electron.
  doi: 10.1109/TIE.2020.3040669
– ident: 10.1016/j.aei.2024.102579_b0080
– volume: 22
  start-page: 2572
  issue: 3
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0050
  article-title: Fault detection of the harmonic reducer based on CNN-LSTM with a novel denoising algorithm
  publication-title: IEEE Sens. J.
  doi: 10.1109/JSEN.2021.3137992
– volume: 71
  start-page: 1
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0130
  article-title: Deep self-supervised domain adaptation network for fault diagnosis of rotating machine with unlabeled data
  publication-title: IEEE Trans. Instrum. Meas.
  doi: 10.1109/TIM.2022.3218574
– start-page: 1
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0090
  article-title: Spatio-temporal graph neural networks for predictive learning in urban computing: A survey
  publication-title: IEEE Trans. Knowl. Data Eng.
– volume: 70
  start-page: 4186
  issue: 4
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0110
  article-title: Compound fault diagnosis of harmonic drives using deep capsule graph convolutional network
  publication-title: IEEE Trans. Ind. Electron.
  doi: 10.1109/TIE.2022.3176280
– volume: 66
  start-page: 233
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0060
  article-title: In-situ fault diagnosis for the harmonic reducer of industrial robots via multi-scale mixed convolutional neural networks
  publication-title: J. Manuf. Syst.
  doi: 10.1016/j.jmsy.2022.12.001
– volume: 4
  start-page: 1431
  issue: 2
  year: 2019
  ident: 10.1016/j.aei.2024.102579_b0005
  article-title: Humanoid robot HRP-5P: An electrically actuated humanoid robot with high-power and wide-range joints
  publication-title: IEEE Rob. Autom. Lett.
  doi: 10.1109/LRA.2019.2896465
– volume: 226
  year: 2024
  ident: 10.1016/j.aei.2024.102579_b0040
  article-title: A fault diagnosis method using improved prototypical network and weighting similarity-Manhattan distance with insufficient noisy data
  publication-title: Measurement
  doi: 10.1016/j.measurement.2024.114171
– volume: 54
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0045
  article-title: A novel Brownian correlation metric prototypical network for rotating machinery fault diagnosis with few and zero shot learners
  publication-title: Adv. Eng. Inf.
  doi: 10.1016/j.aei.2022.101815
– volume: 65
  start-page: 2116
  issue: 9
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0065
  article-title: Harmonic reducer in-situ fault diagnosis for industrial robots based on deep learning
  publication-title: Sci. China Technol. Sci.
  doi: 10.1007/s11431-022-2129-9
– volume: 45
  start-page: 5329
  issue: 4
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0150
  article-title: Unsupervised graph embedding via adaptive graph learning
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2022.3202158
– volume: 278
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0155
  article-title: “Attention-aware temporal–spatial graph neural network with multi-sensor information fusion for fault diagnosis,”
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2023.110891
– volume: 139
  start-page: 574
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0165
  article-title: MIM-Graph: A multi-sensor network approach for fault diagnosis of HSR Bogie bearings at the IoT edge via mutual information maximization
  publication-title: ISA Trans.
  doi: 10.1016/j.isatra.2023.04.033
– volume: 200
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0100
  article-title: An improved GNN using dynamic graph embedding mechanism: A novel end-to-end framework for rolling bearing fault diagnosis under variable working conditions
  publication-title: Mech. Syst. Sig. Process.
  doi: 10.1016/j.ymssp.2023.110534
– volume: 62
  start-page: 1
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0095
  article-title: Triplet metric driven multi-head GNN augmented with decoupling adversarial learning for intelligent fault diagnosis of machines under varying working condition
  publication-title: J. Manuf. Syst.
  doi: 10.1016/j.jmsy.2021.10.014
– volume: 70
  start-page: 1
  year: 2021
  ident: 10.1016/j.aei.2024.102579_b0105
  article-title: Rotating machine systems fault diagnosis using semisupervised conditional random field-based graph attention network
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 69
  start-page: 9547
  issue: 9
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0210
  article-title: Fault Feature Extractor Based on Bootstrap Your Own Latent and Data Augmentation Algorithm for Unlabeled Vibration Signals
  publication-title: IEEE Trans. Ind. Electron.
  doi: 10.1109/TIE.2021.3111567
– ident: 10.1016/j.aei.2024.102579_b0120
– volume: 252
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0160
  article-title: A gated graph convolutional network with multi-sensor signals for remaining useful life prediction
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2022.109340
– volume: 68
  start-page: 3445
  issue: 4
  year: 2021
  ident: 10.1016/j.aei.2024.102579_b0015
  article-title: Attention recurrent neural network-based severity estimation method for interturn short-circuit fault in permanent magnet synchronous machines
  publication-title: IEEE Trans. Ind. Electron.
  doi: 10.1109/TIE.2020.2978690
– volume: 72
  start-page: 1
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0175
  article-title: A data privacy protection diagnosis framework for multiple machines vibration signals based on a swarm learning algorithm
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 72
  start-page: 1
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0180
  article-title: An improved data privacy diagnostic framework for multiple machinery components data based on swarm learning algorithm
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 140
  year: 2020
  ident: 10.1016/j.aei.2024.102579_b0010
  article-title: A deep learning method for bearing fault diagnosis based on cyclic spectral coherence and convolutional neural networks
  publication-title: Mech. Syst. Sig. Process.
  doi: 10.1016/j.ymssp.2020.106683
– volume: 70
  start-page: 1
  year: 2021
  ident: 10.1016/j.aei.2024.102579_b0075
  article-title: Fault diagnosis of harmonic drive with imbalanced data using generative adversarial network
  publication-title: IEEE Trans. Instrum. Meas.
  doi: 10.1109/TIM.2021.3126366
– volume: 22
  start-page: 2572
  issue: 3
  year: 2021
  ident: 10.1016/j.aei.2024.102579_b0215
  article-title: Fault detection of the harmonic reducer based on CNN-LSTM with a novel denoising algorithm
  publication-title: IEEE Sens. J.
  doi: 10.1109/JSEN.2021.3137992
– volume: 72
  start-page: 1
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0055
  article-title: Harmonic reducer fault detection with acoustic emission
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 59
  year: 2024
  ident: 10.1016/j.aei.2024.102579_b0140
  article-title: Time-frequency supervised contrastive learning via pseudo-labeling: An unsupervised domain adaptation network for rolling bearing fault diagnosis under time-varying speeds
  publication-title: Adv. Eng. Inf.
  doi: 10.1016/j.aei.2023.102304
– volume: 230
  year: 2021
  ident: 10.1016/j.aei.2024.102579_b0125
  article-title: Self-learning transferable neural network for intelligent fault diagnosis of rotating machinery with unlabeled and imbalanced data
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2021.107374
– volume: 19
  start-page: 7733
  issue: 6
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0135
  article-title: Time-varying online transfer learning for intelligent bearing fault diagnosis with incomplete unlabeled target data
  publication-title: IEEE Trans. Ind. Inf.
  doi: 10.1109/TII.2022.3230669
– volume: 250
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0185
  article-title: Transferable graph features-driven cross-domain rotating machinery fault diagnosis
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2022.109069
– volume: 149
  year: 2021
  ident: 10.1016/j.aei.2024.102579_b0020
  article-title: A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery
  publication-title: Mech. Syst. Sig. Process.
  doi: 10.1016/j.ymssp.2020.107327
– volume: 72
  start-page: 1
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0070
  article-title: Fault diagnosis of harmonic drives based on an SDP-ConvNeXt joint methodology
  publication-title: IEEE Trans. Instrum. Meas.
– year: 2023
  ident: 10.1016/j.aei.2024.102579_b0170
  article-title: Knowledge correlation graph-guided multi-source interaction domain adaptation network for rotating machinery fault diagnosis
  publication-title: ISA Trans.
  doi: 10.1016/j.isatra.2023.07.036
– year: 2016
  ident: 10.1016/j.aei.2024.102579_b0200
  article-title: Learning convolutional neural networks for graphs
– volume: 113
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0035
  article-title: Adversarial domain adaptation network with pseudo-siamese feature extractors for cross-bearing fault transfer diagnosis
  publication-title: Eng. Appl. Artif. Intel.
  doi: 10.1016/j.engappai.2022.104932
– volume: 260
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0145
  article-title: Deep hypergraph autoencoder embedding: An efficient intelligent approach for rotating machinery fault diagnosis
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2022.110172
– volume: 52
  start-page: 9157
  issue: 9
  year: 2022
  ident: 10.1016/j.aei.2024.102579_b0195
  article-title: Graph convolutional network-based method for fault diagnosis using a hybrid of measurement and prior knowledge
  publication-title: IEEE Trans. Cybern.
  doi: 10.1109/TCYB.2021.3059002
– volume: 34
  start-page: 6015
  issue: 9
  year: 2023
  ident: 10.1016/j.aei.2024.102579_b0115
  article-title: Interaction-aware graph neural networks for fault diagnosis of complex industrial processes
  publication-title: IEEE Trans. Neural Networks Learn. Syst.
  doi: 10.1109/TNNLS.2021.3132376
– ident: 10.1016/j.aei.2024.102579_b0085
– year: 2023
  ident: 10.1016/j.aei.2024.102579_b0030
  article-title: Contrastive learning and dynamics embedding neural network for label-free interpretable machine fault diagnosis
  publication-title: ISA Trans.
SSID ssj0016897
Score 2.4543235
Snippet As a pivotal component in robotic systems, harmonic reducer fault diagnosis plays a crucial role in safe and stable operation; however, the lack of labelled...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 102579
SubjectTerms Graph autoencoder
Self-constructed graph
Single-variable vibration signals
Unsupervised fault feature extractor
Title SCG-GFFE: A Self-Constructed graph fault feature extractor based on graph Auto-encoder algorithm for unlabeled single-variable vibration signals of harmonic reducer
URI https://dx.doi.org/10.1016/j.aei.2024.102579
Volume 62
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier)
  issn: 1474-0346
  databaseCode: GBLVA
  dateStart: 20110101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: true
  ssIdentifier: ssj0016897
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier Science Direct Journals
  issn: 1474-0346
  databaseCode: AIKHN
  dateStart: 20020101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: true
  ssIdentifier: ssj0016897
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Complete Freedom Collection
  issn: 1474-0346
  databaseCode: ACRLP
  dateStart: 20020101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: true
  ssIdentifier: ssj0016897
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection
  issn: 1474-0346
  databaseCode: .~1
  dateStart: 20020101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: true
  ssIdentifier: ssj0016897
  providerName: Elsevier
– providerCode: PRVLSH
  databaseName: Elsevier Journals
  issn: 1474-0346
  databaseCode: AKRWK
  dateStart: 20020101
  customDbUrl:
  isFulltext: true
  mediaType: online
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0016897
  providerName: Library Specific Holdings
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELaqcuFCC7SiPKo5cEIymziO43BbrbpdQPSyVOotsmOn3SokVcj22F_DD2UmcSqQoIdeIiUZS5FnMo_km28Ye5_bkhLfimuLB5lkEbceq9bc2CrRqZFaUr_ztzO1OpdfLtKLHbaYemEIVhl8_-jTB28drszCbs5uNpvZOpaZjBKpCAUpxNBHLmVGUww-3t3DPGKlxwErKMxJevqzOWC8jN9giSgkERikhOb6V2z6I94s99mzkCjCfHyW52zHNy_YXkgaIbySP1-yX-vFKT9dLk8-wRzWvq44zeAcWGFRbuCjhsps6x4qP5B4ArrjbpiyAxTCHLRNEJtv-5YTsaXzHZj6su02_dUPwLQWtg1aC0YoB_Rtofb8Fmts6rqCW6q3SbtAUBA0ZmgrID5s4tyFjphhfXfAzpcn3xcrHkYv8FLkWc-x3o6ttplOhdHOZkZoLX2UWqt0iUHelLH2kdKJdLlBn-C1ip0zwtoUb-gkOWS7Tdv4VwxUidaQlZWTiZY2UjaRHpXrrYtELrQ6YtG06UUZeMlpPEZdTAC06wL1VJCeilFPR-zD_ZKbkZTjIWE5abL4y7IKDBr_X_b6ccvesKd0NsL93rJdVLd_h2lLb48HuzxmT-afv67OfgPc2O33
linkProvider Elsevier
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELaqcoALlJcoFJgDJySzieM4Tm-rVbcLtL1sK_UW2bFDF4WkCtke-TX80M4kTgUScOCSQzyWIs9kHsk33zD2LrclJb4V1xYvMskibj1WrbmxVaJTI7WkfufTM7W6kJ8u08sdtph6YQhWGXz_6NMHbx3uzMJpzq43m9k6lpmMEqkIBSkE9ZHfk6nIqAL78OMO5xErPU5YQWlO4tOvzQHkZfwGa0QhicEgJTjXn4LTLwFnuccehkwR5uPDPGY7vnnCHoWsEcI7-f0p-7leHPPj5fLoEOaw9nXFaQjnQAuLcgMhNVRmW_dQ-YHFE9Afd8OYHaAY5qBtgth827ecmC2d78DUX9pu0199A8xrYduguWCIckAfF2rPb7DIprYruKGCm9QLhAVBa4a2AiLEJtJd6Iga1nfP2MXy6Hyx4mH2Ai9FnvUcC-7YapvpVBjtbGaE1tJHqbVKlxjlTRlrHymdSJcbdApeq9g5I6xNcUEnyXO227SNf8FAlWgOWVk5mWhpI2UT6VG73rpI5EKrfRZNh16UgZic5mPUxYRA-1qgngrSUzHqaZ-9v9tyPbJy_EtYTposfjOtAqPG37e9_L9tb9n91fnpSXHy8ezzK_aAVkbs3wHbRdX715jD9PbNYKO3ZqHvjA
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=SCG-GFFE%3A+A+Self-Constructed+graph+fault+feature+extractor+based+on+graph+Auto-encoder+algorithm+for+unlabeled+single-variable+vibration+signals+of+harmonic+reducer&rft.jtitle=Advanced+engineering+informatics&rft.au=Sun%2C+Shilong&rft.au=Ding%2C+Hao&rft.au=Zhao%2C+Zida&rft.au=Xu%2C+Wenfu&rft.date=2024-10-01&rft.pub=Elsevier+Ltd&rft.issn=1474-0346&rft.volume=62&rft_id=info:doi/10.1016%2Fj.aei.2024.102579&rft.externalDocID=S1474034624002271
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1474-0346&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1474-0346&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1474-0346&client=summon