Health indicator construction for degradation assessment by embedded LSTM–CNN​ autoencoder and growing self-organized map

Health indicator (HI) construction is the most significant task of degradation assessment (DA) that facilitates prognostic and health management of rotating machinery. Many stacked autoencoder (SAE) models represented by CNN-based and RNN-based SAE have been applied to the field of DA. However, the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Knowledge-based systems Ročník 252; s. 109399
Hlavní autoři: Chen, Zhipeng, Zhu, Haiping, Wu, Jun, Fan, Liangzhi
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 27.09.2022
Témata:
ISSN:0950-7051, 1872-7409
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Health indicator (HI) construction is the most significant task of degradation assessment (DA) that facilitates prognostic and health management of rotating machinery. Many stacked autoencoder (SAE) models represented by CNN-based and RNN-based SAE have been applied to the field of DA. However, the former has a small receptive vision which makes it weak in encoding time-series information, while the latter can easily encounter the problem of overfitting or parameter expansion. To solve these problems, this paper proposes an embedded LSTM–CNN​ autoencoder to extract trend features that contain both local characteristics and degradation trend information from vibration data. And, a transfer learning-based two-phase network training algorithm is designed to enhance the ability of noise filtering of the model. Then, HI is obtained by fusing the extracted trend features with a growing self-organized map. Finally, two case studies are implemented by using bearing datasets to verify the proposed method. The results show that HI gained by the proposed method is more effective than that by other existing methods. Moreover, the goodness-of-fit of polynomial degradation models with the HI is analyzed.
AbstractList Health indicator (HI) construction is the most significant task of degradation assessment (DA) that facilitates prognostic and health management of rotating machinery. Many stacked autoencoder (SAE) models represented by CNN-based and RNN-based SAE have been applied to the field of DA. However, the former has a small receptive vision which makes it weak in encoding time-series information, while the latter can easily encounter the problem of overfitting or parameter expansion. To solve these problems, this paper proposes an embedded LSTM–CNN​ autoencoder to extract trend features that contain both local characteristics and degradation trend information from vibration data. And, a transfer learning-based two-phase network training algorithm is designed to enhance the ability of noise filtering of the model. Then, HI is obtained by fusing the extracted trend features with a growing self-organized map. Finally, two case studies are implemented by using bearing datasets to verify the proposed method. The results show that HI gained by the proposed method is more effective than that by other existing methods. Moreover, the goodness-of-fit of polynomial degradation models with the HI is analyzed.
ArticleNumber 109399
Author Wu, Jun
Chen, Zhipeng
Zhu, Haiping
Fan, Liangzhi
Author_xml – sequence: 1
  givenname: Zhipeng
  surname: Chen
  fullname: Chen, Zhipeng
  organization: School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China
– sequence: 2
  givenname: Haiping
  surname: Zhu
  fullname: Zhu, Haiping
  email: haipzhu@hust.edu.cn
  organization: School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China
– sequence: 3
  givenname: Jun
  surname: Wu
  fullname: Wu, Jun
  organization: School of Naval Architecture and Ocean Engineering, Huazhong University of Science and Technology, Wuhan, China
– sequence: 4
  givenname: Liangzhi
  surname: Fan
  fullname: Fan, Liangzhi
  organization: School of Mechanical Engineering and Automation, Wuhan Textile University, Wuhan, China
BookMark eNqFkMtOIzEQRS0EEuHxByz8Ax3sfsRtFkijaHhIGVgAa8t2VQeHxEa2GRSkkbKfJX_Il0wnYTULWJXqqs6V6hyQXR88EnLC2ZAzPjqdDZ98SMs0LFlZ9pGspNwhA96KshA1k7tkwGTDCsEavk8OUpox1l_ydkD-XKGe50fqPDirc4jUBp9yfLHZBU-7PgCcRg16s-uUMKUF-kzNkuLCIAACndzd__pYvY9vbj5Wf6l-yQG9DYCRag90GsOr81OacN4VIU61d289tNDPR2Sv0_OEx5_zkDxc_LwfXxWT28vr8Y9JYSs2ykXNjdBNC7wzrNENByn4CAR0o9pwaEsEycEK27RGNF0jDKKxYDtZmbqSFqtDcrbttTGkFLFT1uXNRzlqN1ecqbVINVNbkWotUm1F9nD9H_wc3ULH5XfY-RbD_rHfDqNK1vVaEFxEmxUE93XBPxpkl7U
CitedBy_id crossref_primary_10_1016_j_ssci_2024_106590
crossref_primary_10_3390_e25020242
crossref_primary_10_1109_TIM_2024_3378268
crossref_primary_10_1007_s40430_024_04866_2
crossref_primary_10_1016_j_aei_2024_102998
crossref_primary_10_1016_j_ress_2025_110906
crossref_primary_10_1016_j_ymssp_2023_110688
crossref_primary_10_1016_j_ymssp_2024_111699
crossref_primary_10_1016_j_engappai_2023_107562
crossref_primary_10_1016_j_ymssp_2025_112589
crossref_primary_10_1016_j_ress_2025_111039
crossref_primary_10_1016_j_rineng_2025_106373
crossref_primary_10_1088_1361_6501_ad0ad5
crossref_primary_10_3390_electronics12071569
crossref_primary_10_1109_JSEN_2023_3309630
crossref_primary_10_1038_s41598_025_02347_7
crossref_primary_10_1109_TIM_2025_3584158
crossref_primary_10_1088_1361_6501_ad0f67
crossref_primary_10_1016_j_aei_2024_102945
crossref_primary_10_1016_j_engappai_2023_106934
crossref_primary_10_1016_j_aei_2024_102863
crossref_primary_10_1016_j_knosys_2025_113841
crossref_primary_10_1016_j_ress_2023_109776
crossref_primary_10_1016_j_ress_2023_109337
crossref_primary_10_3390_s24072135
crossref_primary_10_1016_j_ress_2024_110238
crossref_primary_10_1016_j_ymssp_2025_112431
Cites_doi 10.1016/j.ymssp.2016.04.028
10.1109/TII.2020.2999442
10.1016/j.ymssp.2017.11.016
10.1109/TII.2020.2966326
10.1016/j.isatra.2020.12.052
10.1109/TMECH.2020.3042806
10.1109/TIE.2020.3003649
10.1016/j.jmsy.2019.11.008
10.1109/72.557663
10.1016/j.ymssp.2017.02.003
10.1016/j.knosys.2021.106796
10.1016/j.asoc.2018.09.037
10.3390/en14082322
10.1109/TII.2018.2866549
10.1088/1361-6501/abd498
10.1016/j.neucom.2017.02.045
10.1016/j.ins.2020.03.018
10.1016/j.asoc.2019.106060
10.1016/j.compstruct.2021.114590
ContentType Journal Article
Copyright 2022 Elsevier B.V.
Copyright_xml – notice: 2022 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.knosys.2022.109399
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-7409
ExternalDocumentID 10_1016_j_knosys_2022_109399
S0950705122007018
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
ABYKQ
ACAZW
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
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ARUGR
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
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
ROL
RPZ
SDF
SDG
SDP
SES
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
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
G-2
HLZ
HVGLF
HZ~
R2-
SBC
SET
SEW
UHS
WUQ
~HD
ID FETCH-LOGICAL-c306t-41b7a58d1fb05a51d9716d7df64b1d82ed91dc7c58b75f57beebcdcf93b439ce3
ISICitedReferencesCount 31
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000853871500006&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 21:16:18 EST 2025
Sat Nov 29 07:05:45 EST 2025
Fri Feb 23 02:40:21 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Growing self-organized map
Autoencoder
Transfer learning
Degradation assessment
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-41b7a58d1fb05a51d9716d7df64b1d82ed91dc7c58b75f57beebcdcf93b439ce3
ParticipantIDs crossref_citationtrail_10_1016_j_knosys_2022_109399
crossref_primary_10_1016_j_knosys_2022_109399
elsevier_sciencedirect_doi_10_1016_j_knosys_2022_109399
PublicationCentury 2000
PublicationDate 2022-09-27
PublicationDateYYYYMMDD 2022-09-27
PublicationDate_xml – month: 09
  year: 2022
  text: 2022-09-27
  day: 27
PublicationDecade 2020
PublicationTitle Knowledge-based systems
PublicationYear 2022
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Cheng (b25) 2019; 15
Yuan (b17) 2020; 534
P. Nectoux, et al., PRONOSTIA : An experimental platform for bearings accelerated degradation tests, in: IEEE International Conference on Prognostics and Health Management, PHM’12. 2012. Denver, Colorado, United States: IEEE Catalog Number : CPF12PHM-CDR.
Wang (b10) 2018
Xia (b3) 2021
Tian, Wang, Lu (b29) 2019; 114
Cheng (b24) 2021; 216
Xu, Tse, Tse (b26) 2018; 73
Yu, Zhou (b12) 2020; 16
Chen (b32) 2020; 54
Cheng (b21) 2021
Bedi, Toshniwal (b13) 2020
Cheng (b1) 2021; 70
Wu (b2) 2020
Lei (b5) 2018; 104
Guo (b15) 2017; 240
Zhu (b16) 2020; 88
Villmann (b27) 1997; 8
Xiao (b18) 2020
Haidong (b20) 2020
Ding (b8) 2020; 2020
Qin (b6) 2021; 17
Chen (b22) 2021; 114
Rai, Upadhyay (b30) 2017; 93
Mao (b31) 2021; 70
Aremu (b9) 2020
Kuang (b11) 2021; 32
Kong (b14) 2019
Yu, Kim, Mechefske (b19) 2020
Wang (b4) 2021; 68
Soualhi (b7) 2021; 14
Wu (b23) 2021; 276
Wu (10.1016/j.knosys.2022.109399_b23) 2021; 276
10.1016/j.knosys.2022.109399_b28
Zhu (10.1016/j.knosys.2022.109399_b16) 2020; 88
Yu (10.1016/j.knosys.2022.109399_b12) 2020; 16
Wu (10.1016/j.knosys.2022.109399_b2) 2020
Qin (10.1016/j.knosys.2022.109399_b6) 2021; 17
Wang (10.1016/j.knosys.2022.109399_b4) 2021; 68
Lei (10.1016/j.knosys.2022.109399_b5) 2018; 104
Kong (10.1016/j.knosys.2022.109399_b14) 2019
Chen (10.1016/j.knosys.2022.109399_b22) 2021; 114
Villmann (10.1016/j.knosys.2022.109399_b27) 1997; 8
Aremu (10.1016/j.knosys.2022.109399_b9) 2020
Bedi (10.1016/j.knosys.2022.109399_b13) 2020
Wang (10.1016/j.knosys.2022.109399_b10) 2018
Guo (10.1016/j.knosys.2022.109399_b15) 2017; 240
Soualhi (10.1016/j.knosys.2022.109399_b7) 2021; 14
Xiao (10.1016/j.knosys.2022.109399_b18) 2020
Chen (10.1016/j.knosys.2022.109399_b32) 2020; 54
Kuang (10.1016/j.knosys.2022.109399_b11) 2021; 32
Cheng (10.1016/j.knosys.2022.109399_b1) 2021; 70
Haidong (10.1016/j.knosys.2022.109399_b20) 2020
Cheng (10.1016/j.knosys.2022.109399_b24) 2021; 216
Ding (10.1016/j.knosys.2022.109399_b8) 2020; 2020
Cheng (10.1016/j.knosys.2022.109399_b25) 2019; 15
Xu (10.1016/j.knosys.2022.109399_b26) 2018; 73
Xia (10.1016/j.knosys.2022.109399_b3) 2021
Cheng (10.1016/j.knosys.2022.109399_b21) 2021
Yuan (10.1016/j.knosys.2022.109399_b17) 2020; 534
Yu (10.1016/j.knosys.2022.109399_b19) 2020
Tian (10.1016/j.knosys.2022.109399_b29) 2019; 114
Rai (10.1016/j.knosys.2022.109399_b30) 2017; 93
Mao (10.1016/j.knosys.2022.109399_b31) 2021; 70
References_xml – volume: 32
  year: 2021
  ident: b11
  article-title: Learning a superficial correlated representation using a local mapping strategy for bearing performance degradation assessment
  publication-title: Meas. Sci. Technol.
– volume: 88
  year: 2020
  ident: b16
  article-title: Stacked pruning sparse denoising autoencoder based intelligent fault diagnosis of rolling bearings
  publication-title: Appl. Soft Comput.
– volume: 54
  start-page: 1
  year: 2020
  end-page: 11
  ident: b32
  article-title: Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks
  publication-title: J. Manuf. Syst.
– start-page: 1
  year: 2018
  end-page: 12
  ident: b10
  article-title: A hybrid prognostics approach for estimating remaining useful life of rolling element bearings
  publication-title: IEEE Trans. Reliab.
– volume: 8
  start-page: 256
  year: 1997
  end-page: 266
  ident: b27
  article-title: Topology preservation in self-organizing feature maps: exact definition and measurement
  publication-title: IEEE Trans. Neural Netw.
– volume: 104
  start-page: 799
  year: 2018
  end-page: 834
  ident: b5
  article-title: Machinery health prognostics: A systematic review from data acquisition to RUL prediction
  publication-title: Mech. Syst. Signal Process.
– volume: 240
  start-page: 98
  year: 2017
  end-page: 109
  ident: b15
  article-title: A recurrent neural network based health indicator for remaining useful life prediction of bearings
  publication-title: Neurocomputing
– start-page: 188
  year: 2020
  ident: b20
  article-title: Enhanced deep gated recurrent unit and complex wavelet packet energy moment entropy for early fault prognosis of bearing
  publication-title: Knowl.-Based Syst.
– volume: 114
  start-page: 658
  year: 2019
  end-page: 673
  ident: b29
  article-title: Self-adaptive bearing fault diagnosis based on permutation entropy and manifold-based dynamic time warping
  publication-title: Mech. Syst. Signal Process.
– volume: 2020
  start-page: 1
  year: 2020
  end-page: 14
  ident: b8
  article-title: Feature clustering analysis using reference model towards rolling bearing performance degradation assessment
  publication-title: Shock Vib.
– reference: P. Nectoux, et al., PRONOSTIA : An experimental platform for bearings accelerated degradation tests, in: IEEE International Conference on Prognostics and Health Management, PHM’12. 2012. Denver, Colorado, United States: IEEE Catalog Number : CPF12PHM-CDR.
– start-page: 48
  year: 2021
  ident: b21
  article-title: A convolutional neural network based degradation indicator construction and health prognosis using bidirectional long short-term memory network for rolling bearings
  publication-title: Adv. Eng. Inf.
– volume: 73
  start-page: 898
  year: 2018
  end-page: 913
  ident: b26
  article-title: Roller bearing fault diagnosis using stacked denoising autoencoder in deep learning and gath–geva clustering algorithm without principal component analysis and data label
  publication-title: Appl. Soft Comput.
– volume: 68
  start-page: 7496
  year: 2021
  end-page: 7504
  ident: b4
  article-title: Multiscale convolutional attention network for predicting remaining useful life of machinery
  publication-title: Ieee Trans. Ind. Electron.
– volume: 70
  start-page: 1
  year: 2021
  end-page: 12
  ident: b1
  article-title: Remaining useful life prognosis based on ensemble long short-term memory neural network
  publication-title: IEEE Trans. Instrum. Meas.
– start-page: 125
  year: 2021
  ident: b3
  article-title: LSTM-based multi-layer self-attention method for remaining useful life estimation of mechanical systems
  publication-title: Eng. Fail. Anal.
– start-page: 145
  year: 2020
  ident: b9
  article-title: A relative entropy based feature selection framework for asset data in predictive maintenance
  publication-title: Comput. Ind. Eng.
– volume: 17
  start-page: 6438
  year: 2021
  end-page: 6447
  ident: b6
  article-title: Gated dual attention unit neural networks for remaining useful life prediction of rolling bearings
  publication-title: Ieee Trans. Ind. Inf.
– volume: 14
  year: 2021
  ident: b7
  article-title: A novel feature extraction method for the condition monitoring of bearings
  publication-title: Energies
– volume: 216
  year: 2021
  ident: b24
  article-title: Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network
  publication-title: Knowl.-Based Syst.
– volume: 114
  start-page: 44
  year: 2021
  end-page: 56
  ident: b22
  article-title: Health indicator construction by quadratic function-based deep convolutional auto-encoder and its application into bearing RUL prediction
  publication-title: Isa Trans.
– volume: 534
  start-page: 72
  year: 2020
  end-page: 84
  ident: b17
  article-title: Stacked isomorphic autoencoder based soft analyzer and its application to sulfur recovery unit
  publication-title: Inform. Sci.
– volume: 276
  year: 2021
  ident: b23
  article-title: Lamb wave-based damage detection of composite structures using deep convolutional neural network and continuous wavelet transform
  publication-title: Compos. Struct.
– volume: 15
  start-page: 987
  year: 2019
  end-page: 997
  ident: b25
  article-title: Machine health monitoring using adaptive kernel spectral clustering and deep long short-term memory recurrent neural networks
  publication-title: IEEE Trans. Ind. Inf.
– start-page: 1
  year: 2020
  ident: b2
  article-title: Ensemble generalized multiclass support vector machine-based health evaluation of complex degradation systems
  publication-title: IEEE/ASME Trans. Mechatronics
– year: 2019
  ident: b14
  article-title: A Multi-Ensemble Method Based on Deep Auto-Encoders for Fault Diagnosis of Rolling Bearings, Vol. 151
– start-page: 165
  year: 2020
  ident: b18
  article-title: Degradation assessment of bearings with trend-reconstruct-based features selection and gated recurrent unit network
  publication-title: Measurement
– volume: 93
  start-page: 16
  year: 2017
  end-page: 29
  ident: b30
  article-title: Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering
  publication-title: Mech. Syst. Signal Process.
– volume: 16
  start-page: 6347
  year: 2020
  end-page: 6358
  ident: b12
  article-title: One-dimensional residual convolutional autoencoder based feature learning for gearbox fault diagnosis
  publication-title: IEEE Trans. Ind. Inf.
– start-page: 93
  year: 2020
  ident: b13
  article-title: Energy load time-series forecast using decomposition and autoencoder integrated memory network
  publication-title: Appl. Soft Comput.
– start-page: 199
  year: 2020
  ident: b19
  article-title: An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme
  publication-title: Reliab. Eng. Syst. Saf.
– volume: 70
  start-page: 1
  year: 2021
  end-page: 13
  ident: b31
  article-title: Construction of health indicators for rotating machinery using deep transfer learning with multiscale feature representation
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 114
  start-page: 658
  year: 2019
  ident: 10.1016/j.knosys.2022.109399_b29
  article-title: Self-adaptive bearing fault diagnosis based on permutation entropy and manifold-based dynamic time warping
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2016.04.028
– volume: 17
  start-page: 6438
  issue: 9
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b6
  article-title: Gated dual attention unit neural networks for remaining useful life prediction of rolling bearings
  publication-title: Ieee Trans. Ind. Inf.
  doi: 10.1109/TII.2020.2999442
– volume: 104
  start-page: 799
  year: 2018
  ident: 10.1016/j.knosys.2022.109399_b5
  article-title: Machinery health prognostics: A systematic review from data acquisition to RUL prediction
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2017.11.016
– volume: 16
  start-page: 6347
  issue: 10
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b12
  article-title: One-dimensional residual convolutional autoencoder based feature learning for gearbox fault diagnosis
  publication-title: IEEE Trans. Ind. Inf.
  doi: 10.1109/TII.2020.2966326
– year: 2019
  ident: 10.1016/j.knosys.2022.109399_b14
– volume: 114
  start-page: 44
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b22
  article-title: Health indicator construction by quadratic function-based deep convolutional auto-encoder and its application into bearing RUL prediction
  publication-title: Isa Trans.
  doi: 10.1016/j.isatra.2020.12.052
– volume: 70
  start-page: 1
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b1
  article-title: Remaining useful life prognosis based on ensemble long short-term memory neural network
  publication-title: IEEE Trans. Instrum. Meas.
– start-page: 1
  year: 2018
  ident: 10.1016/j.knosys.2022.109399_b10
  article-title: A hybrid prognostics approach for estimating remaining useful life of rolling element bearings
  publication-title: IEEE Trans. Reliab.
– start-page: 1
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b2
  article-title: Ensemble generalized multiclass support vector machine-based health evaluation of complex degradation systems
  publication-title: IEEE/ASME Trans. Mechatronics
  doi: 10.1109/TMECH.2020.3042806
– volume: 68
  start-page: 7496
  issue: 8
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b4
  article-title: Multiscale convolutional attention network for predicting remaining useful life of machinery
  publication-title: Ieee Trans. Ind. Electron.
  doi: 10.1109/TIE.2020.3003649
– volume: 54
  start-page: 1
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b32
  article-title: Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks
  publication-title: J. Manuf. Syst.
  doi: 10.1016/j.jmsy.2019.11.008
– start-page: 125
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b3
  article-title: LSTM-based multi-layer self-attention method for remaining useful life estimation of mechanical systems
  publication-title: Eng. Fail. Anal.
– volume: 8
  start-page: 256
  issue: 2
  year: 1997
  ident: 10.1016/j.knosys.2022.109399_b27
  article-title: Topology preservation in self-organizing feature maps: exact definition and measurement
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/72.557663
– volume: 2020
  start-page: 1
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b8
  article-title: Feature clustering analysis using reference model towards rolling bearing performance degradation assessment
  publication-title: Shock Vib.
– start-page: 188
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b20
  article-title: Enhanced deep gated recurrent unit and complex wavelet packet energy moment entropy for early fault prognosis of bearing
  publication-title: Knowl.-Based Syst.
– start-page: 199
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b19
  article-title: An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme
  publication-title: Reliab. Eng. Syst. Saf.
– start-page: 145
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b9
  article-title: A relative entropy based feature selection framework for asset data in predictive maintenance
  publication-title: Comput. Ind. Eng.
– volume: 93
  start-page: 16
  year: 2017
  ident: 10.1016/j.knosys.2022.109399_b30
  article-title: Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2017.02.003
– volume: 216
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b24
  article-title: Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2021.106796
– ident: 10.1016/j.knosys.2022.109399_b28
– volume: 73
  start-page: 898
  year: 2018
  ident: 10.1016/j.knosys.2022.109399_b26
  article-title: Roller bearing fault diagnosis using stacked denoising autoencoder in deep learning and gath–geva clustering algorithm without principal component analysis and data label
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2018.09.037
– volume: 14
  issue: 8
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b7
  article-title: A novel feature extraction method for the condition monitoring of bearings
  publication-title: Energies
  doi: 10.3390/en14082322
– volume: 15
  start-page: 987
  issue: 2
  year: 2019
  ident: 10.1016/j.knosys.2022.109399_b25
  article-title: Machine health monitoring using adaptive kernel spectral clustering and deep long short-term memory recurrent neural networks
  publication-title: IEEE Trans. Ind. Inf.
  doi: 10.1109/TII.2018.2866549
– volume: 32
  issue: 6
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b11
  article-title: Learning a superficial correlated representation using a local mapping strategy for bearing performance degradation assessment
  publication-title: Meas. Sci. Technol.
  doi: 10.1088/1361-6501/abd498
– start-page: 93
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b13
  article-title: Energy load time-series forecast using decomposition and autoencoder integrated memory network
  publication-title: Appl. Soft Comput.
– volume: 240
  start-page: 98
  year: 2017
  ident: 10.1016/j.knosys.2022.109399_b15
  article-title: A recurrent neural network based health indicator for remaining useful life prediction of bearings
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2017.02.045
– volume: 534
  start-page: 72
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b17
  article-title: Stacked isomorphic autoencoder based soft analyzer and its application to sulfur recovery unit
  publication-title: Inform. Sci.
  doi: 10.1016/j.ins.2020.03.018
– volume: 70
  start-page: 1
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b31
  article-title: Construction of health indicators for rotating machinery using deep transfer learning with multiscale feature representation
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 88
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b16
  article-title: Stacked pruning sparse denoising autoencoder based intelligent fault diagnosis of rolling bearings
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2019.106060
– start-page: 48
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b21
  article-title: A convolutional neural network based degradation indicator construction and health prognosis using bidirectional long short-term memory network for rolling bearings
  publication-title: Adv. Eng. Inf.
– start-page: 165
  year: 2020
  ident: 10.1016/j.knosys.2022.109399_b18
  article-title: Degradation assessment of bearings with trend-reconstruct-based features selection and gated recurrent unit network
  publication-title: Measurement
– volume: 276
  year: 2021
  ident: 10.1016/j.knosys.2022.109399_b23
  article-title: Lamb wave-based damage detection of composite structures using deep convolutional neural network and continuous wavelet transform
  publication-title: Compos. Struct.
  doi: 10.1016/j.compstruct.2021.114590
SSID ssj0002218
Score 2.4847758
Snippet Health indicator (HI) construction is the most significant task of degradation assessment (DA) that facilitates prognostic and health management of rotating...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 109399
SubjectTerms Autoencoder
Deep learning
Degradation assessment
Growing self-organized map
Transfer learning
Title Health indicator construction for degradation assessment by embedded LSTM–CNN​ autoencoder and growing self-organized map
URI https://dx.doi.org/10.1016/j.knosys.2022.109399
Volume 252
WOSCitedRecordID wos000853871500006&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/eLvHCXMwtV1Lb9NAEF6FlAMX3ojy0h64RRvFjte7PpaoFY8SIREg4mLty21K6kSQVKUSUu8c-QX8tf4SZr3rjUNRoQculrWy13bmy85jZ75B6GlCC5b2lCACbAWSgMIlMqV9IrjVDjzqFdWO6ftdNhzy8Th702r9rGthjqasLPnxcTb_r6KGMRC2LZ29hLjDpDAA5yB0OILY4fhPgveFRXYvWlmP2iaWB5bYKqtQW4II10upIwIzpzVEzaE0sBLpzu7b0es6D6I_GA79OX_WEcvFzJJfWg4KG3TfAz--ikmYaUFcj6gTmOBQzJt276s6dEes2tSeQDrY8wNfI_JxfzI3XpdW0exlpRqFbbAdRj8sXTlJgPWOr58ApO-d7E-agQzwge3eDluLSPYI63n-Wb84x47f1i-vlvvK9VM6t_K7IMRB91M5g0_o2gd0V5evE23_pgBDWmKd8XaQu1lyO0vuZrmCNmJGM95GG1svtscvg7qP4yqIHN6-rs-skgjPv82f7Z-GTTO6ia57ZwRvORDdQi1T3kY36kYf2K_7d9A3hykcMIWbmMKAKdzAFF5hCsuvuMYUtpg6O_0BaDo7_Y4bOMKAI-xxhNdxhAFHd9G7ne3R4DnxfTuIAgd0QZJIMkG5jgrZo4JG2tKUaaaLNJGR5rHRWaQVU5RLRgvKpDFSaVVkfQnmsTL9e6hdzkpzH-GUForFVKZcx4mgQsYqiwTjiZQKLFW1ifr1r5krT2pve6tM84tkuYlIuGvuSF3-cj2rBZV7w9QZnDmg78I7H1zySQ_RtdVf4xFqgyTNY3RVHS0mXz4_8dD7BeX3toU
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=Health+indicator+construction+for+degradation+assessment+by+embedded+LSTM%E2%80%93CNN%E2%80%8B+autoencoder+and+growing+self-organized+map&rft.jtitle=Knowledge-based+systems&rft.au=Chen%2C+Zhipeng&rft.au=Zhu%2C+Haiping&rft.au=Wu%2C+Jun&rft.au=Fan%2C+Liangzhi&rft.date=2022-09-27&rft.issn=0950-7051&rft.volume=252&rft.spage=109399&rft_id=info:doi/10.1016%2Fj.knosys.2022.109399&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_knosys_2022_109399
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