SVAE‐GRU‐based degradation generation and prediction for small samples

The degradation process analysis is the basis of the system reliability assessment. Too few degradation samples will affect the accuracy of the reliability analysis. So, it is necessary to expand the degradation data and construct the degradation prediction model. This paper proposes an SVAE‐GRU‐bas...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Quality and reliability engineering international Ročník 39; číslo 7; s. 2851 - 2868
Hlavní autori: Shangguan, Anqi, Feng, Nan, Mu, Lingxia, Fei, Rong, Hei, Xinhong, Xie, Guo
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Bognor Regis Wiley Subscription Services, Inc 01.11.2023
Predmet:
ISSN:0748-8017, 1099-1638
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The degradation process analysis is the basis of the system reliability assessment. Too few degradation samples will affect the accuracy of the reliability analysis. So, it is necessary to expand the degradation data and construct the degradation prediction model. This paper proposes an SVAE‐GRU‐based degradation generation and prediction model to handle the issues. New degradation data are generated by combining the Stacked Variational Autoencoder (SVAE) and Gated Recurrent Units (GRU) in each time step, which can improve the learning effectiveness of the degradation features. The GRU and the Multi‐layer perceptron calculate the mean and the variance of the degradation distribution for each timestamp, the deeply heterogeneity and temporal feature of the original degraded samples are learned. Then the degradation amount of different samples are predicted. The optimal hyper‐parameters of the SVAE‐GRU are obtained by the grid search method. To verify the effectiveness of the proposed method, three datasets and four methods are used for experiment comparison in this paper. The actual example indicate that the SVAE‐GRU method has the best effect on the degradation generation and prediction.
AbstractList The degradation process analysis is the basis of the system reliability assessment. Too few degradation samples will affect the accuracy of the reliability analysis. So, it is necessary to expand the degradation data and construct the degradation prediction model. This paper proposes an SVAE‐GRU‐based degradation generation and prediction model to handle the issues. New degradation data are generated by combining the Stacked Variational Autoencoder (SVAE) and Gated Recurrent Units (GRU) in each time step, which can improve the learning effectiveness of the degradation features. The GRU and the Multi‐layer perceptron calculate the mean and the variance of the degradation distribution for each timestamp, the deeply heterogeneity and temporal feature of the original degraded samples are learned. Then the degradation amount of different samples are predicted. The optimal hyper‐parameters of the SVAE‐GRU are obtained by the grid search method. To verify the effectiveness of the proposed method, three datasets and four methods are used for experiment comparison in this paper. The actual example indicate that the SVAE‐GRU method has the best effect on the degradation generation and prediction.
The degradation process analysis is the basis of the system reliability assessment. Too few degradation samples will affect the accuracy of the reliability analysis. So, it is necessary to expand the degradation data and construct the degradation prediction model. This paper proposes an SVAE‐GRU‐based degradation generation and prediction model to handle the issues. New degradation data are generated by combining the Stacked Variational Autoencoder (SVAE) and Gated Recurrent Units (GRU) in each time step, which can improve the learning effectiveness of the degradation features. The GRU and the Multi‐layer perceptron calculate the mean and the variance of the degradation distribution for each timestamp, the deeply heterogeneity and temporal feature of the original degraded samples are learned. Then the degradation amount of different samples are predicted. The optimal hyper‐parameters of the SVAE‐GRU are obtained by the grid search method. To verify the effectiveness of the proposed method, three datasets and four methods are used for experiment comparison in this paper. The actual example indicate that the SVAE‐GRU method has the best effect on the degradation generation and prediction.
Author Xie, Guo
Hei, Xinhong
Shangguan, Anqi
Feng, Nan
Mu, Lingxia
Fei, Rong
Author_xml – sequence: 1
  givenname: Anqi
  orcidid: 0000-0003-2848-322X
  surname: Shangguan
  fullname: Shangguan, Anqi
  organization: School of Automation and Information Engineering Xi'an University of Technology Xi'an China
– sequence: 2
  givenname: Nan
  surname: Feng
  fullname: Feng, Nan
  organization: School of Intelligent Science and Technology Beijing University of Science and Technology Beijing China
– sequence: 3
  givenname: Lingxia
  surname: Mu
  fullname: Mu, Lingxia
  organization: School of Automation and Information Engineering Xi'an University of Technology Xi'an China
– sequence: 4
  givenname: Rong
  surname: Fei
  fullname: Fei, Rong
  organization: School of computer science and Engineering Xi'an University of Technology Xi'an China
– sequence: 5
  givenname: Xinhong
  surname: Hei
  fullname: Hei, Xinhong
  organization: School of computer science and Engineering Xi'an University of Technology Xi'an China
– sequence: 6
  givenname: Guo
  orcidid: 0000-0002-9948-453X
  surname: Xie
  fullname: Xie, Guo
  organization: School of Automation and Information Engineering Xi'an University of Technology Xi'an China
BookMark eNplkMtKw0AUhgepYFsFHyHgxk3q3DKXZSm1KgVBrdthkjlTUtIknUkX7nwEn9EnMW1d6eZc4P_Oz_lHaFA3NSB0TfCEYEzvdgEmjGl-hoYEa50SwdQADbHkKlWYyAs0inGDcS_WaoieXt-n8-_Pr8XLqq-5jeASB-tgne3Kpk7WUEM4jbZ2SRvAlcVx9U1I4tZWVRLttq0gXqJzb6sIV799jFb387fZQ7p8XjzOpsu0oFnWpdprnme5pko4SnNBnKDUS0adzIjVTHrQIAXW0kEhfaaZ4N5JS3muRM4zNkY3p7ttaHZ7iJ3ZNPtQ95aGKkmV5ryHxmhyUhWhiTGAN0XZHR_pgi0rQ7A55GX6vMwhrx64_QO0odza8PFf-gOk8247
CitedBy_id crossref_primary_10_1016_j_jfca_2025_107994
Cites_doi 10.1109/TR.2017.2765485
10.1109/TASE.2020.3035620
10.1016/j.knosys.2022.108919
10.1016/j.ins.2019.07.070
10.1016/j.ress.2018.10.002
10.1109/LSP.2020.2977498
10.1109/LSP.2004.840869
10.1016/j.epsr.2022.108462
10.1016/j.ress.2019.106631
10.1016/j.asr.2022.08.072.2022
10.1002/qre.2762
10.1016/j.ress.2022.108412
10.1016/j.ress.2022.108816
10.1016/j.ress.2021.107897
10.3390/rs13030464
10.1016/j.eswa.2023.119775
10.1109/TASLP.2020.3000593
10.1016/j.ress.2022.109078
10.1109/TMECH.2020.3043471
10.1016/j.apm.2020.03.018
10.1016/j.seta.2022.102807
10.1109/LGRS.2019.2913387
10.1109/TII.2020.3025204
10.1016/j.microrel.2017.07.005
10.1109/TNNLS.2020.2980749
10.1016/j.asoc.2022.109515
10.1016/j.ijhydene.2022.09.160
10.1002/qre.1489
10.1016/j.ress.2021.107446
10.1109/JIOT.2021.3052162
10.1109/JSEN.2021.3128562
10.1016/j.jmrt.2021.11.029
10.1016/j.ins.2020.04.042
10.1016/j.ress.2021.107738
10.1109/TII.2020.3046566
10.1109/TKDE.2021.3130595
10.1016/j.measurement.2023.112739
10.1109/TII.2019.2951622
10.1016/j.ins.2020.01.045
ContentType Journal Article
Copyright 2023 John Wiley & Sons Ltd.
Copyright_xml – notice: 2023 John Wiley & Sons Ltd.
DBID AAYXX
CITATION
7TB
8FD
FR3
DOI 10.1002/qre.3394
DatabaseName CrossRef
Mechanical & Transportation Engineering Abstracts
Technology Research Database
Engineering Research Database
DatabaseTitle CrossRef
Technology Research Database
Mechanical & Transportation Engineering Abstracts
Engineering Research Database
DatabaseTitleList Technology Research Database
CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1099-1638
EndPage 2868
ExternalDocumentID 10_1002_qre_3394
GroupedDBID .3N
.GA
.Y3
05W
0R~
10A
123
1L6
1OB
1OC
31~
33P
3SF
3WU
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
8WZ
930
A03
A6W
AAESR
AAEVG
AAHQN
AAMMB
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAYXX
AAZKR
ABCQN
ABCUV
ABEML
ABIJN
ABJNI
ABPVW
ACAHQ
ACBWZ
ACCZN
ACGFS
ACIWK
ACPOU
ACRPL
ACSCC
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADMGS
ADMLS
ADNMO
ADOZA
ADXAS
AEFGJ
AEIGN
AEIMD
AENEX
AEUYR
AEYWJ
AFBPY
AFFNX
AFFPM
AFGKR
AFWVQ
AFZJQ
AGHNM
AGQPQ
AGXDD
AGYGG
AHBTC
AIDQK
AIDYY
AIQQE
AITYG
AIURR
AJXKR
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALVPJ
AMBMR
AMYDB
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CITATION
CMOOK
CS3
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EBS
EJD
F00
F01
F04
FEDTE
G-S
G.N
GNP
GODZA
H.T
H.X
HBH
HF~
HGLYW
HHY
HVGLF
HZ~
IX1
J0M
JPC
KQQ
LATKE
LAW
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
M59
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
NNB
O66
O8X
O9-
P2P
P2W
P2X
P4D
PALCI
Q.N
Q11
QB0
QRW
R.K
RIWAO
RJQFR
RNS
ROL
RX1
RYL
SAMSI
SUPJJ
TN5
UB1
V2E
W8V
W99
WBKPD
WH7
WIH
WIK
WLBEL
WOHZO
WQJ
WXSBR
WYISQ
XG1
XPP
XV2
ZZTAW
~IA
~WT
7TB
8FD
ALUQN
FR3
ID FETCH-LOGICAL-c255t-9f94b5b9286d22b61d622f732d751a937fe9e76097dec7f59364fd7a24b86b453
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001003436600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0748-8017
IngestDate Fri Jul 25 12:17:19 EDT 2025
Tue Nov 18 21:21:10 EST 2025
Sat Nov 29 02:33:18 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c255t-9f94b5b9286d22b61d622f732d751a937fe9e76097dec7f59364fd7a24b86b453
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-9948-453X
0000-0003-2848-322X
PQID 2872894459
PQPubID 1016437
PageCount 18
ParticipantIDs proquest_journals_2872894459
crossref_citationtrail_10_1002_qre_3394
crossref_primary_10_1002_qre_3394
PublicationCentury 2000
PublicationDate 2023-11-00
20231101
PublicationDateYYYYMMDD 2023-11-01
PublicationDate_xml – month: 11
  year: 2023
  text: 2023-11-00
PublicationDecade 2020
PublicationPlace Bognor Regis
PublicationPlace_xml – name: Bognor Regis
PublicationTitle Quality and reliability engineering international
PublicationYear 2023
Publisher Wiley Subscription Services, Inc
Publisher_xml – name: Wiley Subscription Services, Inc
References e_1_2_8_29_1
e_1_2_8_24_1
e_1_2_8_25_1
e_1_2_8_26_1
e_1_2_8_27_1
e_1_2_8_3_1
e_1_2_8_2_1
e_1_2_8_5_1
e_1_2_8_4_1
e_1_2_8_7_1
e_1_2_8_6_1
e_1_2_8_9_1
e_1_2_8_8_1
e_1_2_8_20_1
e_1_2_8_43_1
e_1_2_8_21_1
e_1_2_8_22_1
e_1_2_8_23_1
e_1_2_8_44_1
e_1_2_8_41_1
e_1_2_8_40_1
e_1_2_8_17_1
e_1_2_8_18_1
e_1_2_8_39_1
e_1_2_8_19_1
e_1_2_8_13_1
e_1_2_8_36_1
e_1_2_8_14_1
e_1_2_8_35_1
e_1_2_8_15_1
Chawla N (e_1_2_8_16_1) 2011; 16
e_1_2_8_38_1
e_1_2_8_37_1
Freitas MA (e_1_2_8_42_1) 2010; 25
Kingma D P (e_1_2_8_28_1) 2014; 1050
e_1_2_8_32_1
e_1_2_8_10_1
e_1_2_8_31_1
e_1_2_8_11_1
e_1_2_8_34_1
e_1_2_8_12_1
e_1_2_8_33_1
e_1_2_8_30_1
References_xml – ident: e_1_2_8_39_1
  doi: 10.1109/TR.2017.2765485
– ident: e_1_2_8_33_1
  doi: 10.1109/TASE.2020.3035620
– volume: 16
  start-page: 321
  issue: 1
  year: 2011
  ident: e_1_2_8_16_1
  article-title: SMOTE: Synthetic minority oversampling technique
  publication-title: Artificial Intelligent
– volume: 1050
  start-page: 10
  year: 2014
  ident: e_1_2_8_28_1
  article-title: Auto‐Encoding Variational Bayes
  publication-title: Statistics
– ident: e_1_2_8_17_1
  doi: 10.1016/j.knosys.2022.108919
– ident: e_1_2_8_18_1
  doi: 10.1016/j.ins.2019.07.070
– ident: e_1_2_8_12_1
  doi: 10.1016/j.ress.2018.10.002
– ident: e_1_2_8_29_1
  doi: 10.1109/LSP.2020.2977498
– ident: e_1_2_8_24_1
  doi: 10.1109/LSP.2004.840869
– ident: e_1_2_8_13_1
  doi: 10.1016/j.epsr.2022.108462
– ident: e_1_2_8_7_1
  doi: 10.1016/j.ress.2019.106631
– ident: e_1_2_8_40_1
  doi: 10.1016/j.asr.2022.08.072.2022
– volume: 25
  start-page: 607
  issue: 5
  year: 2010
  ident: e_1_2_8_42_1
  article-title: Using degradation data to assess reliability: a case study on train wheel degradation
  publication-title: Inf Sci
– ident: e_1_2_8_25_1
  doi: 10.1002/qre.2762
– ident: e_1_2_8_11_1
  doi: 10.1016/j.ress.2022.108412
– ident: e_1_2_8_2_1
  doi: 10.1016/j.ress.2022.108816
– ident: e_1_2_8_3_1
  doi: 10.1016/j.ress.2021.107897
– ident: e_1_2_8_20_1
  doi: 10.3390/rs13030464
– ident: e_1_2_8_32_1
  doi: 10.1016/j.eswa.2023.119775
– ident: e_1_2_8_38_1
  doi: 10.1109/TASLP.2020.3000593
– ident: e_1_2_8_26_1
  doi: 10.1016/j.ress.2022.109078
– ident: e_1_2_8_5_1
  doi: 10.1109/TMECH.2020.3043471
– ident: e_1_2_8_6_1
  doi: 10.1016/j.apm.2020.03.018
– ident: e_1_2_8_15_1
  doi: 10.1016/j.seta.2022.102807
– ident: e_1_2_8_19_1
  doi: 10.1109/LGRS.2019.2913387
– ident: e_1_2_8_34_1
  doi: 10.1109/TII.2020.3025204
– ident: e_1_2_8_43_1
  doi: 10.1016/j.microrel.2017.07.005
– ident: e_1_2_8_37_1
  doi: 10.1109/TNNLS.2020.2980749
– ident: e_1_2_8_35_1
– ident: e_1_2_8_10_1
  doi: 10.1016/j.asoc.2022.109515
– ident: e_1_2_8_8_1
  doi: 10.1016/j.ijhydene.2022.09.160
– ident: e_1_2_8_23_1
  doi: 10.1002/qre.1489
– ident: e_1_2_8_9_1
  doi: 10.1016/j.ress.2021.107446
– ident: e_1_2_8_31_1
  doi: 10.1109/JIOT.2021.3052162
– ident: e_1_2_8_36_1
  doi: 10.1109/JSEN.2021.3128562
– ident: e_1_2_8_44_1
  doi: 10.1016/j.jmrt.2021.11.029
– ident: e_1_2_8_4_1
  doi: 10.1016/j.ins.2020.04.042
– ident: e_1_2_8_14_1
  doi: 10.1016/j.ress.2021.107738
– ident: e_1_2_8_21_1
  doi: 10.1109/TII.2020.3046566
– ident: e_1_2_8_22_1
  doi: 10.1109/TKDE.2021.3130595
– ident: e_1_2_8_27_1
  doi: 10.1016/j.measurement.2023.112739
– ident: e_1_2_8_30_1
  doi: 10.1109/TII.2019.2951622
– ident: e_1_2_8_41_1
  doi: 10.1016/j.ins.2020.01.045
SSID ssj0010098
Score 2.3511527
Snippet The degradation process analysis is the basis of the system reliability assessment. Too few degradation samples will affect the accuracy of the reliability...
SourceID proquest
crossref
SourceType Aggregation Database
Enrichment Source
Index Database
StartPage 2851
SubjectTerms Degradation
Effectiveness
Heterogeneity
Prediction models
Reliability analysis
System reliability
Title SVAE‐GRU‐based degradation generation and prediction for small samples
URI https://www.proquest.com/docview/2872894459
Volume 39
WOSCitedRecordID wos001003436600001&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1099-1638
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0010098
  issn: 0748-8017
  databaseCode: DRFUL
  dateStart: 19960101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtZ1Lb9QwEMetpeUAB8RT9AEyEhKHKrBx_DxW0IJQWaHSRb1FTuxUkZbQbnar5cZH4M6345Mwjp3HFg7lwCXKRk5W6_nvzNixf4PQcx27oMJEpDmDAYqmKtLMsIgUhlFjKGSoDWf2SEwm8vRUfRyNfrZ7YS5noqrkaqXO_6up4RoY222d_Qdzdw-FC3AORocjmB2O1zL8p8_7B90ShrfH0-7cBSyzZxwdwhdScuWTbVBA4AWYMu8WH9Zf3GvrWjt-cD1MYj13w4Ob5nZWetT3tz3bsw0bDEU309hN47jZ6bOlDtiCi7JPRL3LmfRa_bAMUwZnq1L37Uq_HDzE2zBdQZKwb6_3aoJKFxZ9lLXe6zpMqEsMh27ZM46C_MTQx8qAqLXho6_L80cs8GzZi7l9mSS-kPI6bvtKGOwWJ3qQM0nhztTdeQNtEsEUuMzNN8eH06PuJZVjsXrKq_9FLdt4TF6137qe7awH-yaDObmL7oShB973krmHRra6j24PgJQP0Hsnnl_ff4Bs4NgIBg8Eg3vBYDA-7gWDQTC4EQwOgnmIpocHJ6_fRaHaRpTDsHIRqULRjGUK-tMQkvHYcEIKkRAjWKwhiy2ssoKPlTA2F4WrBEkLIzShmeQZZckjtFF9rexjhHkWa5ZzqeI8oZmhemyt0DEfF5YrW8gt9KLtlTQPKHpXEWWWXu37LfSsa3nu8St_abPbdmwa_od1SqQgUlHK1PY1HrGDbvVa3UUbi_nSPkE388tFWc-fBrv_BqwIhVE
linkProvider Wiley-Blackwell
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=SVAE%E2%80%90GRU%E2%80%90based+degradation+generation+and+prediction+for+small+samples&rft.jtitle=Quality+and+reliability+engineering+international&rft.au=Shangguan%2C+Anqi&rft.au=Feng%2C+Nan&rft.au=Mu%2C+Lingxia&rft.au=Fei%2C+Rong&rft.date=2023-11-01&rft.issn=0748-8017&rft.eissn=1099-1638&rft.volume=39&rft.issue=7&rft.spage=2851&rft.epage=2868&rft_id=info:doi/10.1002%2Fqre.3394&rft.externalDBID=n%2Fa&rft.externalDocID=10_1002_qre_3394
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0748-8017&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0748-8017&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0748-8017&client=summon