An enhancement denoising autoencoder for rolling bearing fault diagnosis

•A novel data preprocessing method is proposed when there is not enough data for the model.•Adjust the regularization parameters appropriately as the number of layers changes.•Improve the parameter norm penalty by combining with elastic net regularization. Denoising autoencoders can automatically le...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Measurement : journal of the International Measurement Confederation Ročník 130; s. 448 - 454
Hlavní autori: Meng, Zong, Zhan, Xuyang, Li, Jing, Pan, Zuozhou
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.12.2018
Predmet:
ISSN:0263-2241, 1873-412X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract •A novel data preprocessing method is proposed when there is not enough data for the model.•Adjust the regularization parameters appropriately as the number of layers changes.•Improve the parameter norm penalty by combining with elastic net regularization. Denoising autoencoders can automatically learn in-depth features from complex data and extract concise expressions, which are used in fault diagnosis. However, they still have many drawbacks: (1) unsatisfactory results when the input data is not substantial; (2) difficulty in optimising the hyperparameter; (3) inability of existing regularisation methods to combine the advantages of L1 and L2 regularisation. To overcome the aforementioned challenges, here, a new data preprocessing method was proposed to obtain the training data. By reusing the data points between the adjacent samples, the fault identifying rate was significantly improved. Considering the different resilience of each layer after regularisation, the proposed method could alter the hyperparameter by changing the unit numbers of each layer. For a better sparse representation, the norm penalty combined L1 and L2 norm penalties, motivated by the elastic net. Comparison with a normal denoising autoencoder verified the superiority of the proposed method.
AbstractList •A novel data preprocessing method is proposed when there is not enough data for the model.•Adjust the regularization parameters appropriately as the number of layers changes.•Improve the parameter norm penalty by combining with elastic net regularization. Denoising autoencoders can automatically learn in-depth features from complex data and extract concise expressions, which are used in fault diagnosis. However, they still have many drawbacks: (1) unsatisfactory results when the input data is not substantial; (2) difficulty in optimising the hyperparameter; (3) inability of existing regularisation methods to combine the advantages of L1 and L2 regularisation. To overcome the aforementioned challenges, here, a new data preprocessing method was proposed to obtain the training data. By reusing the data points between the adjacent samples, the fault identifying rate was significantly improved. Considering the different resilience of each layer after regularisation, the proposed method could alter the hyperparameter by changing the unit numbers of each layer. For a better sparse representation, the norm penalty combined L1 and L2 norm penalties, motivated by the elastic net. Comparison with a normal denoising autoencoder verified the superiority of the proposed method.
Author Pan, Zuozhou
Zhan, Xuyang
Li, Jing
Meng, Zong
Author_xml – sequence: 1
  givenname: Zong
  surname: Meng
  fullname: Meng, Zong
  email: mzysu@ysu.edu.cn
– sequence: 2
  givenname: Xuyang
  orcidid: 0000-0002-5268-7399
  surname: Zhan
  fullname: Zhan, Xuyang
– sequence: 3
  givenname: Jing
  surname: Li
  fullname: Li, Jing
  email: lj@stumail.ysu.edu.cn
– sequence: 4
  givenname: Zuozhou
  surname: Pan
  fullname: Pan, Zuozhou
BookMark eNqNkNFKwzAUhoNMcJu-Q32A1pOkzdorGUOdMPBGwbuQJqczo0sk6QTf3nTzQrwaHPjhcP4PzjcjE-cdEnJLoaBAxd2u2KOKh4B7dEPBgNYFpKFwQaa0XvC8pOx9QqbABM8ZK-kVmcW4AwDBGzEl66XL0H0op4-EzKDzNlq3zdRh8Oi0Nxiyzocs-L4f9y2qMGanDn26t2rrfLTxmlx2qo9485tz8vb48Lpa55uXp-fVcpNrLmDIGWKpagEp0CxUVaFivGp0UzKKFZTGtLzVHQgUraLINbS1aBa0Kakuu8rwOWlOXB18jAE7-RnsXoVvSUGOSuRO_lEiRyUS0lBI3ft_XW0HNVjvhqBsfxZhdSJgevHLYpBR22QJjQ2oB2m8PYPyA05Gij4
CitedBy_id crossref_primary_10_1109_JIOT_2023_3307127
crossref_primary_10_1109_TNSE_2022_3174674
crossref_primary_10_1088_1361_6501_acb5b7
crossref_primary_10_1016_j_asoc_2022_108912
crossref_primary_10_1109_JSEN_2023_3236838
crossref_primary_10_1016_j_measurement_2022_112327
crossref_primary_10_3390_s20205734
crossref_primary_10_1016_j_cie_2023_109605
crossref_primary_10_1109_ACCESS_2021_3083646
crossref_primary_10_1016_j_ymssp_2021_108765
crossref_primary_10_1186_s40537_023_00684_w
crossref_primary_10_1016_j_measurement_2019_107232
crossref_primary_10_1016_j_eswa_2022_119479
crossref_primary_10_1080_21642583_2021_1992684
crossref_primary_10_1016_j_measurement_2021_110017
crossref_primary_10_1016_j_measurement_2020_108333
crossref_primary_10_1016_j_ymssp_2023_110967
crossref_primary_10_1088_1361_6501_ab8df9
crossref_primary_10_1007_s40799_021_00478_w
crossref_primary_10_1088_1361_6501_adf244
crossref_primary_10_1109_TIM_2025_3545169
crossref_primary_10_1016_j_measurement_2020_107929
crossref_primary_10_1016_j_measurement_2019_106893
crossref_primary_10_1088_1361_6501_ad24ba
crossref_primary_10_1093_jcde_qwad031
crossref_primary_10_1109_JSEN_2024_3362402
crossref_primary_10_1016_j_ymssp_2019_106587
crossref_primary_10_1088_1361_6501_ab3a59
crossref_primary_10_3390_app10186359
crossref_primary_10_3390_rs13091761
crossref_primary_10_1007_s10845_020_01657_z
crossref_primary_10_1016_j_ymssp_2022_109454
crossref_primary_10_1016_j_measurement_2019_06_029
crossref_primary_10_1016_j_measurement_2019_03_079
crossref_primary_10_1088_1361_6501_ad3b29
crossref_primary_10_1088_1361_6501_abf3fb
crossref_primary_10_1016_j_ress_2020_107050
crossref_primary_10_1088_1361_6501_abd900
crossref_primary_10_1016_j_measurement_2020_108908
crossref_primary_10_3390_rs14030682
crossref_primary_10_1016_j_isatra_2020_02_031
crossref_primary_10_1016_j_ymssp_2021_108709
crossref_primary_10_32604_cmc_2024_049665
crossref_primary_10_1016_j_eswa_2024_126109
crossref_primary_10_1088_1361_6501_ad4732
crossref_primary_10_1109_JSEN_2024_3462540
crossref_primary_10_1007_s11071_021_06393_4
crossref_primary_10_1016_j_measurement_2021_109452
crossref_primary_10_1016_j_compind_2018_12_016
crossref_primary_10_1016_j_measurement_2020_107741
crossref_primary_10_1016_j_engappai_2024_109020
crossref_primary_10_1121_1_5128327
crossref_primary_10_1016_j_isatra_2021_06_005
crossref_primary_10_1016_j_neucom_2022_06_066
crossref_primary_10_1016_j_measurement_2020_107589
crossref_primary_10_1016_j_rineng_2025_105488
crossref_primary_10_1016_j_measurement_2019_02_072
crossref_primary_10_1016_j_measurement_2020_107748
crossref_primary_10_1109_ACCESS_2019_2926234
crossref_primary_10_1016_j_eswa_2022_117716
crossref_primary_10_1109_TIM_2019_2902806
crossref_primary_10_3390_machines13090807
crossref_primary_10_3390_s23177567
crossref_primary_10_1016_j_ymssp_2020_106752
crossref_primary_10_3390_machines12110792
crossref_primary_10_1016_j_isatra_2021_10_026
crossref_primary_10_1108_ILT_11_2019_0496
crossref_primary_10_1016_j_measurement_2019_106909
crossref_primary_10_1016_j_apacoust_2020_107903
crossref_primary_10_1016_j_engappai_2023_107690
crossref_primary_10_1016_j_ymssp_2022_109789
crossref_primary_10_1007_s00170_021_08427_y
crossref_primary_10_1155_2021_9942249
crossref_primary_10_1109_TIM_2023_3341134
crossref_primary_10_1177_10775463231164445
crossref_primary_10_1063_1_5136269
crossref_primary_10_1109_TIA_2022_3223637
crossref_primary_10_1007_s10845_023_02303_0
crossref_primary_10_1016_j_ymssp_2025_112894
crossref_primary_10_1016_j_isatra_2020_02_010
crossref_primary_10_23919_JSEE_2022_000023
crossref_primary_10_3390_app11041564
crossref_primary_10_1016_j_mechmachtheory_2020_103786
crossref_primary_10_1016_j_aei_2024_102959
crossref_primary_10_1016_j_compeleceng_2023_108745
crossref_primary_10_1016_j_measurement_2021_109750
crossref_primary_10_3390_electronics11244110
crossref_primary_10_1016_j_engfailanal_2022_106515
crossref_primary_10_3390_machines13090819
crossref_primary_10_3390_electronics12163515
crossref_primary_10_1007_s11760_021_01939_w
crossref_primary_10_1007_s11571_020_09642_1
crossref_primary_10_1016_j_trac_2024_117578
crossref_primary_10_1088_1361_6501_ad2e69
crossref_primary_10_3390_s19040758
crossref_primary_10_1088_1361_6501_ac18d2
crossref_primary_10_1109_ACCESS_2020_3041735
crossref_primary_10_1016_j_engappai_2021_104279
crossref_primary_10_1016_j_apacoust_2022_109188
crossref_primary_10_1109_ACCESS_2019_2923417
crossref_primary_10_1088_1361_6501_ac9854
crossref_primary_10_1088_1361_6501_ab55f8
crossref_primary_10_1016_j_jsv_2019_03_023
crossref_primary_10_1016_j_measurement_2020_108153
crossref_primary_10_3390_en15082796
crossref_primary_10_1016_j_measurement_2022_111943
crossref_primary_10_1016_j_neucom_2020_10_003
crossref_primary_10_1016_j_measurement_2021_109186
crossref_primary_10_3390_machines11111029
crossref_primary_10_1016_j_ymssp_2021_108697
crossref_primary_10_1109_ACCESS_2021_3089251
crossref_primary_10_1016_j_asoc_2025_112785
crossref_primary_10_1109_JSEN_2019_2899396
crossref_primary_10_1016_j_measurement_2019_107419
crossref_primary_10_1007_s42417_022_00757_9
crossref_primary_10_1007_s00521_022_07224_2
crossref_primary_10_1016_j_measurement_2024_115199
crossref_primary_10_1177_1748006X221108598
crossref_primary_10_1007_s13198_022_01843_7
crossref_primary_10_1088_1361_6501_ac8893
crossref_primary_10_1145_3427912
crossref_primary_10_1155_2020_9857839
crossref_primary_10_1007_s10489_021_03107_6
crossref_primary_10_1088_1361_6501_abcefb
crossref_primary_10_1016_j_engappai_2023_105970
crossref_primary_10_1016_j_measurement_2022_111577
crossref_primary_10_1016_j_jmsy_2022_11_012
crossref_primary_10_1109_ACCESS_2019_2914731
crossref_primary_10_1016_j_anucene_2022_109267
crossref_primary_10_1177_01423312231171664
crossref_primary_10_1109_ACCESS_2019_2938227
crossref_primary_10_1016_j_measurement_2023_112709
crossref_primary_10_1088_1361_6501_aba4da
crossref_primary_10_1016_j_measurement_2020_108636
crossref_primary_10_1016_j_measurement_2021_109885
crossref_primary_10_1016_j_measurement_2020_107667
crossref_primary_10_1109_TIM_2023_3348910
crossref_primary_10_1016_j_measurement_2020_108235
crossref_primary_10_1016_j_ress_2021_108017
crossref_primary_10_1016_j_rineng_2024_103420
crossref_primary_10_1007_s11071_025_11469_6
crossref_primary_10_1016_j_measurement_2021_110596
crossref_primary_10_1016_j_compind_2019_04_013
crossref_primary_10_1049_elp2_12063
crossref_primary_10_1016_j_apacoust_2022_108703
crossref_primary_10_1016_j_measurement_2020_107709
crossref_primary_10_1111_exsy_12819
crossref_primary_10_1177_14759217241305159
crossref_primary_10_1108_AEAT_10_2020_0234
crossref_primary_10_1155_2020_8891905
crossref_primary_10_1109_JSEN_2023_3270880
crossref_primary_10_3390_s22197249
crossref_primary_10_3390_s20010223
crossref_primary_10_1109_JSEN_2019_2911299
crossref_primary_10_3390_s23063157
crossref_primary_10_1016_j_measurement_2020_108371
crossref_primary_10_1016_j_measurement_2020_108523
crossref_primary_10_1108_AA_09_2021_0123
crossref_primary_10_3390_math10213953
crossref_primary_10_1007_s10207_025_01005_3
crossref_primary_10_1016_j_neucom_2021_04_122
crossref_primary_10_1016_j_ymssp_2020_107095
crossref_primary_10_1016_j_asoc_2023_110669
crossref_primary_10_3390_e21020115
crossref_primary_10_1007_s10462_023_10513_4
crossref_primary_10_1016_j_measurement_2021_110460
crossref_primary_10_1109_TIM_2023_3251399
crossref_primary_10_3390_machines11020185
crossref_primary_10_1016_j_asoc_2022_109785
Cites_doi 10.1109/TIE.2016.2519325
10.1126/science.1127647
10.21437/Interspeech.2013-432
10.1109/ICPHM.2016.7542865
10.1016/j.eswa.2013.12.026
10.1016/j.ins.2015.09.048
10.1038/nature14539
10.1016/j.neunet.2014.09.003
10.1016/j.ymssp.2011.09.011
10.1016/j.ymssp.2010.07.013
10.1016/j.jco.2011.01.003
10.1016/j.measurement.2016.04.007
10.1016/j.neucom.2015.11.044
10.1016/j.knosys.2015.06.017
10.1016/j.measurement.2013.11.012
10.1016/j.sigpro.2014.11.003
10.1016/j.ymssp.2015.10.025
10.1016/j.sigpro.2016.07.028
10.1016/j.ymssp.2010.07.017
10.1109/JSTARS.2016.2621011
10.1016/j.jsv.2016.09.018
10.1016/j.ymssp.2017.03.034
10.1016/j.jco.2015.07.002
ContentType Journal Article
Copyright 2018 Elsevier Ltd
Copyright_xml – notice: 2018 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.measurement.2018.08.010
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
EISSN 1873-412X
EndPage 454
ExternalDocumentID 10_1016_j_measurement_2018_08_010
S0263224118307474
GroupedDBID --K
--M
.~1
0R~
1B1
1~.
1~5
29M
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
ABFNM
ABFRF
ABJNI
ABMAC
ABNEU
ABXDB
ABYKQ
ACDAQ
ACFVG
ACGFO
ACGFS
ACIWK
ACNNM
ACRLP
ADBBV
ADEZE
ADTZH
AEBSH
AECPX
AEFWE
AEGXH
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AIEXJ
AIKHN
AITUG
AIVDX
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GS5
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LY7
M41
MO0
N9A
O-L
O9-
OAUVE
OGIMB
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SDF
SDG
SES
SET
SEW
SPC
SPCBC
SPD
SSQ
SST
SSZ
T5K
WUQ
XPP
ZMT
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ACLOT
ACVFH
ADCNI
AEIPS
AEUPX
AFJKZ
AFPUW
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c360t-2ee4a860ee4ed7a55ea2359c9421e504ddb3bcf06e6ba1e3c0b86971941c4f5d3
ISICitedReferencesCount 195
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000446464400042&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0263-2241
IngestDate Tue Nov 18 21:45:07 EST 2025
Sat Nov 29 07:20:45 EST 2025
Fri Feb 23 02:47:33 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Fault diagnosis
Denoising autoencoder
Hyperparameter
Elastic net
Regularisation
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c360t-2ee4a860ee4ed7a55ea2359c9421e504ddb3bcf06e6ba1e3c0b86971941c4f5d3
ORCID 0000-0002-5268-7399
PageCount 7
ParticipantIDs crossref_primary_10_1016_j_measurement_2018_08_010
crossref_citationtrail_10_1016_j_measurement_2018_08_010
elsevier_sciencedirect_doi_10_1016_j_measurement_2018_08_010
PublicationCentury 2000
PublicationDate 2018-12-01
PublicationDateYYYYMMDD 2018-12-01
PublicationDate_xml – month: 12
  year: 2018
  text: 2018-12-01
  day: 01
PublicationDecade 2010
PublicationTitle Measurement : journal of the International Measurement Confederation
PublicationYear 2018
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Jia, Lei, Lin, Zhou, Lu (b0075) 2016; 72–73
Barad, Ramaiah, Giridhar, Krishnaiah (b0025) 2012; 27
De Vito, Umanità, Villa (b0120) 2011; 27
R. Memisevic, D. Krueger, Zero-bias autoencoders and the benefits of co-adapting features, in: Proceedings of International Conference on Learning Representations, 2015, pp. 1–11.
LeCun, Bengio, Hinton (b0045) 2015; 521
N. Jaitly, G.E. Hinton, “Using an autoencoder with deformable templates to discover features for automated speech recognition.” in INTERSPEECH, Lyon, France, 2013,pp.1737–1740.
Shao, Jiang, Zhao, Fu (b0065) 2017; 95
Liu, He, Liu, Liu (b0015) 2016; 385
Lu, Wang, Qin (b0100) 2017; 130
Su, Liu, Xu, Li (b0040) 2015; 112
Wang, Chen (b0020) 2011; 511–518
Tran, AlThobiani, Ball (b0055) 2014; 41
Schmidhuber (b0145) 2015; 61
Worden, Staszewski, Hensman (b0035) 2011; 25
Hinton, Salakhutdinov (b0110) 2006; 313
Zabalza, Ren, Zheng, Zhao, Qing (b0090) 2016; 185
Bengio, Courville (b0150) 2013; 35
Zhang, Wang, Chen (b0030) 2015; 89
Sun, Shao, Zhao, Yan, Zhang (b0135) 2016; 89
Randall, Antoni (b0005) 2011; 25
Jia, Lei, Guo, Lin, Xing (b0060) 2017; 000
Rosa, Yu (b0140) 2016; 364–365
Lei, Jia, Lin (b0155) 2016; 63
Erhan, Bengio, Courville, Manzagol, Vincent, Bengio (b0105) 2010; 11
Shen, Han, Braverman (b0130) 2016; 32
R. Thirukovalluru, S. Dixit, R.K. Sevakula, N.K. Verma, A. Salour, Generating feature sets for fault diagnosis using denoising stacked auto-encoder, in: Proceedings of IEEE Conference on Prognostics and Health Management, 2016, pp. 1–7.
Ceng, Ansari (b0125) 2013
Lei, Lin, Zuo, He (b0010) 2014; 48
Li, Du, Samat, Meng, Che (b0080) 2017; 10
Deng (b0050) 2014; 3
Hinton, Zemel, Autoencoders (b0085) 1994
Tran (10.1016/j.measurement.2018.08.010_b0055) 2014; 41
Deng (10.1016/j.measurement.2018.08.010_b0050) 2014; 3
Sun (10.1016/j.measurement.2018.08.010_b0135) 2016; 89
Zabalza (10.1016/j.measurement.2018.08.010_b0090) 2016; 185
Zhang (10.1016/j.measurement.2018.08.010_b0030) 2015; 89
Ceng (10.1016/j.measurement.2018.08.010_b0125) 2013
Hinton (10.1016/j.measurement.2018.08.010_b0110) 2006; 313
LeCun (10.1016/j.measurement.2018.08.010_b0045) 2015; 521
Liu (10.1016/j.measurement.2018.08.010_b0015) 2016; 385
Jia (10.1016/j.measurement.2018.08.010_b0060) 2017; 000
Hinton (10.1016/j.measurement.2018.08.010_b0085) 1994
10.1016/j.measurement.2018.08.010_b0095
10.1016/j.measurement.2018.08.010_b0070
Jia (10.1016/j.measurement.2018.08.010_b0075) 2016; 72–73
Erhan (10.1016/j.measurement.2018.08.010_b0105) 2010; 11
Lei (10.1016/j.measurement.2018.08.010_b0155) 2016; 63
Barad (10.1016/j.measurement.2018.08.010_b0025) 2012; 27
Worden (10.1016/j.measurement.2018.08.010_b0035) 2011; 25
Shao (10.1016/j.measurement.2018.08.010_b0065) 2017; 95
De Vito (10.1016/j.measurement.2018.08.010_b0120) 2011; 27
Shen (10.1016/j.measurement.2018.08.010_b0130) 2016; 32
Schmidhuber (10.1016/j.measurement.2018.08.010_b0145) 2015; 61
Su (10.1016/j.measurement.2018.08.010_b0040) 2015; 112
Randall (10.1016/j.measurement.2018.08.010_b0005) 2011; 25
10.1016/j.measurement.2018.08.010_b0115
Li (10.1016/j.measurement.2018.08.010_b0080) 2017; 10
Rosa (10.1016/j.measurement.2018.08.010_b0140) 2016; 364–365
Lei (10.1016/j.measurement.2018.08.010_b0010) 2014; 48
Lu (10.1016/j.measurement.2018.08.010_b0100) 2017; 130
Bengio (10.1016/j.measurement.2018.08.010_b0150) 2013; 35
Wang (10.1016/j.measurement.2018.08.010_b0020) 2011; 511–518
References_xml – volume: 185
  start-page: 1
  year: 2016
  end-page: 10
  ident: b0090
  article-title: Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging
  publication-title: Neurocomputing
– volume: 27
  start-page: 189
  year: 2011
  end-page: 203
  ident: b0120
  article-title: A consistent algorithm to solve Lasso, elastic-net and Tikhonov regularization
  publication-title: J. Complexity.
– reference: R. Thirukovalluru, S. Dixit, R.K. Sevakula, N.K. Verma, A. Salour, Generating feature sets for fault diagnosis using denoising stacked auto-encoder, in: Proceedings of IEEE Conference on Prognostics and Health Management, 2016, pp. 1–7.
– volume: 521
  start-page: 436
  year: 2015
  end-page: 444
  ident: b0045
  article-title: Review: deep learning
  publication-title: Nature
– volume: 72–73
  start-page: 303
  year: 2016
  end-page: 315
  ident: b0075
  article-title: Deep neural network: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data
  publication-title: Meth. Syst. Signal Process.
– start-page: 3
  year: 1994
  ident: b0085
  article-title: minimum description length, and Helmholtz free energy
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 000
  start-page: 1
  year: 2017
  end-page: 10
  ident: b0060
  article-title: A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines
  publication-title: Neurocomputing
– volume: 511–518
  year: 2011
  ident: b0020
  article-title: Intelligent diagnosis method for rolling element bearing faults using possibility theory and neural network
  publication-title: Comput. Ind. Eng.
– volume: 95
  start-page: 187
  year: 2017
  end-page: 204
  ident: b0065
  article-title: A novel deep autoencoder feature learning method for rotating machinery fault diagnosis
  publication-title: Meth. Syst. Signal Process.
– volume: 41
  start-page: 4113
  year: 2014
  end-page: 4122
  ident: b0055
  article-title: An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks
  publication-title: Expert Syst. Appl.
– volume: 48
  start-page: 292
  year: 2014
  end-page: 305
  ident: b0010
  article-title: Condition monitoring and fault diagnosis of planetary gearboxes: a review
  publication-title: Measurement
– volume: 313
  start-page: 504
  year: 2006
  end-page: 507
  ident: b0110
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
– reference: R. Memisevic, D. Krueger, Zero-bias autoencoders and the benefits of co-adapting features, in: Proceedings of International Conference on Learning Representations, 2015, pp. 1–11.
– start-page: 10
  year: 2013
  end-page: 26
  ident: b0125
  article-title: and Ching-Feng Wen, Multi-step implicit iterative methods with regularization for minimization problems and fixed point problems
  publication-title: J. Inequalities Appl.
– volume: 35
  start-page: 1798
  year: 2013
  end-page: 1828
  ident: b0150
  article-title: Representation learning: a review and new perspectives
  publication-title: IEEE Trans. Software Eng.
– volume: 130
  start-page: 377
  year: 2017
  end-page: 388
  ident: b0100
  article-title: J, Ma, Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification
  publication-title: Signal Process.
– volume: 25
  start-page: 4
  year: 2011
  end-page: 111
  ident: b0035
  article-title: Natural computing for mechanical systems research: a tutorial overview
  publication-title: Mech. Syst. Signal Process.
– volume: 27
  start-page: 729
  year: 2012
  end-page: 742
  ident: b0025
  article-title: Neural network approach for a combined performance and mechanical health monitoring of a gas turbine engine
  publication-title: Mech. Syst. Signal Process.
– volume: 32
  start-page: 20
  year: 2016
  end-page: 39
  ident: b0130
  article-title: Stability of the elastic net estimator
  publication-title: J. Complexity
– volume: 89
  start-page: 171
  year: 2016
  end-page: 178
  ident: b0135
  article-title: A sparse auto-encoder-based deep neural network approach for induction motor faults classification
  publication-title: Measurement
– volume: 63
  start-page: 3137
  year: 2016
  end-page: 3147
  ident: b0155
  article-title: An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data
  publication-title: IEEE Trans. Industry. Electron.
– volume: 112
  start-page: 43
  year: 2015
  end-page: 52
  ident: b0040
  article-title: Sparse auto-encoder based feature learning for human body detection in depth image
  publication-title: Signal Process.
– volume: 25
  start-page: 485
  year: 2011
  end-page: 520
  ident: b0005
  article-title: Rolling element bearing diagnostics—a tutorial
  publication-title: Mech. Syst. Signal Process.
– volume: 364–365
  start-page: 197
  year: 2016
  end-page: 212
  ident: b0140
  article-title: Randomized algorithms for nonlinear system identification with deep learning modification
  publication-title: Inf. Sci.
– volume: 89
  start-page: 56
  year: 2015
  end-page: 85
  ident: b0030
  article-title: Intelligent fault diagnosis of roller bearings with multivariable ensemble-based incremental support vector machine
  publication-title: Knowl.-Based Syst.
– volume: 3
  year: 2014
  ident: b0050
  article-title: A tutorial survey of architectures, algorithms, and applications for deep learning
  publication-title: APSIPA Trans. Signal Inf. Process.
– reference: N. Jaitly, G.E. Hinton, “Using an autoencoder with deformable templates to discover features for automated speech recognition.” in INTERSPEECH, Lyon, France, 2013,pp.1737–1740.
– volume: 385
  start-page: 389
  year: 2016
  end-page: 401
  ident: b0015
  article-title: Feature fusion using kernel joint approximate diagonalization of eigen-matrices for rolling bearing fault identification
  publication-title: J. Sound Vib.
– volume: 11
  start-page: 625
  year: 2010
  end-page: 660
  ident: b0105
  article-title: Why does unsupervised pre-training help deep learning?
  publication-title: J. Mach. Learn. Res.
– volume: 10
  start-page: 1068
  year: 2017
  end-page: 1081
  ident: b0080
  article-title: Mid-level feature representation via sparse autoencoder for remotely sensed scene classification
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
– volume: 61
  start-page: 85
  year: 2015
  end-page: 117
  ident: b0145
  article-title: Deep learning in neural networks: an overview
  publication-title: Neural Networks
– volume: 63
  start-page: 3137
  year: 2016
  ident: 10.1016/j.measurement.2018.08.010_b0155
  article-title: An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data
  publication-title: IEEE Trans. Industry. Electron.
  doi: 10.1109/TIE.2016.2519325
– start-page: 10
  year: 2013
  ident: 10.1016/j.measurement.2018.08.010_b0125
  article-title: and Ching-Feng Wen, Multi-step implicit iterative methods with regularization for minimization problems and fixed point problems
  publication-title: J. Inequalities Appl.
– volume: 313
  start-page: 504
  year: 2006
  ident: 10.1016/j.measurement.2018.08.010_b0110
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
  doi: 10.1126/science.1127647
– volume: 000
  start-page: 1
  year: 2017
  ident: 10.1016/j.measurement.2018.08.010_b0060
  article-title: A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines
  publication-title: Neurocomputing
– ident: 10.1016/j.measurement.2018.08.010_b0070
  doi: 10.21437/Interspeech.2013-432
– ident: 10.1016/j.measurement.2018.08.010_b0115
– ident: 10.1016/j.measurement.2018.08.010_b0095
  doi: 10.1109/ICPHM.2016.7542865
– volume: 41
  start-page: 4113
  year: 2014
  ident: 10.1016/j.measurement.2018.08.010_b0055
  article-title: An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2013.12.026
– volume: 364–365
  start-page: 197
  year: 2016
  ident: 10.1016/j.measurement.2018.08.010_b0140
  article-title: Randomized algorithms for nonlinear system identification with deep learning modification
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2015.09.048
– volume: 35
  start-page: 1798
  year: 2013
  ident: 10.1016/j.measurement.2018.08.010_b0150
  article-title: Representation learning: a review and new perspectives
  publication-title: IEEE Trans. Software Eng.
– volume: 11
  start-page: 625
  year: 2010
  ident: 10.1016/j.measurement.2018.08.010_b0105
  article-title: Why does unsupervised pre-training help deep learning?
  publication-title: J. Mach. Learn. Res.
– volume: 521
  start-page: 436
  year: 2015
  ident: 10.1016/j.measurement.2018.08.010_b0045
  article-title: Review: deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– start-page: 3
  year: 1994
  ident: 10.1016/j.measurement.2018.08.010_b0085
  article-title: minimum description length, and Helmholtz free energy
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 61
  start-page: 85
  year: 2015
  ident: 10.1016/j.measurement.2018.08.010_b0145
  article-title: Deep learning in neural networks: an overview
  publication-title: Neural Networks
  doi: 10.1016/j.neunet.2014.09.003
– volume: 27
  start-page: 729
  year: 2012
  ident: 10.1016/j.measurement.2018.08.010_b0025
  article-title: Neural network approach for a combined performance and mechanical health monitoring of a gas turbine engine
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2011.09.011
– volume: 25
  start-page: 4
  year: 2011
  ident: 10.1016/j.measurement.2018.08.010_b0035
  article-title: Natural computing for mechanical systems research: a tutorial overview
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2010.07.013
– volume: 27
  start-page: 189
  year: 2011
  ident: 10.1016/j.measurement.2018.08.010_b0120
  article-title: A consistent algorithm to solve Lasso, elastic-net and Tikhonov regularization
  publication-title: J. Complexity.
  doi: 10.1016/j.jco.2011.01.003
– volume: 3
  year: 2014
  ident: 10.1016/j.measurement.2018.08.010_b0050
  article-title: A tutorial survey of architectures, algorithms, and applications for deep learning
  publication-title: APSIPA Trans. Signal Inf. Process.
– volume: 89
  start-page: 171
  year: 2016
  ident: 10.1016/j.measurement.2018.08.010_b0135
  article-title: A sparse auto-encoder-based deep neural network approach for induction motor faults classification
  publication-title: Measurement
  doi: 10.1016/j.measurement.2016.04.007
– volume: 185
  start-page: 1
  year: 2016
  ident: 10.1016/j.measurement.2018.08.010_b0090
  article-title: Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.11.044
– volume: 89
  start-page: 56
  year: 2015
  ident: 10.1016/j.measurement.2018.08.010_b0030
  article-title: Intelligent fault diagnosis of roller bearings with multivariable ensemble-based incremental support vector machine
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2015.06.017
– volume: 48
  start-page: 292
  year: 2014
  ident: 10.1016/j.measurement.2018.08.010_b0010
  article-title: Condition monitoring and fault diagnosis of planetary gearboxes: a review
  publication-title: Measurement
  doi: 10.1016/j.measurement.2013.11.012
– volume: 112
  start-page: 43
  year: 2015
  ident: 10.1016/j.measurement.2018.08.010_b0040
  article-title: Sparse auto-encoder based feature learning for human body detection in depth image
  publication-title: Signal Process.
  doi: 10.1016/j.sigpro.2014.11.003
– volume: 511–518
  year: 2011
  ident: 10.1016/j.measurement.2018.08.010_b0020
  article-title: Intelligent diagnosis method for rolling element bearing faults using possibility theory and neural network
  publication-title: Comput. Ind. Eng.
– volume: 72–73
  start-page: 303
  year: 2016
  ident: 10.1016/j.measurement.2018.08.010_b0075
  article-title: Deep neural network: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data
  publication-title: Meth. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2015.10.025
– volume: 130
  start-page: 377
  year: 2017
  ident: 10.1016/j.measurement.2018.08.010_b0100
  article-title: J, Ma, Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification
  publication-title: Signal Process.
  doi: 10.1016/j.sigpro.2016.07.028
– volume: 25
  start-page: 485
  year: 2011
  ident: 10.1016/j.measurement.2018.08.010_b0005
  article-title: Rolling element bearing diagnostics—a tutorial
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2010.07.017
– volume: 10
  start-page: 1068
  year: 2017
  ident: 10.1016/j.measurement.2018.08.010_b0080
  article-title: Mid-level feature representation via sparse autoencoder for remotely sensed scene classification
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
  doi: 10.1109/JSTARS.2016.2621011
– volume: 385
  start-page: 389
  year: 2016
  ident: 10.1016/j.measurement.2018.08.010_b0015
  article-title: Feature fusion using kernel joint approximate diagonalization of eigen-matrices for rolling bearing fault identification
  publication-title: J. Sound Vib.
  doi: 10.1016/j.jsv.2016.09.018
– volume: 95
  start-page: 187
  year: 2017
  ident: 10.1016/j.measurement.2018.08.010_b0065
  article-title: A novel deep autoencoder feature learning method for rotating machinery fault diagnosis
  publication-title: Meth. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2017.03.034
– volume: 32
  start-page: 20
  year: 2016
  ident: 10.1016/j.measurement.2018.08.010_b0130
  article-title: Stability of the elastic net estimator
  publication-title: J. Complexity
  doi: 10.1016/j.jco.2015.07.002
SSID ssj0006396
Score 2.593616
Snippet •A novel data preprocessing method is proposed when there is not enough data for the model.•Adjust the regularization parameters appropriately as the number of...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 448
SubjectTerms Denoising autoencoder
Elastic net
Fault diagnosis
Hyperparameter
Regularisation
Title An enhancement denoising autoencoder for rolling bearing fault diagnosis
URI https://dx.doi.org/10.1016/j.measurement.2018.08.010
Volume 130
WOSCitedRecordID wos000446464400042&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect database
  customDbUrl:
  eissn: 1873-412X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0006396
  issn: 0263-2241
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1ba9swFBah3Ub3MLZuY90NDfY2PHyRZQn6EkZHV7bShw7CXowsyzQltUtil7b_pv-0Rxfb6i60G-zFCQdJiX2-HJ0cffqE0HsWkkqGZRwkokwDUiZpwAvOAlESGlWMU5FJc9hEtr_PZjN-MJlc9XthzhZZXbPzc376X10NNnC23jr7F-4eBgUDvAenwxXcDtc7OX5af1D1kXamWeeHuNLMTUFAdG2jZSu1eoQmFy6dHncBT8DwKUW3aHUxVnPv5is_bf02VhJNDcHTmxjZl31Z0W9sNhRqcU9_vV8zac2iSOOmTVe41rZZdyFG61fDNdibj5YD2-xH11weNZ1fs4iYx_-woS2mSaCThxtx2C3Q2EhKrACnm5SJVZr-Jd7b0sPxx5PxzjRdjxlZVseXvaGx_dPcNzASe7Lbce4Nleuhcn1Mp97Etx5nKYfAuT79sjPbG6Z7SPGoLeTZW3qA3o0kwj98r98nQV5ic_gYPXL_SPDUIukJmqh6Ez30dCo30X3DE5arp2h3WmMPXXhAF_bQhQFd2KELO3Rhgy48oOsZ-v555_DTbuAO4whkQsM2iJUigtEQXlSZiTRVIk5SLjmJI5WGpCyLpJBVSBUtRKQSGRaM8iziJJKkSsvkOVqrm1q9QJjGkPeKrIKWRq-O80woiAtMwiBFybYQ659OLp1SvT4wZZHf6qUtFA9dT61cy106bfcuyF3eafPJHGB2e_eX__KZr9DG-MN4jdbaZafeoHvyrJ2vlm8dxq4Bgn6wqg
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=An+enhancement+denoising+autoencoder+for+rolling+bearing+fault+diagnosis&rft.jtitle=Measurement+%3A+journal+of+the+International+Measurement+Confederation&rft.au=Meng%2C+Zong&rft.au=Zhan%2C+Xuyang&rft.au=Li%2C+Jing&rft.au=Pan%2C+Zuozhou&rft.date=2018-12-01&rft.issn=0263-2241&rft.volume=130&rft.spage=448&rft.epage=454&rft_id=info:doi/10.1016%2Fj.measurement.2018.08.010&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_measurement_2018_08_010
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0263-2241&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0263-2241&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0263-2241&client=summon