Wind Turbine Fault Detection Using a Denoising Autoencoder With Temporal Information

Data-driven approaches have gained increasing interests in the fault detection of wind turbines (WTs) due to the difficulty in system modeling and the availability of sensor data. However, the nonlinearity of WTs, uncertainty of disturbances and measurement noise, and temporal dependence in time-ser...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE/ASME transactions on mechatronics Ročník 23; číslo 1; s. 89 - 100
Hlavní autoři:	Jiang, Guoqian, Xie, Ping, He, Haibo, Yan, Jun
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	IEEE 01.02.2018
Témata:	Complex mechatronics Correlation denoising autoencoder (DAE) Fault detection Mechatronics Monitoring multivariate data driven Noise reduction Robustness Temperature measurement temporal information wind turbines (WTs)
ISSN:	1083-4435, 1941-014X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Data-driven approaches have gained increasing interests in the fault detection of wind turbines (WTs) due to the difficulty in system modeling and the availability of sensor data. However, the nonlinearity of WTs, uncertainty of disturbances and measurement noise, and temporal dependence in time-series data still pose grand challenges to effective fault detection. To this end, this paper proposes a new fault detector based on a recently developed unsupervised learning method, denoising autoencoder (DAE), which offers the learning of robust nonlinear representations from data against noise and input fluctuation. A DAE is used to build a robust multivariate reconstruction model on raw time-series data from multiple sensors, and then, the reconstruction error of the DAE trained with normal data is analyzed for fault detection. In addition, we apply the sliding-window technique to consider temporal information inherent in time-series data by including the current and past information within a small time window. A key advantage of the proposed approach is the ability to capture the nonlinear correlations among multiple sensor variables and the temporal dependence of each sensor variable simultaneously, which significantly enhanced the fault detection performance. Simulated data from a generic WT benchmark and field supervisory control and data acquisition data from a real wind farm are used to evaluate the proposed approach. The results of two case studies demonstrate the effectiveness and advantages of our proposed approach.
AbstractList	Data-driven approaches have gained increasing interests in the fault detection of wind turbines (WTs) due to the difficulty in system modeling and the availability of sensor data. However, the nonlinearity of WTs, uncertainty of disturbances and measurement noise, and temporal dependence in time-series data still pose grand challenges to effective fault detection. To this end, this paper proposes a new fault detector based on a recently developed unsupervised learning method, denoising autoencoder (DAE), which offers the learning of robust nonlinear representations from data against noise and input fluctuation. A DAE is used to build a robust multivariate reconstruction model on raw time-series data from multiple sensors, and then, the reconstruction error of the DAE trained with normal data is analyzed for fault detection. In addition, we apply the sliding-window technique to consider temporal information inherent in time-series data by including the current and past information within a small time window. A key advantage of the proposed approach is the ability to capture the nonlinear correlations among multiple sensor variables and the temporal dependence of each sensor variable simultaneously, which significantly enhanced the fault detection performance. Simulated data from a generic WT benchmark and field supervisory control and data acquisition data from a real wind farm are used to evaluate the proposed approach. The results of two case studies demonstrate the effectiveness and advantages of our proposed approach.
Author	Jiang, Guoqian He, Haibo Yan, Jun Xie, Ping
Author_xml	– sequence: 1 givenname: Guoqian orcidid: 0000-0002-1813-8249 surname: Jiang fullname: Jiang, Guoqian email: jgqysu@gmail.com organization: Qinhuangdao, China – sequence: 2 givenname: Ping surname: Xie fullname: Xie, Ping email: pingx@ysu.edu.cn organization: Kingston, RI, USA – sequence: 3 givenname: Haibo orcidid: 0000-0002-5247-9370 surname: He fullname: He, Haibo email: he@ele.uri.edu organization: Montréal, QC, Canada – sequence: 4 givenname: Jun orcidid: 0000-0002-5148-1399 surname: Yan fullname: Yan, Jun email: jun.yan@concordia.ca organization: Montréal, QC, Canada
BookMark	eNp9kE1PAjEQhhuDiYD-Ab30DyzObLtfR4IgJBovS_C2abut1kBLuuXgv3f5iAcPnubNJM-bmWdEBs47Tcg9wgQRqsf6dT5bTlLAYpIWWcUAr8gQK44JIH8f9BlKlnDOshsy6rovAOAIOCT1xrqW1ocgrdN0IQ7bSJ901Cpa7-i6s-6Din7jvD3l6SF67ZRvdaAbGz9prXd7H8SWrpzxYSeO3C25NmLb6bvLHJP1Yl7PlsnL2_NqNn1JFEOMicw0Ay6VUJXJCiGA8SyXoDLGc5lKLI1WhhktW-h_rIpCSTQFciZybLlibEzKc68KvuuCNo2y8XRBDMJuG4TmaKc52WmOdpqLnR5N_6D7YHcifP8PPZwhq7X-BUrIqjJH9gP8PnPC
CODEN	IATEFW
CitedBy_id	crossref_primary_10_1109_TASE_2022_3141186 crossref_primary_10_1109_TMECH_2019_2908233 crossref_primary_10_3390_en18051158 crossref_primary_10_1016_j_rser_2021_111051 crossref_primary_10_1109_JSEN_2022_3149721 crossref_primary_10_1109_TIM_2022_3227606 crossref_primary_10_1109_JSEN_2025_3545415 crossref_primary_10_1088_1361_6501_ac919b crossref_primary_10_3390_en15082864 crossref_primary_10_1016_j_cie_2023_109605 crossref_primary_10_1007_s11831_021_09671_x crossref_primary_10_1002_acs_3643 crossref_primary_10_1016_j_eswa_2022_117297 crossref_primary_10_1109_JSEN_2022_3173156 crossref_primary_10_1109_TII_2022_3177662 crossref_primary_10_1109_TII_2024_3359409 crossref_primary_10_1016_j_eswa_2022_119479 crossref_primary_10_1007_s10462_023_10410_w crossref_primary_10_1016_j_neucom_2024_127574 crossref_primary_10_1109_ACCESS_2020_3000152 crossref_primary_10_1088_1361_6501_adf244 crossref_primary_10_1016_j_measurement_2020_107929 crossref_primary_10_1109_TII_2023_3268685 crossref_primary_10_1088_1361_6501_ad4dd4 crossref_primary_10_1109_ACCESS_2018_2872796 crossref_primary_10_1016_j_aei_2025_103620 crossref_primary_10_1109_ACCESS_2022_3192134 crossref_primary_10_1016_j_anucene_2021_108621 crossref_primary_10_1109_TII_2024_3409443 crossref_primary_10_1109_TMECH_2021_3059801 crossref_primary_10_1155_2024_7733730 crossref_primary_10_1109_TIE_2022_3189085 crossref_primary_10_1109_ACCESS_2018_2824352 crossref_primary_10_1109_ACCESS_2020_2994077 crossref_primary_10_3390_s25154862 crossref_primary_10_1109_TASE_2019_2956087 crossref_primary_10_3390_app10196789 crossref_primary_10_1016_j_ifacol_2023_10_1456 crossref_primary_10_3390_en15197186 crossref_primary_10_1016_j_measurement_2019_02_080 crossref_primary_10_1109_TMECH_2022_3199985 crossref_primary_10_1109_TMECH_2021_3065522 crossref_primary_10_1088_1361_6501_adfcfd crossref_primary_10_1177_14759217221139642 crossref_primary_10_3390_app12031270 crossref_primary_10_1002_cpe_7886 crossref_primary_10_1016_j_isatra_2022_10_031 crossref_primary_10_1109_ACCESS_2022_3164897 crossref_primary_10_1109_TMECH_2020_2992331 crossref_primary_10_1109_ACCESS_2023_3321320 crossref_primary_10_1016_j_conbuildmat_2023_131643 crossref_primary_10_1109_TIM_2025_3533631 crossref_primary_10_1109_TII_2022_3176821 crossref_primary_10_1109_TPAMI_2024_3387317 crossref_primary_10_1016_j_eswa_2023_119738 crossref_primary_10_1016_j_ress_2023_109108 crossref_primary_10_1109_TII_2024_3381790 crossref_primary_10_1016_j_isatra_2023_03_045 crossref_primary_10_1016_j_renene_2020_12_116 crossref_primary_10_1177_1475921719893594 crossref_primary_10_1002_cjce_23753 crossref_primary_10_1088_1361_6501_aca3c3 crossref_primary_10_1109_TII_2021_3078414 crossref_primary_10_1109_TIM_2020_3048799 crossref_primary_10_1002_ese3_1706 crossref_primary_10_1109_TIA_2025_3544169 crossref_primary_10_2478_amns_2024_2723 crossref_primary_10_3390_machines13060457 crossref_primary_10_1109_TII_2018_2885365 crossref_primary_10_1016_j_heliyon_2024_e38470 crossref_primary_10_3390_en15155638 crossref_primary_10_1109_TII_2018_2875956 crossref_primary_10_1049_rpg2_12319 crossref_primary_10_1007_s10489_024_05530_x crossref_primary_10_1016_j_rser_2023_114039 crossref_primary_10_1109_TIM_2023_3323967 crossref_primary_10_1080_14786451_2024_2326296 crossref_primary_10_3390_act10050086 crossref_primary_10_3390_app15147698 crossref_primary_10_1016_j_measurement_2022_111529 crossref_primary_10_1587_transinf_2020EDL8127 crossref_primary_10_1016_j_energy_2022_124996 crossref_primary_10_1109_TII_2024_3465597 crossref_primary_10_1109_ACCESS_2023_3240306 crossref_primary_10_1007_s12559_019_09710_7 crossref_primary_10_1088_1361_6501_ad6f33 crossref_primary_10_3390_s21165654 crossref_primary_10_1109_JIOT_2024_3387417 crossref_primary_10_1016_j_ymssp_2024_111420 crossref_primary_10_1016_j_neucom_2024_128211 crossref_primary_10_1109_TII_2024_3413952 crossref_primary_10_1016_j_ins_2024_120635 crossref_primary_10_1109_TII_2018_2886048 crossref_primary_10_1109_TMECH_2020_3004589 crossref_primary_10_1177_0959651820954577 crossref_primary_10_1080_15435075_2024_2315445 crossref_primary_10_1016_j_engappai_2021_104300 crossref_primary_10_1109_ACCESS_2021_3062865 crossref_primary_10_1190_geo2024_0451_1 crossref_primary_10_1177_1748006X20976817 crossref_primary_10_1016_j_measurement_2024_116202 crossref_primary_10_1080_15435075_2023_2253896 crossref_primary_10_1109_ACCESS_2020_2972935 crossref_primary_10_1016_j_measurement_2020_108782 crossref_primary_10_1016_j_rineng_2025_104844 crossref_primary_10_1109_JSEN_2021_3061109 crossref_primary_10_1007_s10462_020_09934_2 crossref_primary_10_1016_j_renene_2018_10_062 crossref_primary_10_1109_TII_2019_2952931 crossref_primary_10_3390_en13051063 crossref_primary_10_1016_j_eswa_2023_120428 crossref_primary_10_1016_j_jsv_2020_115879 crossref_primary_10_3390_jmse13091638 crossref_primary_10_3390_s21165488 crossref_primary_10_1142_S0218126625503785 crossref_primary_10_3390_w14162492 crossref_primary_10_1109_TEC_2021_3075897 crossref_primary_10_1109_TNNLS_2020_2985223 crossref_primary_10_3390_en17225538 crossref_primary_10_3390_s20216265 crossref_primary_10_1109_ACCESS_2022_3219480 crossref_primary_10_1088_1361_6501_ad4ab4 crossref_primary_10_1016_j_isatra_2023_12_031 crossref_primary_10_1109_TII_2021_3076077 crossref_primary_10_3390_en17051010 crossref_primary_10_1016_j_rser_2018_09_012 crossref_primary_10_1109_TII_2022_3149935 crossref_primary_10_1016_j_measurement_2024_114658 crossref_primary_10_1109_TMECH_2020_3011005 crossref_primary_10_1109_TMECH_2019_2928967 crossref_primary_10_1016_j_renene_2020_04_148 crossref_primary_10_3390_en12060984 crossref_primary_10_1016_j_energy_2023_126894 crossref_primary_10_1016_j_jmsy_2024_08_013 crossref_primary_10_3390_en12060982 crossref_primary_10_1177_09596518211056165 crossref_primary_10_3390_s21175830 crossref_primary_10_1109_TNNLS_2022_3230458 crossref_primary_10_1109_TAI_2022_3143079 crossref_primary_10_3390_en14217129 crossref_primary_10_1016_j_compchemeng_2022_107857 crossref_primary_10_3390_en14010028 crossref_primary_10_1002_cjce_25445 crossref_primary_10_3390_app10238649 crossref_primary_10_1109_ACCESS_2024_3379529 crossref_primary_10_1016_j_engappai_2023_106028 crossref_primary_10_1177_01423312211057994 crossref_primary_10_26748_KSOE_2021_018 crossref_primary_10_3390_s23063260 crossref_primary_10_1016_j_psep_2024_11_086 crossref_primary_10_1109_ACCESS_2020_2964294 crossref_primary_10_1109_TMECH_2022_3185675 crossref_primary_10_3390_s20123580 crossref_primary_10_1109_TIM_2023_3324347 crossref_primary_10_1109_TMECH_2021_3127213 crossref_primary_10_1016_j_engappai_2023_105859 crossref_primary_10_1016_j_engstruct_2024_118208 crossref_primary_10_1109_ACCESS_2019_2914731 crossref_primary_10_1109_TII_2024_3353921 crossref_primary_10_3390_en13123132 crossref_primary_10_1109_ACCESS_2019_2950985 crossref_primary_10_1109_JSEN_2024_3455328 crossref_primary_10_1016_j_conengprac_2021_104843 crossref_primary_10_1109_TMECH_2020_3012179 crossref_primary_10_1016_j_measurement_2020_108234 crossref_primary_10_1016_j_ymssp_2023_110109 crossref_primary_10_1109_JSEN_2023_3282230 crossref_primary_10_3390_en12203920 crossref_primary_10_1109_TMECH_2022_3166839 crossref_primary_10_3390_app9152990 crossref_primary_10_1016_j_engfailanal_2023_107056 crossref_primary_10_1088_1742_6596_2303_1_012013 crossref_primary_10_1016_j_conengprac_2019_104235 crossref_primary_10_1016_j_eswa_2024_124511 crossref_primary_10_1109_TIM_2024_3463007 crossref_primary_10_3390_machines12120894 crossref_primary_10_3390_jmse13071337 crossref_primary_10_1007_s12555_021_0323_6 crossref_primary_10_1109_TMECH_2020_3030001 crossref_primary_10_1088_1361_6501_aca496 crossref_primary_10_3390_en16124544 crossref_primary_10_1016_j_renene_2019_07_033 crossref_primary_10_1109_TIA_2019_2901732 crossref_primary_10_1016_j_compind_2021_103528 crossref_primary_10_3390_pr10112408 crossref_primary_10_1109_TIM_2025_3544383 crossref_primary_10_3390_en14092509 crossref_primary_10_1016_j_knosys_2024_112114 crossref_primary_10_1109_TMECH_2021_3058061 crossref_primary_10_1016_j_renene_2020_06_154 crossref_primary_10_3390_en12163091 crossref_primary_10_1016_j_epsr_2022_108642
Cites_doi	10.1109/TSTE.2011.2163430 10.1145/1390156.1390294 10.1109/TSTE.2011.2167164 10.1109/TII.2009.2032654 10.1109/TCST.2013.2259235 10.1109/TMECH.2014.2358674 10.1016/j.compchemeng.2004.07.014 10.1109/TIE.2015.2399401 10.1016/0169-7439(95)00076-3 10.1016/j.asoc.2012.08.033 10.1016/j.renene.2012.11.030 10.3182/20120829-3-MX-2028.00010 10.1109/TEC.2013.2294893 10.1016/j.renene.2012.02.018 10.1109/ACC.2013.6580525 10.1109/TCYB.2015.2404432 10.1016/j.mechatronics.2013.11.009 10.1109/TR.2013.2241204 10.1109/TSTE.2015.2405971 10.1002/we.319 10.1198/106186005X77685 10.1109/TMECH.2016.2547905 10.1109/TSTE.2011.2163177 10.1109/TIM.2017.2698738 10.1109/SysTol.2013.6693951 10.1109/TSG.2016.2621135 10.1109/SMC.2014.6974327 10.1016/j.automatica.2009.02.027 10.1049/PBRN013E 10.1109/TMECH.2015.2507186 10.1002/aic.10978 10.1162/089976600300015691 10.1109/TIE.2014.2301773 10.1016/j.rser.2007.05.008 10.1109/TSG.2014.2386305 10.1109/TCST.2014.2361291 10.1175/1520-0477(1993)074<0615:WMAAUT>2.0.CO;2 10.1109/TIE.2015.2422112 10.1109/SysTol.2013.6693901 10.1109/TIE.2014.2364548 10.1002/acs.1162 10.1049/iet-rpg.2016.0248 10.3390/en81012100 10.1016/S0967-0661(99)00191-4 10.1109/TCST.2014.2364956 10.1109/TKDE.2008.239
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION
DOI	10.1109/TMECH.2017.2759301
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
Database_xml	– sequence: 1 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1941-014X
EndPage	100
ExternalDocumentID	10_1109_TMECH_2017_2759301 8059861
Genre	orig-research
GrantInformation_xml	– fundername: Natural Science Foundation of Hebei Province grantid: F2016203421 funderid: 10.13039/501100003787 – fundername: National Natural Science Foundation of China grantid: 61673336; 51529701 funderid: 10.13039/501100001809
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E 9M8 AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS ACIWK ACKIV AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS EJD F5P H~9 IFIPE IFJZH IPLJI JAVBF LAI M43 OCL RIA RIE RNS TN5 VH1 AAYXX CITATION
ID	FETCH-LOGICAL-c311t-b5e304bcac9f57aa03456b0c5346b2b18fecf3febd0109977cb1f7143a61d4c33
IEDL.DBID	RIE
ISICitedReferencesCount	229
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000425673100010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1083-4435
IngestDate	Sat Nov 29 06:33:05 EST 2025 Tue Nov 18 22:24:34 EST 2025 Wed Aug 27 08:34:09 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c311t-b5e304bcac9f57aa03456b0c5346b2b18fecf3febd0109977cb1f7143a61d4c33
ORCID	0000-0002-5148-1399 0000-0002-5247-9370 0000-0002-1813-8249
OpenAccessLink	https://digitalcommons.uri.edu/ele_facpubs/401
PageCount	12
ParticipantIDs	crossref_citationtrail_10_1109_TMECH_2017_2759301 crossref_primary_10_1109_TMECH_2017_2759301 ieee_primary_8059861
PublicationCentury	2000
PublicationDate	2018-Feb. 2018-2-00
PublicationDateYYYYMMDD	2018-02-01
PublicationDate_xml	– month: 02 year: 2018 text: 2018-Feb.
PublicationDecade	2010
PublicationTitle	IEEE/ASME transactions on mechatronics
PublicationTitleAbbrev	TMECH
PublicationYear	2018
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref12 ref15 ref14 ref11 ref10 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref42 ref41 ref44 ref43 ref49 fawcett (ref47) 2004; 31 ref8 ref7 ref4 ref3 ref6 ref5 ref40 ref34 ref37 ref31 ref30 ref33 wang (ref36) 0 ngiam (ref39) 0 ref32 ref2 ref1 wei (ref9) 2010; 24 ref38 ref24 ref23 ref25 ref20 ref22 ref21 ref28 ref27 ref29 vanini (ref26) 2014; 136 vincent (ref35) 2010; 11
References_xml	– ident: ref20 doi: 10.1109/TSTE.2011.2163430 – ident: ref34 doi: 10.1145/1390156.1390294 – ident: ref13 doi: 10.1109/TSTE.2011.2167164 – ident: ref42 doi: 10.1109/TII.2009.2032654 – ident: ref5 doi: 10.1109/TCST.2013.2259235 – ident: ref27 doi: 10.1109/TMECH.2014.2358674 – ident: ref33 doi: 10.1016/j.compchemeng.2004.07.014 – ident: ref8 doi: 10.1109/TIE.2015.2399401 – ident: ref32 doi: 10.1016/0169-7439(95)00076-3 – ident: ref22 doi: 10.1016/j.asoc.2012.08.033 – ident: ref24 doi: 10.1016/j.renene.2012.11.030 – volume: 136 start-page: 91603-1 year: 2014 ident: ref26 article-title: Multiple-model sensor and components fault diagnosis in gas turbine engines using autoassociative neural networks publication-title: J Eng Gas Turbines Power – ident: ref4 doi: 10.3182/20120829-3-MX-2028.00010 – start-page: 265 year: 0 ident: ref39 article-title: On optimization methods for deep learning publication-title: Proc 28th Int Conf Mach Learn – ident: ref15 doi: 10.1109/TEC.2013.2294893 – ident: ref16 doi: 10.1016/j.renene.2012.02.018 – ident: ref49 doi: 10.1109/ACC.2013.6580525 – ident: ref37 doi: 10.1109/TCYB.2015.2404432 – ident: ref11 doi: 10.1016/j.mechatronics.2013.11.009 – ident: ref40 doi: 10.1109/TR.2013.2241204 – ident: ref17 doi: 10.1109/TSTE.2015.2405971 – ident: ref18 doi: 10.1002/we.319 – ident: ref41 doi: 10.1198/106186005X77685 – ident: ref10 doi: 10.1109/TMECH.2016.2547905 – ident: ref21 doi: 10.1109/TSTE.2011.2163177 – ident: ref7 doi: 10.1109/TIM.2017.2698738 – ident: ref14 doi: 10.1109/SysTol.2013.6693951 – ident: ref30 doi: 10.1109/TSG.2016.2621135 – ident: ref31 doi: 10.1109/SMC.2014.6974327 – ident: ref45 doi: 10.1016/j.automatica.2009.02.027 – start-page: 809 year: 0 ident: ref36 article-title: Learning a deep compact image representation for visual tracking publication-title: Proc Adv Neural Inf Process Syst – ident: ref2 doi: 10.1049/PBRN013E – ident: ref25 doi: 10.1109/TMECH.2015.2507186 – ident: ref44 doi: 10.1002/aic.10978 – ident: ref38 doi: 10.1162/089976600300015691 – ident: ref50 doi: 10.1109/TIE.2014.2301773 – ident: ref3 doi: 10.1016/j.rser.2007.05.008 – ident: ref19 doi: 10.1109/TSG.2014.2386305 – ident: ref6 doi: 10.1109/TCST.2014.2361291 – ident: ref51 doi: 10.1175/1520-0477(1993)074<0615:WMAAUT>2.0.CO;2 – ident: ref1 doi: 10.1109/TIE.2015.2422112 – ident: ref28 doi: 10.1109/SysTol.2013.6693901 – ident: ref23 doi: 10.1109/TIE.2014.2364548 – volume: 24 start-page: 687 year: 2010 ident: ref9 article-title: Sensor fault detection and isolation for wind turbines based on subspace identification and Kalman filter techniques publication-title: Int J Adaptive Control Signal Process doi: 10.1002/acs.1162 – volume: 11 start-page: 3371 year: 2010 ident: ref35 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J Mach Learn Res – ident: ref12 doi: 10.1049/iet-rpg.2016.0248 – ident: ref29 doi: 10.3390/en81012100 – ident: ref43 doi: 10.1016/S0967-0661(99)00191-4 – ident: ref46 doi: 10.1109/TCST.2014.2364956 – ident: ref48 doi: 10.1109/TKDE.2008.239 – volume: 31 start-page: 1 year: 2004 ident: ref47 article-title: Roc graphs: Notes and practical considerations for researchers publication-title: Mach Learn
SSID	ssj0004101
Score	2.6276827
Snippet	Data-driven approaches have gained increasing interests in the fault detection of wind turbines (WTs) due to the difficulty in system modeling and the...
SourceID	crossref ieee
SourceType	Enrichment Source Index Database Publisher
StartPage	89
SubjectTerms	Complex mechatronics Correlation denoising autoencoder (DAE) Fault detection Mechatronics Monitoring multivariate data driven Noise reduction Robustness Temperature measurement temporal information wind turbines (WTs)
Title	Wind Turbine Fault Detection Using a Denoising Autoencoder With Temporal Information
URI	https://ieeexplore.ieee.org/document/8059861
Volume	23
WOSCitedRecordID	wos000425673100010&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: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 1941-014X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004101 issn: 1083-4435 databaseCode: RIE dateStart: 19960101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA5zeNCDv6Y4f5GDN-3WNGnTHsfc2EGHh8p2K036goPRSm39-03Sbu4ggrcQ8kr5Usj7mve-D6F7plQIIQQOgch1WCC5I4RSDuGaM4dUBZ6wriXPfD4Pl8votYMet70wAGCLz2BghvYuPytkbX6VDUPXqIlrrrPHOW96tX56IIm1OiY6pXCYzgE2DTJuNIxfJuOZqeLiA4_7EW0NYDaH0I6rij1Upsf_e50TdNQmj3jU7PYp6kB-hg53JAV7KF5oko3jutSMF_A0rdcVfoLKFlzl2BYI4FTP5MXKjkd1VRgtywxKvFhV7zhutKrWuG1UMnHn6G06icczp3VOcCQlpHKED9RlQqYyUj5PU5fqPEm40qcsEJ4goQKpqAKR2ZsxzqUgyjihpwHJmKT0AnXzIodLhDV_EjQKJMuEYEzvt8f0E4JQKUi9QKR9RDZQJrKVFTfuFuvE0gs3Siz8iYE_aeHvo4dtzEcjqvHn6p7Bfruyhf3q9-lrdKCDw6aw-gZ1q7KGW7Qvv6rVZ3lnv5lvsGS_iQ
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFA1jCuqDX1Ocn3nwTbs1Tfr1OObGxG34UNneSpPe4GC0Mlt_v0nazT2I4FsISSgngdzT3HsOQvdMygAC8CwCoW0xT_gW51JaxFecOaDSc7hxLRn702kwn4evDfS4qYUBAJN8Bh3dNG_5aS5K_ausG9haTVxxnR2XMYdU1Vo_VZDEmB0TFVRYTEUB6xIZO-xGk0F_pPO4_I7juyGtLWDW19CWr4q5VoZH__ugY3RYh4-4V-33CWpAdooOtkQFWyiaKZqNo3KlOC_gYVIuC_wEhUm5yrBJEcCJ6snyhWn3yiLXapYprPBsUbzjqFKrWuK6VEnPO0Nvw0HUH1m1d4IlKCGFxV2gNuMiEaF0_SSxqYqUuC1cyjzucBJIEJJK4Kl5G_N9wYnUXuiJR1ImKD1HzSzP4AJhxaA4DT3BUs4ZUzvuMLWCF0gJiePxpI3IGspY1MLi2t9iGRuCYYexgT_W8Mc1_G30sJnzUclq_Dm6pbHfjKxhv_y9-w7tjaLJOB4_T1-u0L5aKKjSrK9Rs1iVcIN2xVex-FzdmvPzDdK4wtA
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=Wind+Turbine+Fault+Detection+Using+a+Denoising+Autoencoder+With+Temporal+Information&rft.jtitle=IEEE%2FASME+transactions+on+mechatronics&rft.au=Jiang%2C+Guoqian&rft.au=Xie%2C+Ping&rft.au=He%2C+Haibo&rft.au=Yan%2C+Jun&rft.date=2018-02-01&rft.issn=1083-4435&rft.eissn=1941-014X&rft.volume=23&rft.issue=1&rft.spage=89&rft.epage=100&rft_id=info:doi/10.1109%2FTMECH.2017.2759301&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMECH_2017_2759301
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1083-4435&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1083-4435&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1083-4435&client=summon