Wear indicator construction for rolling bearings based on an enhanced and unsupervised stacked auto-encoder
The degradation state of a bearing can be monitored effectively by using a wear indicator (WI). A WI curve having smoothness and monotonicity can lay a good foundation for predicting the remaining useful life of the bearing. Most traditional models for bearing WI construction, such as time–frequency...
Saved in:
Published in | Soft computing (Berlin, Germany) Vol. 28; no. 15-16; pp. 8835 - 8848 |
---|---|
Main Authors | , , , , , , |
Format | Journal Article |
Language | English |
Published |
Berlin/Heidelberg
Springer Berlin Heidelberg
01.08.2024
Springer Nature B.V |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The degradation state of a bearing can be monitored effectively by using a wear indicator (WI). A WI curve having smoothness and monotonicity can lay a good foundation for predicting the remaining useful life of the bearing. Most traditional models for bearing WI construction, such as time–frequency indicators and signal decomposition, are complicated; for example, some WI construction models need several models to select from, and their fusion depends on the manual experience of engineers. For example, single and mixed traditional time–frequency indicators, such as the root mean square (RMS), Kurtosis, multiple time–frequency domain fusion. However, the mentioned-above time–frequency domain indicators are difficult to adaptively reflect the operating status of the equipment when the operating conditions of the mechanical system change. Some signal decomposition models are combined with other models and rely on manual experience to extract WI, such as the selection of effective intrinsic mode function components function, parameter setting of empirical mode decomposition and ensemble empirical mode decomposition model, etc. Deep learning models, such as stacked auto encoder (SAE) and convolution neural network, have been widely used in bearing health monitoring and WI construction, because its powerful learning and feature extraction capabilities of multiple hidden layer structures. But these deep learning models are designed to use output labels. Particularly when the data volume is large, it requires manpower, material resources, and experienced engineers to label the data, or it is difficult to label and distinguish the categories of data samples. Therefore, to solve these problems and eliminate the need for manual labor, such as labeling data and selecting models for fusion, we propose using SAE without an output label layer to extract WI from original signals directly. However, an extracted WI curve without good monotonicity (Mon) will result in a poor remaining useful life prediction accuracy. To improve the monotonicity of the extracted WI and reduce the complexity of the WI construction model, we propose an unsupervised enhanced SAE without an output layer, named SINSAE, by adding a sine function of an average value which is calculated form start time to current at each hidden layer to eliminate concussion. Moreover, to demonstrate that our proposed model is better than other models, such as the RMS, Kurtosis, multiple time–frequency domain fusion, SAE, SAE without an output layer, and signal decomposition models, the
Mon
indicator in this study is used to compare the monotonicity of the extracted WI. Lastly, the results of our experiments using different bearing datasets and various working conditions show that the smoothness and monotonicity of the WI curve extracted by the SINSAE is better than that of other models. Moreover, compared to the traditional commonly used single and multiple time–frequency domain indicators, supervised deep learning and basic unsupervised deep models, the unsupervised SINSAE model can increase the
Mon
indicators from [0.1, 0.8], [0.02, 0.1], [0.1, 0.8] to above 0.9, respectively. |
---|---|
AbstractList | The degradation state of a bearing can be monitored effectively by using a wear indicator (WI). A WI curve having smoothness and monotonicity can lay a good foundation for predicting the remaining useful life of the bearing. Most traditional models for bearing WI construction, such as time–frequency indicators and signal decomposition, are complicated; for example, some WI construction models need several models to select from, and their fusion depends on the manual experience of engineers. For example, single and mixed traditional time–frequency indicators, such as the root mean square (RMS), Kurtosis, multiple time–frequency domain fusion. However, the mentioned-above time–frequency domain indicators are difficult to adaptively reflect the operating status of the equipment when the operating conditions of the mechanical system change. Some signal decomposition models are combined with other models and rely on manual experience to extract WI, such as the selection of effective intrinsic mode function components function, parameter setting of empirical mode decomposition and ensemble empirical mode decomposition model, etc. Deep learning models, such as stacked auto encoder (SAE) and convolution neural network, have been widely used in bearing health monitoring and WI construction, because its powerful learning and feature extraction capabilities of multiple hidden layer structures. But these deep learning models are designed to use output labels. Particularly when the data volume is large, it requires manpower, material resources, and experienced engineers to label the data, or it is difficult to label and distinguish the categories of data samples. Therefore, to solve these problems and eliminate the need for manual labor, such as labeling data and selecting models for fusion, we propose using SAE without an output label layer to extract WI from original signals directly. However, an extracted WI curve without good monotonicity (Mon) will result in a poor remaining useful life prediction accuracy. To improve the monotonicity of the extracted WI and reduce the complexity of the WI construction model, we propose an unsupervised enhanced SAE without an output layer, named SINSAE, by adding a sine function of an average value which is calculated form start time to current at each hidden layer to eliminate concussion. Moreover, to demonstrate that our proposed model is better than other models, such as the RMS, Kurtosis, multiple time–frequency domain fusion, SAE, SAE without an output layer, and signal decomposition models, the Mon indicator in this study is used to compare the monotonicity of the extracted WI. Lastly, the results of our experiments using different bearing datasets and various working conditions show that the smoothness and monotonicity of the WI curve extracted by the SINSAE is better than that of other models. Moreover, compared to the traditional commonly used single and multiple time–frequency domain indicators, supervised deep learning and basic unsupervised deep models, the unsupervised SINSAE model can increase the Mon indicators from [0.1, 0.8], [0.02, 0.1], [0.1, 0.8] to above 0.9, respectively. The degradation state of a bearing can be monitored effectively by using a wear indicator (WI). A WI curve having smoothness and monotonicity can lay a good foundation for predicting the remaining useful life of the bearing. Most traditional models for bearing WI construction, such as time–frequency indicators and signal decomposition, are complicated; for example, some WI construction models need several models to select from, and their fusion depends on the manual experience of engineers. For example, single and mixed traditional time–frequency indicators, such as the root mean square (RMS), Kurtosis, multiple time–frequency domain fusion. However, the mentioned-above time–frequency domain indicators are difficult to adaptively reflect the operating status of the equipment when the operating conditions of the mechanical system change. Some signal decomposition models are combined with other models and rely on manual experience to extract WI, such as the selection of effective intrinsic mode function components function, parameter setting of empirical mode decomposition and ensemble empirical mode decomposition model, etc. Deep learning models, such as stacked auto encoder (SAE) and convolution neural network, have been widely used in bearing health monitoring and WI construction, because its powerful learning and feature extraction capabilities of multiple hidden layer structures. But these deep learning models are designed to use output labels. Particularly when the data volume is large, it requires manpower, material resources, and experienced engineers to label the data, or it is difficult to label and distinguish the categories of data samples. Therefore, to solve these problems and eliminate the need for manual labor, such as labeling data and selecting models for fusion, we propose using SAE without an output label layer to extract WI from original signals directly. However, an extracted WI curve without good monotonicity (Mon) will result in a poor remaining useful life prediction accuracy. To improve the monotonicity of the extracted WI and reduce the complexity of the WI construction model, we propose an unsupervised enhanced SAE without an output layer, named SINSAE, by adding a sine function of an average value which is calculated form start time to current at each hidden layer to eliminate concussion. Moreover, to demonstrate that our proposed model is better than other models, such as the RMS, Kurtosis, multiple time–frequency domain fusion, SAE, SAE without an output layer, and signal decomposition models, the Mon indicator in this study is used to compare the monotonicity of the extracted WI. Lastly, the results of our experiments using different bearing datasets and various working conditions show that the smoothness and monotonicity of the WI curve extracted by the SINSAE is better than that of other models. Moreover, compared to the traditional commonly used single and multiple time–frequency domain indicators, supervised deep learning and basic unsupervised deep models, the unsupervised SINSAE model can increase the Mon indicators from [0.1, 0.8], [0.02, 0.1], [0.1, 0.8] to above 0.9, respectively. |
Author | Zhou, Shengwen Guo, Shunsheng Xu, Fan Huang, Zhelin Du, Baigang Zeng, Wenhui Yu, Lisha |
Author_xml | – sequence: 1 givenname: Wenhui surname: Zeng fullname: Zeng, Wenhui organization: School of Mechanical and Electronic Engineering, Wuhan University of Technology – sequence: 2 givenname: Lisha surname: Yu fullname: Yu, Lisha organization: School of Design, The Hong Kong Polytechnic University – sequence: 3 givenname: Fan orcidid: 0000-0002-2222-7949 surname: Xu fullname: Xu, Fan organization: School of Mechanical and Electronic Engineering, Wuhan University of Technology – sequence: 4 givenname: Zhelin surname: Huang fullname: Huang, Zhelin email: huangzl@szu.edu.cn organization: Department of Statistics, College of Economics, Shenzhen University – sequence: 5 givenname: Shengwen surname: Zhou fullname: Zhou, Shengwen organization: School of Mechanical and Electronic Engineering, Wuhan University of Technology – sequence: 6 givenname: Shunsheng surname: Guo fullname: Guo, Shunsheng organization: School of Mechanical and Electronic Engineering, Wuhan University of Technology – sequence: 7 givenname: Baigang surname: Du fullname: Du, Baigang organization: School of Mechanical and Electronic Engineering, Wuhan University of Technology |
BookMark | eNp9kEtLxDAUhYOM4MzoH3AVcB29eU3apQy-YMCN4jKkaaqdGZOatDL-e1MruHN1H-ece-FboJkP3iF0TuGSAqirBCABCDBOoIRVQQ5HaE4F50QJVc5-ekbUSvATtEhpC8CoknyOdi_ORNz6urWmDxHb4FMfB9u3weMmL2LY71v_iqvsyzXhyiRX46waj51_M97m0fgaDz4NnYuf7ain3tjdKAx9IM7bULt4io4bs0_u7Lcu0fPtzdP6nmwe7x7W1xtimYKeVJWgVtYgGdDCMebKyhXAqVTU1mCcVYUEyVeKCbCWgTKFcXVDRaEEq43gS3Qx3e1i-Bhc6vU2DNHnl5pDWUhJyxKyi00uG0NK0TW6i-27iV-agh6h6gmqzlD1D1R9yCE-hVI30nDx7_Q_qW-N1X2K |
Cites_doi | 10.4028/www.scientific.net/AMM.493.343 10.1016/j.ymssp.2017.02.003 10.1016/j.measurement.2019.107371 10.1002/cem.2912 10.1016/j.neucom.2017.02.045 10.3901/JME.2013.02.183 10.1016/j.neucom.2019.03.024 10.1016/j.measurement.2021.108973 10.1109/TR.2013.2285318 10.1016/j.jmsy.2017.02.013 10.1016/j.neunet.2021.10.021 10.1016/j.asoc.2020.106119 10.1016/j.ins.2021.08.042 10.1109/TIM.2016.2601004 10.1007/s00500-018-3178-x 10.1016/j.eswa.2017.05.039 10.1016/j.asoc.2018.09.037 10.1016/j.jsv.2009.10.021 10.1016/j.ymssp.2008.06.009 10.1007/s11042-020-10486-4 10.1109/ACCESS.2017.2728010 10.1177/1077546315604522 10.1016/j.neucom.2018.02.083 10.1109/TIM.2017.2759418 10.1016/j.neucom.2014.08.092 10.1016/j.measurement.2018.11.040 10.7551/mitpress/1888.003.0013 10.1016/j.jsv.2011.07.014 |
ContentType | Journal Article |
Copyright | The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
Copyright_xml | – notice: The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
DBID | AAYXX CITATION JQ2 |
DOI | 10.1007/s00500-023-09068-x |
DatabaseName | CrossRef ProQuest Computer Science Collection |
DatabaseTitle | CrossRef ProQuest Computer Science Collection |
DatabaseTitleList | ProQuest Computer Science Collection |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Computer Science |
EISSN | 1433-7479 |
EndPage | 8848 |
ExternalDocumentID | 10_1007_s00500_023_09068_x |
GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 51705386; 52205168; 51905396; 62203482 funderid: http://dx.doi.org/10.13039/501100001809 – fundername: Guangdong Basic and Applied Basic Research Foundation grantid: 2023A1515011367 – fundername: Natural Science Foundation of Hubei Province grantid: 2021CFB316 funderid: http://dx.doi.org/10.13039/501100003819 |
GroupedDBID | -5B -5G -BR -EM -Y2 -~C .86 .VR 06D 0R~ 0VY 1N0 1SB 203 29~ 2J2 2JN 2JY 2KG 2LR 2P1 2VQ 2~H 30V 4.4 406 408 409 40D 40E 5VS 67Z 6NX 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO ABAKF ABBBX ABBXA ABDZT ABECU ABFGW ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACHXU ACIPQ ACKNC ACMDZ ACMLO ACOKC ACOMO ACSNA ACWMK ACZOJ ADHHG ADHIR ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AESTI AETLH AEVLU AEVTX AEXYK AFBBN AFGCZ AFKRA AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AIMYW AITGF AJBLW AJRNO AJZVZ AKQUC ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARAPS ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN B-. BA0 BDATZ BENPR BGLVJ BGNMA CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 EBLON EBS EIOEI EJD ESBYG FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ6 GQ7 GQ8 GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I09 IHE IJ- IKXTQ IWAJR IXC IXD IXE IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ K7- KDC KOV LAS LLZTM M4Y MA- N2Q NB0 NPVJJ NQJWS NU0 O9- O93 O9J OAM P2P P9P PF0 PT4 PT5 QOS R89 R9I RIG RNI ROL RPX RSV RZK S16 S1Z S27 S3B SAP SDH SEG SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TSG TSK TSV TUC U2A UG4 UNUBA UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 Z5O Z7R Z7X Z7Y Z7Z Z81 Z83 Z88 ZMTXR AAYXX CITATION JQ2 |
ID | FETCH-LOGICAL-c270t-bb41c5d052018e22e9be8031571cd0aec78505367240cc207a8aedf148742da43 |
IEDL.DBID | U2A |
ISSN | 1432-7643 |
IngestDate | Wed Sep 25 02:15:03 EDT 2024 Thu Sep 12 20:33:35 EDT 2024 Fri Aug 30 01:10:15 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 15-16 |
Keywords | Deep learning Stacked auto-encoder Wear indicator Sine function Roller bearings |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c270t-bb41c5d052018e22e9be8031571cd0aec78505367240cc207a8aedf148742da43 |
ORCID | 0000-0002-2222-7949 |
PQID | 3098551990 |
PQPubID | 2043697 |
PageCount | 14 |
ParticipantIDs | proquest_journals_3098551990 crossref_primary_10_1007_s00500_023_09068_x springer_journals_10_1007_s00500_023_09068_x |
PublicationCentury | 2000 |
PublicationDate | 20240801 |
PublicationDateYYYYMMDD | 2024-08-01 |
PublicationDate_xml | – month: 08 year: 2024 text: 20240801 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Berlin/Heidelberg |
PublicationPlace_xml | – name: Berlin/Heidelberg – name: Heidelberg |
PublicationSubtitle | A Fusion of Foundations, Methodologies and Applications |
PublicationTitle | Soft computing (Berlin, Germany) |
PublicationTitleAbbrev | Soft Comput |
PublicationYear | 2024 |
Publisher | Springer Berlin Heidelberg Springer Nature B.V |
Publisher_xml | – name: Springer Berlin Heidelberg – name: Springer Nature B.V |
References | Sarath, Lauly, Larochelle, Khapra (CR21) 2014; 3 Xu, Tse, Tse (CR27) 2018; 73 Tse, Wang (CR26) 2017; 23 Guo, Lei, Li, Yan, Li (CR7) 2018; 292 Ren, Cui, Cheng (CR17) 2017; 43 CR19 Ali, Zhu, Zakarya (CR2) 2021; 80 Sun, Zhang, Xie, Zhang (CR24) 2017; 25 Xu, Tse (CR28) 2019; 23 CR14 Lei, Li, Lin (CR11) 2016; 65 Shen, Chen, He (CR23) 2013; 49 Theodoros, Dimitrios, George (CR20) 2013; 62 Xu, Huang, Yang, Wang, Tsui (CR29) 2020; 89 Lv, Wen, Liu (CR13) 2017; 31 Resta, Ripamonti, Cazzluani (CR18) 2011; 329 Qi, Shen, Wang (CR15) 2017; 5 Guo, Li, Feng, Lei, Lin (CR6) 2017; 240 Heng, Zhang, Tan (CR8) 2009; 23 Ali, Zhu, Zakarya (CR4) 2022; 145 Kosasih, Caesarendra, Tieu, Widodo, Moodie, Tieu (CR10) 2014; 493 Sun, Yan, Wen (CR25) 2018; 67 CR5 Li, Struzik, Zhang, Cichocki (CR12) 2014; 165 Xu, Yang, Fan, Huang, Tsui (CR30) 2020; 152 Zhao, Xianmin Zhang, Zhan, Wu (CR32) 2021; 174 Rai, Upadhyay (CR16) 2017; 93 Huang, Wu, Wang (CR9) 2012; 31 Affonso, Rossi, Vieira, Carvalho (CR1) 2017; 85 Zhang, Jiao, Ma, Duan, Zhang (CR31) 2019; 351 CR22 Ali, Zhu, Zakarya (CR3) 2021; 577 F Xu (9068_CR28) 2019; 23 L Guo (9068_CR6) 2017; 240 F Xu (9068_CR30) 2020; 152 J Li (9068_CR12) 2014; 165 JD Sun (9068_CR25) 2018; 67 F Resta (9068_CR18) 2011; 329 S Sun (9068_CR24) 2017; 25 F Xu (9068_CR29) 2020; 89 9068_CR19 F Xu (9068_CR27) 2018; 73 Y Huang (9068_CR9) 2012; 31 CAP Sarath (9068_CR21) 2014; 3 A Heng (9068_CR8) 2009; 23 9068_CR14 ZH Shen (9068_CR23) 2013; 49 B Zhao (9068_CR32) 2021; 174 A Ali (9068_CR2) 2021; 80 YM Qi (9068_CR15) 2017; 5 A Rai (9068_CR16) 2017; 93 A Ali (9068_CR4) 2022; 145 L Ren (9068_CR17) 2017; 43 C Affonso (9068_CR1) 2017; 85 L Zhang (9068_CR31) 2019; 351 Y Lei (9068_CR11) 2016; 65 PW Tse (9068_CR26) 2017; 23 HL Theodoros (9068_CR20) 2013; 62 L Guo (9068_CR7) 2018; 292 9068_CR5 A Ali (9068_CR3) 2021; 577 9068_CR22 FY Lv (9068_CR13) 2017; 31 BY Kosasih (9068_CR10) 2014; 493 |
References_xml | – volume: 493 start-page: 343 year: 2014 end-page: 348 ident: CR10 article-title: Degradation trend estimation and prognosis of large low speed slewing bearing lifetime publication-title: Appl Mech Mater doi: 10.4028/www.scientific.net/AMM.493.343 contributor: fullname: Tieu – volume: 3 start-page: 1853 year: 2014 end-page: 1861 ident: CR21 article-title: An autoencoder approach to learning bilingual word representations publication-title: Adv Neural Inf Process Syst contributor: fullname: Khapra – ident: CR22 – volume: 93 start-page: 16 year: 2017 end-page: 29 ident: CR16 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 contributor: fullname: Upadhyay – ident: CR14 – volume: 152 year: 2020 ident: CR30 article-title: Extracting degradation trends for roller bearings by using a moving-average stacked auto-encoder and a novel exponential function publication-title: Measurement doi: 10.1016/j.measurement.2019.107371 contributor: fullname: Tsui – volume: 31 start-page: 1 issue: 9 year: 2017 end-page: 16 ident: CR13 article-title: Weighted time series fault diagnosis based on a stacked sparse autoencoder publication-title: J Chemom doi: 10.1002/cem.2912 contributor: fullname: Liu – volume: 25 start-page: 779 year: 2017 end-page: 787 ident: CR24 article-title: An unsupervised deep domain adaptation approach for robust speech recognition publication-title: Neurocomputing contributor: fullname: Zhang – volume: 240 start-page: 98 issue: 31 year: 2017 end-page: 109 ident: CR6 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 contributor: fullname: Lin – volume: 49 start-page: 183 issue: 2 year: 2013 end-page: 189 ident: CR23 article-title: remaining life predictions of rolling bearing based on relative features and multivariable support vector machine publication-title: J Mech Eng doi: 10.3901/JME.2013.02.183 contributor: fullname: He – volume: 351 start-page: 167 year: 2019 end-page: 179 ident: CR31 article-title: PolSAR image classification based on multi-scale stacked sparse autoencoder publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.03.024 contributor: fullname: Zhang – volume: 174 year: 2021 ident: CR32 article-title: A robust construction of normalized CNN for online intelligent condition monitoring of rolling bearings considering variable working conditions and sources publication-title: Measurement doi: 10.1016/j.measurement.2021.108973 contributor: fullname: Wu – volume: 62 start-page: 821 issue: 4 year: 2013 end-page: 832 ident: CR20 article-title: Remaining useful life estimation in rolling bearings utilizing data-driven probabilistic e-support vectors regression publication-title: IEEE Trans Reliab doi: 10.1109/TR.2013.2285318 contributor: fullname: George – volume: 43 start-page: 248 issue: 2 year: 2017 end-page: 256 ident: CR17 article-title: Multi-bearing remaining useful life collaborative prediction: a deep learning approach publication-title: J Manuf Syst doi: 10.1016/j.jmsy.2017.02.013 contributor: fullname: Cheng – volume: 145 start-page: 233 year: 2022 end-page: 247 ident: CR4 article-title: Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction publication-title: Neural Netw doi: 10.1016/j.neunet.2021.10.021 contributor: fullname: Zakarya – volume: 89 year: 2020 ident: CR29 article-title: Constructing a health indicator for roller bearings by using a stacked auto-encoder with an exponential function to eliminate concussion publication-title: Applied Soft Computing Journal doi: 10.1016/j.asoc.2020.106119 contributor: fullname: Tsui – volume: 577 start-page: 852 year: 2021 end-page: 870 ident: CR3 article-title: Exploiting dynamic spatio-temporal correlations for citywide traffic flow prediction using attention based neural networks publication-title: Inf Sci doi: 10.1016/j.ins.2021.08.042 contributor: fullname: Zakarya – volume: 65 start-page: 2671 issue: 12 year: 2016 end-page: 2684 ident: CR11 article-title: A new method based on stochastic process models for machine remaining useful life prediction’,’ publication-title: IEEE Trans Instrum Meas doi: 10.1109/TIM.2016.2601004 contributor: fullname: Lin – ident: CR19 – volume: 23 start-page: 5117 issue: 13 year: 2019 end-page: 5128 ident: CR28 article-title: Automatic roller bearings fault diagnosis using DSAE in deep learning and CFS algorithm publication-title: Soft Comput doi: 10.1007/s00500-018-3178-x contributor: fullname: Tse – volume: 85 start-page: 114 year: 2017 end-page: 122 ident: CR1 article-title: Deep learning for biological image classification publication-title: Expert System with Applications doi: 10.1016/j.eswa.2017.05.039 contributor: fullname: Carvalho – volume: 73 start-page: 898 year: 2018 end-page: 913 ident: CR27 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 contributor: fullname: Tse – volume: 329 start-page: 961 issue: 8 year: 2011 end-page: 972 ident: CR18 article-title: Independent modal control for nonlinear flexible structures: an experimental test rig publication-title: J Sound Vib doi: 10.1016/j.jsv.2009.10.021 contributor: fullname: Cazzluani – volume: 23 start-page: 724 issue: 3 year: 2009 end-page: 739 ident: CR8 article-title: Rotating machinery prognostics: state of the art, challenges and opportunities publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2008.06.009 contributor: fullname: Tan – volume: 80 start-page: 31401 issue: 20 year: 2021 end-page: 31433 ident: CR2 article-title: A data aggregation based approach to exploit dynamic spatio-temporal correlations for citywide crowd flows prediction in fog computing publication-title: Multimedia Tools Appl doi: 10.1007/s11042-020-10486-4 contributor: fullname: Zakarya – volume: 31 start-page: 91 issue: 2 year: 2012 end-page: 94 ident: CR9 article-title: Test for active control of boom vibration of a concrete pump truck publication-title: J Vib Shock contributor: fullname: Wang – volume: 5 start-page: 15066 year: 2017 end-page: 15079 ident: CR15 article-title: Stacked Sparse Autoencoder-Based Deep Network for Fault Diagnosis of Rotating Machinery publication-title: IEEE ACCESS doi: 10.1109/ACCESS.2017.2728010 contributor: fullname: Wang – ident: CR5 – volume: 23 start-page: 1925 issue: 12 year: 2017 end-page: 1937 ident: CR26 article-title: Enhancing the abilities in assessing slurry pumps’ performance degradation and estimating their remaining useful lives by using captured vibration signals publication-title: J Vib Control doi: 10.1177/1077546315604522 contributor: fullname: Wang – volume: 292 start-page: 142 year: 2018 end-page: 150 ident: CR7 article-title: Machinery health indicator construction based on convolution neural network considering trend burr publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.02.083 contributor: fullname: Li – volume: 67 start-page: 185 year: 2018 end-page: 195 ident: CR25 article-title: Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning publication-title: IEEE Trans Instrum Meas doi: 10.1109/TIM.2017.2759418 contributor: fullname: Wen – volume: 165 start-page: 23 year: 2014 end-page: 31 ident: CR12 article-title: Feature learning from incomplete EEG with denoising autoencoder publication-title: Neurocomputing doi: 10.1016/j.neucom.2014.08.092 contributor: fullname: Cichocki – volume: 23 start-page: 1925 issue: 12 year: 2017 ident: 9068_CR26 publication-title: J Vib Control doi: 10.1177/1077546315604522 contributor: fullname: PW Tse – volume: 80 start-page: 31401 issue: 20 year: 2021 ident: 9068_CR2 publication-title: Multimedia Tools Appl doi: 10.1007/s11042-020-10486-4 contributor: fullname: A Ali – volume: 25 start-page: 779 year: 2017 ident: 9068_CR24 publication-title: Neurocomputing contributor: fullname: S Sun – volume: 351 start-page: 167 year: 2019 ident: 9068_CR31 publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.03.024 contributor: fullname: L Zhang – volume: 5 start-page: 15066 year: 2017 ident: 9068_CR15 publication-title: IEEE ACCESS doi: 10.1109/ACCESS.2017.2728010 contributor: fullname: YM Qi – volume: 65 start-page: 2671 issue: 12 year: 2016 ident: 9068_CR11 publication-title: IEEE Trans Instrum Meas doi: 10.1109/TIM.2016.2601004 contributor: fullname: Y Lei – volume: 31 start-page: 91 issue: 2 year: 2012 ident: 9068_CR9 publication-title: J Vib Shock contributor: fullname: Y Huang – ident: 9068_CR14 – volume: 152 year: 2020 ident: 9068_CR30 publication-title: Measurement doi: 10.1016/j.measurement.2019.107371 contributor: fullname: F Xu – volume: 73 start-page: 898 year: 2018 ident: 9068_CR27 publication-title: Appl Soft Comput doi: 10.1016/j.asoc.2018.09.037 contributor: fullname: F Xu – volume: 145 start-page: 233 year: 2022 ident: 9068_CR4 publication-title: Neural Netw doi: 10.1016/j.neunet.2021.10.021 contributor: fullname: A Ali – volume: 3 start-page: 1853 year: 2014 ident: 9068_CR21 publication-title: Adv Neural Inf Process Syst contributor: fullname: CAP Sarath – volume: 23 start-page: 724 issue: 3 year: 2009 ident: 9068_CR8 publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2008.06.009 contributor: fullname: A Heng – volume: 85 start-page: 114 year: 2017 ident: 9068_CR1 publication-title: Expert System with Applications doi: 10.1016/j.eswa.2017.05.039 contributor: fullname: C Affonso – volume: 329 start-page: 961 issue: 8 year: 2011 ident: 9068_CR18 publication-title: J Sound Vib doi: 10.1016/j.jsv.2009.10.021 contributor: fullname: F Resta – volume: 493 start-page: 343 year: 2014 ident: 9068_CR10 publication-title: Appl Mech Mater doi: 10.4028/www.scientific.net/AMM.493.343 contributor: fullname: BY Kosasih – volume: 67 start-page: 185 year: 2018 ident: 9068_CR25 publication-title: IEEE Trans Instrum Meas doi: 10.1109/TIM.2017.2759418 contributor: fullname: JD Sun – ident: 9068_CR22 doi: 10.1016/j.measurement.2018.11.040 – volume: 23 start-page: 5117 issue: 13 year: 2019 ident: 9068_CR28 publication-title: Soft Comput doi: 10.1007/s00500-018-3178-x contributor: fullname: F Xu – volume: 31 start-page: 1 issue: 9 year: 2017 ident: 9068_CR13 publication-title: J Chemom doi: 10.1002/cem.2912 contributor: fullname: FY Lv – volume: 292 start-page: 142 year: 2018 ident: 9068_CR7 publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.02.083 contributor: fullname: L Guo – volume: 89 year: 2020 ident: 9068_CR29 publication-title: Applied Soft Computing Journal doi: 10.1016/j.asoc.2020.106119 contributor: fullname: F Xu – ident: 9068_CR19 doi: 10.7551/mitpress/1888.003.0013 – volume: 174 year: 2021 ident: 9068_CR32 publication-title: Measurement doi: 10.1016/j.measurement.2021.108973 contributor: fullname: B Zhao – volume: 43 start-page: 248 issue: 2 year: 2017 ident: 9068_CR17 publication-title: J Manuf Syst doi: 10.1016/j.jmsy.2017.02.013 contributor: fullname: L Ren – volume: 93 start-page: 16 year: 2017 ident: 9068_CR16 publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2017.02.003 contributor: fullname: A Rai – volume: 49 start-page: 183 issue: 2 year: 2013 ident: 9068_CR23 publication-title: J Mech Eng doi: 10.3901/JME.2013.02.183 contributor: fullname: ZH Shen – volume: 577 start-page: 852 year: 2021 ident: 9068_CR3 publication-title: Inf Sci doi: 10.1016/j.ins.2021.08.042 contributor: fullname: A Ali – volume: 240 start-page: 98 issue: 31 year: 2017 ident: 9068_CR6 publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.02.045 contributor: fullname: L Guo – volume: 62 start-page: 821 issue: 4 year: 2013 ident: 9068_CR20 publication-title: IEEE Trans Reliab doi: 10.1109/TR.2013.2285318 contributor: fullname: HL Theodoros – ident: 9068_CR5 doi: 10.1016/j.jsv.2011.07.014 – volume: 165 start-page: 23 year: 2014 ident: 9068_CR12 publication-title: Neurocomputing doi: 10.1016/j.neucom.2014.08.092 contributor: fullname: J Li |
SSID | ssj0021753 |
Score | 2.409775 |
Snippet | The degradation state of a bearing can be monitored effectively by using a wear indicator (WI). A WI curve having smoothness and monotonicity can lay a good... |
SourceID | proquest crossref springer |
SourceType | Aggregation Database Publisher |
StartPage | 8835 |
SubjectTerms | Application of Soft Computing Artificial Intelligence Artificial neural networks Bearings Coders Computational Intelligence Construction Control Deep learning Depth indicators Engineering Engineers Fault diagnosis Frequency domain analysis Indicators Kurtosis Labeling Labels Life prediction Machine learning Mathematical Logic and Foundations Mechanical systems Mechatronics Neural networks Physical work Robotics Roller bearings Smoothness Time-frequency analysis Unsupervised learning Useful life |
Title | Wear indicator construction for rolling bearings based on an enhanced and unsupervised stacked auto-encoder |
URI | https://link.springer.com/article/10.1007/s00500-023-09068-x https://www.proquest.com/docview/3098551990/abstract/ |
Volume | 28 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLbQdoEDjwFiMFAO3CBSm3ZtetzQxgRiJybGqcprQkLqpj0kfj52HysgOHBqJUc5xHb8ObG_AFx30Wpi5VNRu7Q8FDbhGoEyR_RrrJOxiBT1Oz-No9EkfJh2p3Ufd17sXt1I5hv1tteNmEo8jiGGjhYiyRE4Ngk8kClPRG-bZZXUk4gDEDpivC07ZX6f43s0qiHmj1vRPNgMD2G_RImsV6j1CHZc1oKD6gUGVjpkC_a-0Akew_sLmi2jS2hDqTQz85oeliE4ZcuCgZtpHEcn5IximGUoVRlz2VteDYD_lm2y1WZB2wjJEUCir6Ngs55zIr60bnkCk-Hg-W7Ey8cUuBGxt-Zah77pWip78aUTwiXaSXriIfaN9ZQzsUQwFEQxhnhjBCpQKmdnmC1h8mxVGJxCI5tn7gxYpJ11ke9rbV3ozQKldBjGONzTSkVe0oabalHTRcGZkW7ZkXMVpKiCNFdB-tGGTrXuaek_qzTwEolYDkNlG24rXdTiv2c7_9_wC9gViFKKir4ONFAp7hJRxlpfQbM37PfH9L1_fRxc5Vb2CZ_NzZg |
link.rule.ids | 315,786,790,27957,27958,41116,41558,42185,42627,52146,52269 |
linkProvider | Springer Nature |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB6kHtSDj6pYrZqDNw3sptvd7LGIUrXtqcXeQl5FELalD_DnO7OPVkUP3gITcsiXZL5JZr4A3LRx1SQ6pKR26XgkXMoNEmWO7Nc6LxMRa6p37g_i7ih6HrfHZVHYosp2r54k85N6XexGUiUBRx9Ddwux5Mgct0lPnUKukeisw6xSexKJAHJHdLhlqczvY3x3RxuO-eNZNPc2j4ewX9JE1ilwPYItn9XhoPqCgZU7sg57X_QEj-H9Fdcto1doS7E0s9ONPixDdsrmhQQ3M9iPrsgZOTHH0Koz5rO3PB0A246tssVqRucI2ZFB4mZHw2o55aR86fz8BEaPD8P7Li9_U-BWJMGSGxOFtu0o7yWUXgifGi_pj4cktC7Q3iYS2VArTtDHWysQQam9m2C4hNGz01HrFGrZNPNnwGLjnY_D0Bjno2DS0tpEUYLdA6N1HKQNuK0mVc0K0Qy1lkfOIVAIgcohUB8NaFbzrsoNtFCtIJVI5tBXNuCuwmJj_nu08_91v4ad7rDfU72nwcsF7AqkLEV6XxNqCJC_RMqxNFf5CvsEtG3N4w |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5EQfTgoypWq-bgTUN30-0-jkUt9VU8WOwt5FUEYVvaLfjzndlHW0UP3hYm5JDJ7PdNMvMF4LKNuyZSPhW1x5YHwiZcI1HmyH6NdXEkQkX9zs_9sDcIHobt4UoXf17tXl1JFj0NpNKUZs2JHTUXjW8kW-JxxBs6Zwhjjixyg6CRiroGorNIuUodSiQFyCMRfMu2md_n-A5NS77544o0R57uHuyUlJF1Ch_vw5pLa7BbPcfAyuiswfaKtuABfLzhHmZ0I20or2ZmvNSKZchU2bSQ42Yax9FxOSNAswytKmUufc9LA_Dbsnk6m0_on0J2ZJMY-GiYZ2NOKpjWTQ9h0L17venx8mUFbkTkZVzrwDdtSzUwfuyEcIl2Mb33EPnGesqZKEZm1AojxHtjBHozVs6OMHXCTNqqoHUE6-k4dcfAQu2sC31fa-sCb9RSSgdBhMM9rVToJXW4qhZVTgoBDbmQSs5dINEFMneB_KxDo1p3WQbTTLa8JEZih7hZh-vKF0vz37Od_G_4BWy-3Hbl033_8RS2BLKXotKvAevoH3eG7CPT5_kG-wLE1tIo |
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=Wear+indicator+construction+for+rolling+bearings+based+on+an+enhanced+and+unsupervised+stacked+auto-encoder&rft.jtitle=Soft+computing+%28Berlin%2C+Germany%29&rft.au=Zeng%2C+Wenhui&rft.au=Yu%2C+Lisha&rft.au=Xu%2C+Fan&rft.au=Huang%2C+Zhelin&rft.date=2024-08-01&rft.pub=Springer+Berlin+Heidelberg&rft.issn=1432-7643&rft.eissn=1433-7479&rft.volume=28&rft.issue=15-16&rft.spage=8835&rft.epage=8848&rft_id=info:doi/10.1007%2Fs00500-023-09068-x&rft.externalDocID=10_1007_s00500_023_09068_x |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1432-7643&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1432-7643&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1432-7643&client=summon |