Roller bearing fault diagnosis using stacked denoising autoencoder in deep learning and Gath–Geva clustering algorithm without principal component analysis and data label
Most deep learning models such as stacked autoencoder (SAE) and stacked denoising autoencoder (SDAE) are used for fault diagnosis with a data label. These models are applied to extract the useful features with several hidden layers, then a classifier is used to complete the fault diagnosis. However,...
Gespeichert in:
| Veröffentlicht in: | Applied soft computing Jg. 73; S. 898 - 913 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Elsevier B.V
01.12.2018
|
| Schlagworte: | |
| ISSN: | 1568-4946, 1872-9681 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Most deep learning models such as stacked autoencoder (SAE) and stacked denoising autoencoder (SDAE) are used for fault diagnosis with a data label. These models are applied to extract the useful features with several hidden layers, then a classifier is used to complete the fault diagnosis. However, these fault diagnosis classification methods are only suitable for tagged datasets. Actually, many datasets are untagged in practical engineering. The clustering method can classify data without a label. Therefore, a method based on the SDAE and Gath–Geva (GG) clustering algorithm for roller bearing fault diagnosis without a data label is proposed in this study. First, SDAE is selected to extract the useful feature and reduce the dimension of the vibration signal to two or three dimensions direct without principal component analysis (PCA) of the final hidden layer. Then GG is deployed to identify the different faults. To demonstrate that the feature extraction performance of the SDAE is better than that of the SAE and EEMD with the FE model, the PCA is selected to reduce the dimension of eigenvectors obtained from several previously hidden layers, except for the final hidden layer. Compared with SAE and ensemble empirical mode decomposition (EEMD)-fuzzy entropy (FE) models, the results show that as the number of the hidden layers increases, all the fault samples under different conditions are separated better by using SDAE rather than those feature extraction models mentioned. In addition, three evaluation indicators such as PC, CE, and classification accuracy are used to assess the performance of the method presented. Finally, the results show that the clustering effect of the method presented, and its classification accuracy are superior to those of the other combination models, including the SAE-fuzzy C-means (FCM)/Gustafson–Kessel (GK)/GG and EEMD-fuzzy entropy FE-PCA-FCM/GK/GG.
•Reduce the dimension of extracted feature using SDAE directly without PCA.•Fulfilling the bearing fault diagnosis by using SDAE and clustering model without data label.•Using the SDAE reduce the high dimension to 2 or 3 directly from frequency domain feature directly after FFT decomposition. |
|---|---|
| AbstractList | Most deep learning models such as stacked autoencoder (SAE) and stacked denoising autoencoder (SDAE) are used for fault diagnosis with a data label. These models are applied to extract the useful features with several hidden layers, then a classifier is used to complete the fault diagnosis. However, these fault diagnosis classification methods are only suitable for tagged datasets. Actually, many datasets are untagged in practical engineering. The clustering method can classify data without a label. Therefore, a method based on the SDAE and Gath–Geva (GG) clustering algorithm for roller bearing fault diagnosis without a data label is proposed in this study. First, SDAE is selected to extract the useful feature and reduce the dimension of the vibration signal to two or three dimensions direct without principal component analysis (PCA) of the final hidden layer. Then GG is deployed to identify the different faults. To demonstrate that the feature extraction performance of the SDAE is better than that of the SAE and EEMD with the FE model, the PCA is selected to reduce the dimension of eigenvectors obtained from several previously hidden layers, except for the final hidden layer. Compared with SAE and ensemble empirical mode decomposition (EEMD)-fuzzy entropy (FE) models, the results show that as the number of the hidden layers increases, all the fault samples under different conditions are separated better by using SDAE rather than those feature extraction models mentioned. In addition, three evaluation indicators such as PC, CE, and classification accuracy are used to assess the performance of the method presented. Finally, the results show that the clustering effect of the method presented, and its classification accuracy are superior to those of the other combination models, including the SAE-fuzzy C-means (FCM)/Gustafson–Kessel (GK)/GG and EEMD-fuzzy entropy FE-PCA-FCM/GK/GG.
•Reduce the dimension of extracted feature using SDAE directly without PCA.•Fulfilling the bearing fault diagnosis by using SDAE and clustering model without data label.•Using the SDAE reduce the high dimension to 2 or 3 directly from frequency domain feature directly after FFT decomposition. |
| Author | Tse, Yiu Lun Xu, Fan Tse, Wai tai Peter |
| Author_xml | – sequence: 1 givenname: Fan orcidid: 0000-0003-1735-5011 surname: Xu fullname: Xu, Fan – sequence: 2 givenname: Wai tai Peter surname: Tse fullname: Tse, Wai tai Peter email: Peter.W.Tse@cityu.edu.hk – sequence: 3 givenname: Yiu Lun surname: Tse fullname: Tse, Yiu Lun |
| BookMark | eNp9kEFuHCEQRVHkSLGdXCArLtBt6KYZWsomspJxJEuRInuNaqB6zISBEdCOvPMdfA2fyicJPc4qC28A_dL7xf9n5CTEgIR85qzljMuLXQs5mrZjXLVsbFm_ekdOuVp1zSgVP6nvQapGjEJ-IGc571iFxk6dkudf0XtMdIOQXNjSCWZfqHWwDTG7TOe8qLmA-Y2WWgzRHRWYS8Rgoq2sC3WAB-qrRzgOg6VrKHcvj09rvAdq_JwLHv3Bb2Ny5W5P_9QzzoUeqm7cATw1cX-osUKpBuAflvWLk4UC1MMG_UfyfgKf8dO_-5zcfv92c3nVXP9c_7j8et2YXqjSKN7LSbLNSkqmhJCTkN04QRUGtLYbBLPGotr0I_ZWwMCtqP9nQzfZcaV4158T9eprUsw54aSNK1BcDCWB85ozvbSud3ppXS-tazbq2npFu__Qmm8P6eFt6MsrhDXUvcOks3G1XbQuoSnaRvcW_hfzWaR9 |
| CitedBy_id | crossref_primary_10_1016_j_asoc_2020_106577 crossref_primary_10_1016_j_measurement_2022_111594 crossref_primary_10_1016_j_aei_2022_101708 crossref_primary_10_1016_j_asoc_2022_108912 crossref_primary_10_3390_s20205734 crossref_primary_10_1109_ACCESS_2020_2972859 crossref_primary_10_1007_s00521_023_08949_4 crossref_primary_10_1109_TIM_2024_3472786 crossref_primary_10_1007_s11571_020_09642_1 crossref_primary_10_1007_s11042_023_15325_w crossref_primary_10_1016_j_jmsy_2020_07_003 crossref_primary_10_1109_ACCESS_2021_3056944 crossref_primary_10_1155_2020_8509142 crossref_primary_10_1109_TII_2024_3476547 crossref_primary_10_1109_TSMC_2021_3130232 crossref_primary_10_1007_s00500_023_09068_x crossref_primary_10_1093_tse_tdac050 crossref_primary_10_1007_s12206_025_0102_z crossref_primary_10_1016_j_asoc_2020_106886 crossref_primary_10_1177_14759217231221214 crossref_primary_10_1016_j_asoc_2022_109958 crossref_primary_10_1016_j_neucom_2019_06_073 crossref_primary_10_1080_23307706_2020_1759466 crossref_primary_10_1177_14759217221113323 crossref_primary_10_1007_s10489_021_03004_y crossref_primary_10_1177_1475921720963951 crossref_primary_10_1109_TII_2025_3568512 crossref_primary_10_1016_j_asoc_2021_107284 crossref_primary_10_1088_1361_6501_ac1461 crossref_primary_10_1155_2020_5013871 crossref_primary_10_1016_j_asoc_2020_106119 crossref_primary_10_1007_s40430_024_04866_2 crossref_primary_10_1016_j_measurement_2019_107371 crossref_primary_10_1109_TIM_2021_3116309 crossref_primary_10_3390_s25072246 crossref_primary_10_1109_TII_2021_3116145 crossref_primary_10_3390_machines10100849 crossref_primary_10_3390_s23031305 crossref_primary_10_1016_j_cie_2020_106427 crossref_primary_10_1177_1475921719893594 crossref_primary_10_1016_j_measurement_2020_107788 crossref_primary_10_1109_ACCESS_2020_3028465 crossref_primary_10_1016_j_measurement_2020_107902 crossref_primary_10_1109_ACCESS_2021_3056767 crossref_primary_10_1016_j_asoc_2019_105975 crossref_primary_10_1109_JSEN_2025_3560460 crossref_primary_10_1109_ACCESS_2019_2963092 crossref_primary_10_1016_j_measurement_2024_116216 crossref_primary_10_1016_j_jfranklin_2020_04_024 crossref_primary_10_1016_j_knosys_2022_109399 crossref_primary_10_1007_s00170_021_08392_6 crossref_primary_10_1016_j_ress_2020_107396 crossref_primary_10_1016_j_measurement_2021_110023 crossref_primary_10_1007_s40430_022_03973_2 crossref_primary_10_1016_j_measurement_2025_117098 crossref_primary_10_1109_ACCESS_2024_3397184 crossref_primary_10_1109_TIM_2021_3063189 crossref_primary_10_1016_j_asoc_2022_109785 crossref_primary_10_1016_j_asoc_2020_106992 |
| Cites_doi | 10.1109/CDC.1978.268028 10.1016/j.sigpro.2014.09.005 10.1109/T-C.1975.224317 10.1177/1077546314550221 10.1098/rspa.1998.0193 10.1016/j.energy.2018.08.048 10.1016/j.apenergy.2018.06.092 10.1109/TII.2015.2500098 10.1016/j.medengphy.2008.04.005 10.1109/ICPHM.2011.6024349 10.1007/s10916-009-9340-3 10.1145/1390156.1390294 10.1109/34.192473 10.1073/pnas.88.6.2297 10.1016/j.ymssp.2006.02.009 10.1016/j.sigpro.2015.01.001 10.1016/j.jsv.2011.07.014 10.1016/j.jsv.2009.10.021 10.1142/S1793536909000047 10.1002/cem.2912 10.1109/ACCESS.2017.2728010 10.1016/j.ymssp.2017.03.034 10.1016/j.neucom.2014.08.092 10.1016/j.compmedimag.2016.03.003 10.1631/jzus.A0900360 10.1016/j.ymssp.2013.07.006 10.1016/j.knosys.2017.07.023 10.1016/j.eswa.2010.02.118 10.1016/j.measurement.2015.03.017 |
| ContentType | Journal Article |
| Copyright | 2018 Elsevier B.V. |
| Copyright_xml | – notice: 2018 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.asoc.2018.09.037 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-9681 |
| EndPage | 913 |
| ExternalDocumentID | 10_1016_j_asoc_2018_09_037 S1568494618305544 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 23M 4.4 457 4G. 53G 5GY 5VS 6J9 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HVGLF HZ~ IHE J1W JJJVA KOM M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SDF SDG SES SEW SPC SPCBC SST SSV SSZ T5K UHS UNMZH ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c348t-8136f60b76608446f4629fa0b75edd2540dcde8b39e3d4a51d4dee052fd978123 |
| ISICitedReferencesCount | 69 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000450124900062&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1568-4946 |
| IngestDate | Sat Nov 29 03:05:35 EST 2025 Tue Nov 18 22:18:59 EST 2025 Fri Feb 23 02:24:52 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Roller bearing fault diagnosis Gath–Geva clustering algorithm Stacked denoising autoencoder |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c348t-8136f60b76608446f4629fa0b75edd2540dcde8b39e3d4a51d4dee052fd978123 |
| ORCID | 0000-0003-1735-5011 |
| PageCount | 16 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_asoc_2018_09_037 crossref_primary_10_1016_j_asoc_2018_09_037 elsevier_sciencedirect_doi_10_1016_j_asoc_2018_09_037 |
| 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 | Applied soft computing |
| PublicationYear | 2018 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Zhang, Liang, Zang (b7) 2015; 69 Tang, Li, Lai (b41) 2018; 228 Wu, Huang (b6) 2009; 1 Resta, Ripamonti, Cazzluani (b2) 2011; 329 Bezdek, Dunn (b32) 1975 Leng, Chen, Mao (b39) 2018; 143 Dolz, Betrouni, Quidet (b40) 2016; 52 Xu, Fang, Zhang (b33) 2016; 22 Xiong, Zhang, Liu (b38) 2010; 11 Huang, Wu, Wang (b1) 2012; 31 D.E. Gustafson, W.C. Kessel, Fuzzy clustering with fuzzy covariance matrix, in: IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes, 1979, pp. 761–766. Bagordo, Cazzluani, Resta (b3) 2011; 330 Yi, Wang, Wei (b10) 2018; 18 Chen, Zhuang, Yu (b37) 2009; 31 Xu, Fang, Kong (b26) 2016; 4 Wang, Li, Zhang (b30) 2013; 24 Wang, Guo, Tse (b11) 2014; 22 Van, Kang (b13) 2016; 12 Tan, Eswaran (b15) 2011; 35 Leng, Guo, Zhang, Zhang (b22) 2015; 112 Zhang, Zhou (b8) 2013; 41 Shao, Jiang, Zhao (b12) 2017; 95 Feng, Lei, Jing (b14) 2016 Qi, Shen, Wang (b17) 2017; 5 Guo, Shen, Chen (b27) 2017; 7 Gath, Geva (b31) 1989; 11 Tang, Shen, Wang (b19) 2018 Li, Struzik, Zhang, Cichocki (b24) 2014; 165 Vincent, Larochelle, Lajoie (b20) 2010; 11 Tang, Wu, Li (b42) 2018; 162 Zhang, Sun, Li (b28) 2013; 34 Q. Miao, D. Wang, M. Pecht, Rolling element bearing fault feature extraction using EMD-based independent component analysis, in: IEEE PHM, 2011, pp. 1–6. Case Western Reserve University. Bearing data center test seeded fault test data. . Huang, Shen, Long (b5) 1998; 454 Liu, Feng, Zhou (b23) 2015; 120 Zhang, Xiong, Liu (b25) 2010; 37 (Accessed 2013). Yan, Gao (b36) 2007; 21 Lv, Wen, Liu (b16) 2017; 31 P. Vincent, H. Larochelle, Y. Bengio, Extracting and composing robust features with denoising autoencoders, in: International Conference, 2008, pp. 1096–1103. Wang, Zhao, Pei (b18) 2016; 5 Wang, Tong (b4) 2014; 33 Pincus (b35) 1991; 55 Feng (10.1016/j.asoc.2018.09.037_b14) 2016 Vincent (10.1016/j.asoc.2018.09.037_b20) 2010; 11 10.1016/j.asoc.2018.09.037_b29 Xiong (10.1016/j.asoc.2018.09.037_b38) 2010; 11 Lv (10.1016/j.asoc.2018.09.037_b16) 2017; 31 Tang (10.1016/j.asoc.2018.09.037_b41) 2018; 228 Liu (10.1016/j.asoc.2018.09.037_b23) 2015; 120 Zhang (10.1016/j.asoc.2018.09.037_b28) 2013; 34 Leng (10.1016/j.asoc.2018.09.037_b22) 2015; 112 10.1016/j.asoc.2018.09.037_b21 Yan (10.1016/j.asoc.2018.09.037_b36) 2007; 21 Li (10.1016/j.asoc.2018.09.037_b24) 2014; 165 Gath (10.1016/j.asoc.2018.09.037_b31) 1989; 11 Huang (10.1016/j.asoc.2018.09.037_b5) 1998; 454 Leng (10.1016/j.asoc.2018.09.037_b39) 2018; 143 Xu (10.1016/j.asoc.2018.09.037_b26) 2016; 4 Tang (10.1016/j.asoc.2018.09.037_b19) 2018 Dolz (10.1016/j.asoc.2018.09.037_b40) 2016; 52 Zhang (10.1016/j.asoc.2018.09.037_b7) 2015; 69 Zhang (10.1016/j.asoc.2018.09.037_b25) 2010; 37 Shao (10.1016/j.asoc.2018.09.037_b12) 2017; 95 Resta (10.1016/j.asoc.2018.09.037_b2) 2011; 329 Wang (10.1016/j.asoc.2018.09.037_b11) 2014; 22 10.1016/j.asoc.2018.09.037_b34 Xu (10.1016/j.asoc.2018.09.037_b33) 2016; 22 10.1016/j.asoc.2018.09.037_b9 Tang (10.1016/j.asoc.2018.09.037_b42) 2018; 162 Huang (10.1016/j.asoc.2018.09.037_b1) 2012; 31 Wang (10.1016/j.asoc.2018.09.037_b18) 2016; 5 Bagordo (10.1016/j.asoc.2018.09.037_b3) 2011; 330 Zhang (10.1016/j.asoc.2018.09.037_b8) 2013; 41 Yi (10.1016/j.asoc.2018.09.037_b10) 2018; 18 Pincus (10.1016/j.asoc.2018.09.037_b35) 1991; 55 Wang (10.1016/j.asoc.2018.09.037_b4) 2014; 33 Wang (10.1016/j.asoc.2018.09.037_b30) 2013; 24 Bezdek (10.1016/j.asoc.2018.09.037_b32) 1975 Tan (10.1016/j.asoc.2018.09.037_b15) 2011; 35 Qi (10.1016/j.asoc.2018.09.037_b17) 2017; 5 Wu (10.1016/j.asoc.2018.09.037_b6) 2009; 1 Chen (10.1016/j.asoc.2018.09.037_b37) 2009; 31 Van (10.1016/j.asoc.2018.09.037_b13) 2016; 12 Guo (10.1016/j.asoc.2018.09.037_b27) 2017; 7 |
| References_xml | – volume: 18 start-page: 1 year: 2018 end-page: 21 ident: b10 article-title: EEMD based steady-state indexes and their applications to condition monitoring and fault diagnosis of railway axle bearings publication-title: Sensors – reference: P. Vincent, H. Larochelle, Y. Bengio, Extracting and composing robust features with denoising autoencoders, in: International Conference, 2008, pp. 1096–1103. – volume: 7 start-page: 1 year: 2017 end-page: 17 ident: b27 article-title: Deep fault recognizer: An integrated model to denoise and extract features for fault diagnosis in rotating machinery publication-title: Appl. Sci.-Basel. – volume: 11 start-page: 773 year: 1989 end-page: 781 ident: b31 article-title: Unsupervised optimal fuzzy clustering publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 31 start-page: 1 year: 2017 end-page: 16 ident: b16 article-title: Weighted time series fault diagnosis based on a stacked sparse autoencoder publication-title: J. Chemometrics – start-page: 835 year: 1975 end-page: 838 ident: b32 article-title: Optimal fuzzy partitions: A heuristic forb estimating the parameters in a mixture of normal dustrubutions publication-title: IEEE Trans. Comput. – volume: 120 start-page: 761 year: 2015 end-page: 766 ident: b23 article-title: Multimodal video classification with stacked contractive autoencoders publication-title: Signal Process. – reference: Q. Miao, D. Wang, M. Pecht, Rolling element bearing fault feature extraction using EMD-based independent component analysis, in: IEEE PHM, 2011, pp. 1–6. – volume: 24 start-page: 3036 year: 2013 end-page: 3044 ident: b30 article-title: Mechanical fault diagnosis method based on EEMD sample entropy and GK fuzzy clustering publication-title: Chin. J. Sci. Instrum. – volume: 69 start-page: 164 year: 2015 end-page: 179 ident: b7 article-title: A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM publication-title: Measurement – volume: 22 start-page: 2631 year: 2016 end-page: 2642 ident: b33 article-title: PCA-GG rolling bearing clustering fault diagnosis based on EEMD fuzzy entropy publication-title: Comput.-Integr. Manuf. Syst. – reference: D.E. Gustafson, W.C. Kessel, Fuzzy clustering with fuzzy covariance matrix, in: IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes, 1979, pp. 761–766. – volume: 31 start-page: 91 year: 2012 end-page: 94 ident: b1 article-title: Test for active control of boom vibration of a concrete pump truck publication-title: J. Vib. Shock – volume: 143 start-page: 295 year: 2018 end-page: 306 ident: b39 article-title: Combining granular computing technique with deep learning forservice planning under social manufacturing contexts publication-title: Knowl.-Based Syst. – volume: 37 start-page: 6077 year: 2010 end-page: 6085 ident: b25 article-title: Bearing fault diagnosis using multi-scale entropy and adaptive neuro-fuzzy inference publication-title: Expert Syst. Appl. – volume: 22 start-page: 2603 year: 2014 end-page: 2618 ident: b11 article-title: An enhanced empirical mode decomposition method for blind component separation of a single-channel vibration signal mixture publication-title: J. Vib. Control – volume: 228 start-page: 254 year: 2018 end-page: 264 ident: b41 article-title: A novel optimal energymanagement strategy for a maritime hybrid energy system based on largescale global optimization publication-title: Appl. Energy – volume: 34 start-page: 714 year: 2013 end-page: 720 ident: b28 article-title: Study on mechanical fault diagnosis method based on LMD approximate entropy and fuzzy C-means clustering publication-title: Chin. J. Sci. Instrum. – volume: 329 start-page: 961 year: 2011 end-page: 972 ident: b2 article-title: Independent modal control for nonlinear flexible structures: an experimental test rig publication-title: J. Sound Vib. – volume: 33 start-page: 63 year: 2014 end-page: 70 ident: b4 article-title: Nonlinear dynamical behavior analysis on rigid flexible coupling mechanical arm of hydraulic excavator publication-title: J. Vib. Shock – volume: 41 start-page: 127 year: 2013 end-page: 140 ident: b8 article-title: Multi-fault diagnosis for rolling element bearings based on ensemble empirical mode decomposition and optimized support vector machines publication-title: Mech. Syst. Signal Process. – volume: 454 start-page: 903 year: 1998 end-page: 995 ident: b5 article-title: The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis publication-title: Proc. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci. – volume: 5 start-page: 1 year: 2016 end-page: 13 ident: b18 article-title: ransformer fault diagnosis using continuous sparse autoencoder publication-title: Springerplus – volume: 35 start-page: 49 year: 2011 end-page: 58 ident: b15 article-title: Using autoencoders for mammogram compression publication-title: J. Med. Syst. – volume: 330 start-page: 6061 year: 2011 end-page: 6069 ident: b3 article-title: A modal disturbance estimator for vibration suppression in nonlinear flexible structures publication-title: J. Sound Vib. – volume: 1 start-page: 1 year: 2009 end-page: 41 ident: b6 article-title: Ensemble empirical mode decomposition: a noise-assisted data analysis method publication-title: Adv. Adapt. Data Anal. – volume: 12 start-page: 124 year: 2016 end-page: 135 ident: b13 article-title: Bearing defect classification based on individual wavelet local fisher discriminant analysis with particle swarm optimization publication-title: IEEE Trans. Ind. Inf. – reference: Case Western Reserve University. Bearing data center test seeded fault test data. – start-page: 1 year: 2018 end-page: 14 ident: b19 article-title: Adaptive deep feature learning network with Nesterov momentum and its application to rotating machinery fault diagnosis publication-title: Neurocomputing – volume: 11 start-page: 270 year: 2010 end-page: 279 ident: b38 article-title: A comparative study on apen sampen and their fuzzy counterparts in a multiscale framework for feature extraction publication-title: J. Zhejiang Univ. Sci. A (Appl. Phys. Eng). – volume: 95 start-page: 187 year: 2017 end-page: 204 ident: b12 article-title: A novel deep autoencoder feature learning method for rotating machinery fault diagnosis publication-title: Mech. Syst. Signal Process. – volume: 162 start-page: 697 year: 2018 end-page: 714 ident: b42 article-title: Optimal operation of photovoltaic/battery/diesel/coldironing hybrid energy system for maritime application publication-title: Energy – start-page: 303 year: 2016 end-page: 315 ident: b14 article-title: Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data publication-title: Mech. Syst. Signal Process. – volume: 21 start-page: 824 year: 2007 end-page: 839 ident: b36 article-title: Approximate entropy as a diagnostic tool for machine health monitoring publication-title: Mech. Syst. Signal Process. – reference: . (Accessed 2013). – volume: 5 start-page: 15066 year: 2017 end-page: 15079 ident: b17 article-title: Stacked sparse autoencoder-based deep network for fault diagnosis of rotating machinery publication-title: IEEE Access – reference: . – volume: 31 start-page: 61 year: 2009 end-page: 68 ident: b37 article-title: Measuring complexity using FuzzyEn, ApEn, and SampEn publication-title: Med. Eng. Phys. – volume: 11 start-page: 3371 year: 2010 end-page: 3408 ident: b20 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J. Mach. Learn. Res. – volume: 165 start-page: 23 year: 2014 end-page: 31 ident: b24 article-title: Feature learning from incomplete EEG with denoising autoencoder publication-title: Neurocomputing – volume: 55 start-page: 2297 year: 1991 end-page: 2301 ident: b35 article-title: Approximate entropy as a measure of system complexity publication-title: Proc. Natl. Acad. Sci. – volume: 4 start-page: 383 year: 2016 end-page: 394 ident: b26 article-title: A fault diagnosis method based on MBSE and PSO-SVM for roller bearings publication-title: J. Vib. Eng. Technol. – volume: 112 start-page: 119 year: 2015 end-page: 128 ident: b22 article-title: 3D object retrieval with stacked local convolutional autoencoder publication-title: Signal Process. – volume: 52 start-page: 8 year: 2016 end-page: 18 ident: b40 article-title: Stacking denoising auto-encoders in a deep network to segment thebrainstem on MRI in brain cancer patients: A clinical study publication-title: Comput. Med. Imaging Graph. – volume: 31 start-page: 91 issue: 2 year: 2012 ident: 10.1016/j.asoc.2018.09.037_b1 article-title: Test for active control of boom vibration of a concrete pump truck publication-title: J. Vib. Shock – ident: 10.1016/j.asoc.2018.09.037_b29 doi: 10.1109/CDC.1978.268028 – volume: 5 start-page: 1 year: 2016 ident: 10.1016/j.asoc.2018.09.037_b18 article-title: ransformer fault diagnosis using continuous sparse autoencoder publication-title: Springerplus – volume: 112 start-page: 119 year: 2015 ident: 10.1016/j.asoc.2018.09.037_b22 article-title: 3D object retrieval with stacked local convolutional autoencoder publication-title: Signal Process. doi: 10.1016/j.sigpro.2014.09.005 – start-page: 835 year: 1975 ident: 10.1016/j.asoc.2018.09.037_b32 article-title: Optimal fuzzy partitions: A heuristic forb estimating the parameters in a mixture of normal dustrubutions publication-title: IEEE Trans. Comput. doi: 10.1109/T-C.1975.224317 – volume: 7 start-page: 1 issue: 41 year: 2017 ident: 10.1016/j.asoc.2018.09.037_b27 article-title: Deep fault recognizer: An integrated model to denoise and extract features for fault diagnosis in rotating machinery publication-title: Appl. Sci.-Basel. – volume: 22 start-page: 2603 issue: 11 year: 2014 ident: 10.1016/j.asoc.2018.09.037_b11 article-title: An enhanced empirical mode decomposition method for blind component separation of a single-channel vibration signal mixture publication-title: J. Vib. Control doi: 10.1177/1077546314550221 – volume: 454 start-page: 903 year: 1998 ident: 10.1016/j.asoc.2018.09.037_b5 article-title: The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis publication-title: Proc. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci. doi: 10.1098/rspa.1998.0193 – volume: 162 start-page: 697 year: 2018 ident: 10.1016/j.asoc.2018.09.037_b42 article-title: Optimal operation of photovoltaic/battery/diesel/coldironing hybrid energy system for maritime application publication-title: Energy doi: 10.1016/j.energy.2018.08.048 – volume: 34 start-page: 714 issue: 3 year: 2013 ident: 10.1016/j.asoc.2018.09.037_b28 article-title: Study on mechanical fault diagnosis method based on LMD approximate entropy and fuzzy C-means clustering publication-title: Chin. J. Sci. Instrum. – volume: 228 start-page: 254 year: 2018 ident: 10.1016/j.asoc.2018.09.037_b41 article-title: A novel optimal energymanagement strategy for a maritime hybrid energy system based on largescale global optimization publication-title: Appl. Energy doi: 10.1016/j.apenergy.2018.06.092 – volume: 12 start-page: 124 year: 2016 ident: 10.1016/j.asoc.2018.09.037_b13 article-title: Bearing defect classification based on individual wavelet local fisher discriminant analysis with particle swarm optimization publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2015.2500098 – volume: 31 start-page: 61 year: 2009 ident: 10.1016/j.asoc.2018.09.037_b37 article-title: Measuring complexity using FuzzyEn, ApEn, and SampEn publication-title: Med. Eng. Phys. doi: 10.1016/j.medengphy.2008.04.005 – start-page: 1 year: 2018 ident: 10.1016/j.asoc.2018.09.037_b19 article-title: Adaptive deep feature learning network with Nesterov momentum and its application to rotating machinery fault diagnosis publication-title: Neurocomputing – volume: 24 start-page: 3036 issue: 22 year: 2013 ident: 10.1016/j.asoc.2018.09.037_b30 article-title: Mechanical fault diagnosis method based on EEMD sample entropy and GK fuzzy clustering publication-title: Chin. J. Sci. Instrum. – ident: 10.1016/j.asoc.2018.09.037_b9 doi: 10.1109/ICPHM.2011.6024349 – volume: 11 start-page: 3371 year: 2010 ident: 10.1016/j.asoc.2018.09.037_b20 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J. Mach. Learn. Res. – ident: 10.1016/j.asoc.2018.09.037_b34 – volume: 35 start-page: 49 year: 2011 ident: 10.1016/j.asoc.2018.09.037_b15 article-title: Using autoencoders for mammogram compression publication-title: J. Med. Syst. doi: 10.1007/s10916-009-9340-3 – ident: 10.1016/j.asoc.2018.09.037_b21 doi: 10.1145/1390156.1390294 – volume: 11 start-page: 773 issue: 7 year: 1989 ident: 10.1016/j.asoc.2018.09.037_b31 article-title: Unsupervised optimal fuzzy clustering publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.192473 – volume: 55 start-page: 2297 year: 1991 ident: 10.1016/j.asoc.2018.09.037_b35 article-title: Approximate entropy as a measure of system complexity publication-title: Proc. Natl. Acad. Sci. doi: 10.1073/pnas.88.6.2297 – volume: 21 start-page: 824 year: 2007 ident: 10.1016/j.asoc.2018.09.037_b36 article-title: Approximate entropy as a diagnostic tool for machine health monitoring publication-title: Mech. Syst. Signal Process. doi: 10.1016/j.ymssp.2006.02.009 – volume: 120 start-page: 761 year: 2015 ident: 10.1016/j.asoc.2018.09.037_b23 article-title: Multimodal video classification with stacked contractive autoencoders publication-title: Signal Process. doi: 10.1016/j.sigpro.2015.01.001 – volume: 330 start-page: 6061 issue: 25 year: 2011 ident: 10.1016/j.asoc.2018.09.037_b3 article-title: A modal disturbance estimator for vibration suppression in nonlinear flexible structures publication-title: J. Sound Vib. doi: 10.1016/j.jsv.2011.07.014 – volume: 329 start-page: 961 issue: 8 year: 2011 ident: 10.1016/j.asoc.2018.09.037_b2 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 – volume: 1 start-page: 1 year: 2009 ident: 10.1016/j.asoc.2018.09.037_b6 article-title: Ensemble empirical mode decomposition: a noise-assisted data analysis method publication-title: Adv. Adapt. Data Anal. doi: 10.1142/S1793536909000047 – volume: 31 start-page: 1 issue: 9 year: 2017 ident: 10.1016/j.asoc.2018.09.037_b16 article-title: Weighted time series fault diagnosis based on a stacked sparse autoencoder publication-title: J. Chemometrics doi: 10.1002/cem.2912 – start-page: 303 year: 2016 ident: 10.1016/j.asoc.2018.09.037_b14 article-title: Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data publication-title: Mech. Syst. Signal Process. – volume: 5 start-page: 15066 year: 2017 ident: 10.1016/j.asoc.2018.09.037_b17 article-title: Stacked sparse autoencoder-based deep network for fault diagnosis of rotating machinery publication-title: IEEE Access doi: 10.1109/ACCESS.2017.2728010 – volume: 18 start-page: 1 issue: 704 year: 2018 ident: 10.1016/j.asoc.2018.09.037_b10 article-title: EEMD based steady-state indexes and their applications to condition monitoring and fault diagnosis of railway axle bearings publication-title: Sensors – volume: 95 start-page: 187 year: 2017 ident: 10.1016/j.asoc.2018.09.037_b12 article-title: A novel deep autoencoder feature learning method for rotating machinery fault diagnosis publication-title: Mech. Syst. Signal Process. doi: 10.1016/j.ymssp.2017.03.034 – volume: 165 start-page: 23 year: 2014 ident: 10.1016/j.asoc.2018.09.037_b24 article-title: Feature learning from incomplete EEG with denoising autoencoder publication-title: Neurocomputing doi: 10.1016/j.neucom.2014.08.092 – volume: 22 start-page: 2631 issue: 11 year: 2016 ident: 10.1016/j.asoc.2018.09.037_b33 article-title: PCA-GG rolling bearing clustering fault diagnosis based on EEMD fuzzy entropy publication-title: Comput.-Integr. Manuf. Syst. – volume: 52 start-page: 8 year: 2016 ident: 10.1016/j.asoc.2018.09.037_b40 article-title: Stacking denoising auto-encoders in a deep network to segment thebrainstem on MRI in brain cancer patients: A clinical study publication-title: Comput. Med. Imaging Graph. doi: 10.1016/j.compmedimag.2016.03.003 – volume: 11 start-page: 270 issue: 4 year: 2010 ident: 10.1016/j.asoc.2018.09.037_b38 article-title: A comparative study on apen sampen and their fuzzy counterparts in a multiscale framework for feature extraction publication-title: J. Zhejiang Univ. Sci. A (Appl. Phys. Eng). doi: 10.1631/jzus.A0900360 – volume: 4 start-page: 383 year: 2016 ident: 10.1016/j.asoc.2018.09.037_b26 article-title: A fault diagnosis method based on MBSE and PSO-SVM for roller bearings publication-title: J. Vib. Eng. Technol. – volume: 41 start-page: 127 year: 2013 ident: 10.1016/j.asoc.2018.09.037_b8 article-title: Multi-fault diagnosis for rolling element bearings based on ensemble empirical mode decomposition and optimized support vector machines publication-title: Mech. Syst. Signal Process. doi: 10.1016/j.ymssp.2013.07.006 – volume: 143 start-page: 295 year: 2018 ident: 10.1016/j.asoc.2018.09.037_b39 article-title: Combining granular computing technique with deep learning forservice planning under social manufacturing contexts publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2017.07.023 – volume: 37 start-page: 6077 year: 2010 ident: 10.1016/j.asoc.2018.09.037_b25 article-title: Bearing fault diagnosis using multi-scale entropy and adaptive neuro-fuzzy inference publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2010.02.118 – volume: 33 start-page: 63 issue: 1 year: 2014 ident: 10.1016/j.asoc.2018.09.037_b4 article-title: Nonlinear dynamical behavior analysis on rigid flexible coupling mechanical arm of hydraulic excavator publication-title: J. Vib. Shock – volume: 69 start-page: 164 year: 2015 ident: 10.1016/j.asoc.2018.09.037_b7 article-title: A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM publication-title: Measurement doi: 10.1016/j.measurement.2015.03.017 |
| SSID | ssj0016928 |
| Score | 2.4872768 |
| Snippet | Most deep learning models such as stacked autoencoder (SAE) and stacked denoising autoencoder (SDAE) are used for fault diagnosis with a data label. These... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 898 |
| SubjectTerms | Deep learning Gath–Geva clustering algorithm Roller bearing fault diagnosis Stacked denoising autoencoder |
| Title | Roller bearing fault diagnosis using stacked denoising autoencoder in deep learning and Gath–Geva clustering algorithm without principal component analysis and data label |
| URI | https://dx.doi.org/10.1016/j.asoc.2018.09.037 |
| Volume | 73 |
| WOSCitedRecordID | wos000450124900062&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-9681 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0016928 issn: 1568-4946 databaseCode: AIEXJ dateStart: 20010601 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3NbtNAEF6FlgMX_lHLn_bAzTLyz3q9PlaoFFBVIRFEOFlrew2uUsdK7KhH3oHX4Dl4EJ6Emf1xQosqQOIQK9p415vM55nx5JsZQp6FvGCiKkqfgb_rs0Rmvky49KMU2zrEEmyQThQ-Tk9OxGyWvZ1MvrtcmPU8bVtxfp51_1XUMAbCxtTZvxD3uCgMwHsQOhxB7HD8I8FjmW219Ar4XpolKYd5jyFWZNQ1K29Y2QgC3L6VB1pn0egROfQLLGqJtSU0Q1Z1rqWEyWI8Al_RUSPiI7XGrMoByyzoE-afFsum_3ymA7vIde5MFF-XHznrFq3hstsKKLgeclM9wKDl7LtKuNYrXoF50DOH3hlXgMVs0M72BtFT0xfyg2y8Hl6_sI3tZx-bwTse2u3wRiguUEUu590YNc2FzzIbvFRmTKSRn3HTAMbp9jTeUs7C9Lu2dj4zObCXTIiJZpw-l3B3IPVPmDq46cZgjjTGd7gP3AboxQD8MnaN7EZpkoF23T14fTh7M_6fxTPd5Xfct03fMkzDi1f6vYu05fZMb5Ob9nmFHhic3SET1d4lt1wvEGpNwz3yzcCOWthRDTs6wo5q2FELOzrCjm7BjjYtRdhRBzsKMKEIux9fviLg6AZwdAQctYCjI-DoCDjqAKdXQsBRDbj75P3Lw-mLV77tBOKXMRO9L8KY1zwoUs4DwRivGY-yWsJAoqoqgqeOqqyUKOJMxRWTSVgx2G-QRHWFNd2i-AHZaeHCe4TWZZ0IGURYJYpJLIsrVViEsK6oeRqqfRK6Hz8vbZl87NYyzx0f8jRHgeUosDzIchDYPvHGOZ0pEnPl2YmTaW7dXOO-5gDBK-Y9_Md5j8iNzY31mOz0y0E9IdfLdd-slk8tUn8C_VnUzg |
| 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=Roller+bearing+fault+diagnosis+using+stacked+denoising+autoencoder+in+deep+learning+and+Gath%E2%80%93Geva+clustering+algorithm+without+principal+component+analysis+and+data+label&rft.jtitle=Applied+soft+computing&rft.au=Xu%2C+Fan&rft.au=Tse%2C+Wai+tai+Peter&rft.au=Tse%2C+Yiu+Lun&rft.date=2018-12-01&rft.pub=Elsevier+B.V&rft.issn=1568-4946&rft.eissn=1872-9681&rft.volume=73&rft.spage=898&rft.epage=913&rft_id=info:doi/10.1016%2Fj.asoc.2018.09.037&rft.externalDocID=S1568494618305544 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1568-4946&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1568-4946&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1568-4946&client=summon |