Fault Diagnosis of Rolling Bearing Using Convolutional Denoising Autoencoder and Siamese Neural Network With Small Sample

Bearing fault diagnosis is critical for ensuring mechanical reliability and operational safety. Industrial Internet of Things (IIoT) sensors provide real-time monitoring data, advancing research in data-driven approaches to bearing fault diagnosis. However, current studies overlook two key challenge...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE internet of things journal Vol. 12; no. 5; pp. 5233 - 5244
Main Authors:	Zhao, Xufeng, Chen, Ying, Yang, Mengshu, Xiang, Jiawei
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 01.03.2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Artificial neural networks Automation Classification Convolution Convolutional codes Convolutional denoising autoencoder (DAE) Data models Decoding Fault diagnosis Feature extraction Industrial applications Industrial Internet of Things Internet of Things Neural networks Noise Noise reduction Real time Roller bearings rolling bearing Rolling bearings siamese neural network signal processing small sample Training White noise
ISSN:	2327-4662, 2327-4662
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Bearing fault diagnosis is critical for ensuring mechanical reliability and operational safety. Industrial Internet of Things (IIoT) sensors provide real-time monitoring data, advancing research in data-driven approaches to bearing fault diagnosis. However, current studies overlook two key challenges: 1) susceptibility to noise interference during fault signal acquisition and 2) the scarcity of fault data for effective diagnostic tasks in practical scenarios. To address these issues, this article proposes a novel method termed convolutional denoising autoencoder and siamese neural network (CDAE-SNN) for fault diagnosis in rolling bearings. This method is designed to be robust against noise and applicable in scenarios with limited data. Initially, Gaussian white noise is added to raw signals to simulate noisy signals encountered in real operating conditions. Subsequently, a convolutional denoising autoencoder (DAE) is constructed and optimized. The encoder in CDAE compresses feature information from samples into a lower dimensional space, while the decoder reconstructs signals to mitigate noise effects. Denoised signal sample pairs are then fed into a 2-D convolutional neural network-based siamese network to generate embedding vectors. Fault classification of rolling bearings is performed based on similarity metrics between sample pairs. Experimental results confirm the enhanced diagnostic accuracy of our proposed model across various signal-to-noise ratios and sample sizes. Furthermore, the model exhibits superior performance in classifying faults across diverse proportion of new categories.
AbstractList	Bearing fault diagnosis is critical for ensuring mechanical reliability and operational safety. Industrial Internet of Things (IIoT) sensors provide real-time monitoring data, advancing research in data-driven approaches to bearing fault diagnosis. However, current studies overlook two key challenges: 1) susceptibility to noise interference during fault signal acquisition and 2) the scarcity of fault data for effective diagnostic tasks in practical scenarios. To address these issues, this article proposes a novel method termed convolutional denoising autoencoder and siamese neural network (CDAE-SNN) for fault diagnosis in rolling bearings. This method is designed to be robust against noise and applicable in scenarios with limited data. Initially, Gaussian white noise is added to raw signals to simulate noisy signals encountered in real operating conditions. Subsequently, a convolutional denoising autoencoder (DAE) is constructed and optimized. The encoder in CDAE compresses feature information from samples into a lower dimensional space, while the decoder reconstructs signals to mitigate noise effects. Denoised signal sample pairs are then fed into a 2-D convolutional neural network-based siamese network to generate embedding vectors. Fault classification of rolling bearings is performed based on similarity metrics between sample pairs. Experimental results confirm the enhanced diagnostic accuracy of our proposed model across various signal-to-noise ratios and sample sizes. Furthermore, the model exhibits superior performance in classifying faults across diverse proportion of new categories.
Author	Xiang, Jiawei Yang, Mengshu Zhao, Xufeng Chen, Ying
Author_xml	– sequence: 1 givenname: Xufeng orcidid: 0000-0002-9423-5366 surname: Zhao fullname: Zhao, Xufeng email: zx.peak@outlook.com organization: College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing, China – sequence: 2 givenname: Ying surname: Chen fullname: Chen, Ying email: yingchen@nuaa.edu.cn organization: College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing, China – sequence: 3 givenname: Mengshu orcidid: 0009-0008-6093-3503 surname: Yang fullname: Yang, Mengshu email: yms8922@163.com organization: College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing, China – sequence: 4 givenname: Jiawei orcidid: 0000-0003-4028-985X surname: Xiang fullname: Xiang, Jiawei email: jwxiang@wzu.edu.cn organization: College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou, China
BookMark	eNp9kE1PAyEQhonRxM8fYOKBxHMrLBS6R61WaxpNbBuPGwrTilKowGr89-7aHowHOTCTyfNMMu8h2vXBA0KnlHQpJeXF_ehx2i1IwbuM92XZL3fQQcEK2eFCFLu_-n10ktIrIaTRerQUB-hrqGqX8bVVSx-STTgs8FNwzvolvgIV2zpL7T8I_iO4OtvglcPX4IP9mV_WOYDXwUDEyhs8sWoFCfAD1LEBHyB_hviGn21-wZOVcg5P1Grt4BjtLZRLcLKtR2g2vJkO7jrjx9vR4HLc0UXJc4cKYubKGFkuNPBSN48Wcq5pydicG-CGMGHmDSM4l0IXxFCietIYyrSSgh2h883edQzvNaRcvYY6NjekilFJuewzShpKbigdQ0oRFpW2WbXH5qisqyip2qirNuqqjbraRt2Y9I-5jnal4te_ztnGsQDwi5c9xnqCfQPeaY3m
CODEN	IITJAU
CitedBy_id	crossref_primary_10_1016_j_neucom_2025_131093
Cites_doi	10.1109/JSEN.2020.3030910 10.3390/s22093314 10.1109/JSEN.2024.3409768 10.1007/s11071-021-06393-4 10.1109/JIOT.2022.3168317 10.1016/j.ress.2023.109387 10.1109/CVPR.2006.100 10.1080/00207543.2022.2122621 10.1109/TII.2019.2943898 10.1016/j.ymssp.2017.08.002 10.1007/s10845-020-01579-w 10.1109/TR.2023.3328597 10.1088/1361-6501/ad57d9 10.1142/S0218539319500128 10.1109/JIOT.2024.3363837 10.1109/TII.2020.2968370 10.1145/3582688 10.1109/TIE.2016.2627020 10.1016/j.measurement.2016.04.007 10.1109/TIM.2024.3351254 10.1016/j.simpat.2022.102659 10.1109/TIM.2023.3293554 10.1109/JIOT.2024.3363610 10.3390/s17020425 10.1109/ACCESS.2019.2934233 10.1109/TMECH.2023.3267699 10.1109/JIOT.2020.3004452 10.1016/j.cie.2021.107451 10.1016/j.knosys.2022.109846
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
DOI	10.1109/JIOT.2024.3487989
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional
DatabaseTitleList	Computer and Information Systems Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	2327-4662
EndPage	5244
ExternalDocumentID	10_1109_JIOT_2024_3487989 10753356
Genre	orig-research
GrantInformation_xml	– fundername: Aeronautical Science Foundation of China Aviation Academy grantid: 2022Z057052002 funderid: 10.13039/501100001809 – fundername: National Natural Science Foundation of China grantid: 72471116; 52375116 funderid: 10.13039/501100001809
GroupedDBID	0R~ 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS IFIPE IPLJI JAVBF M43 OCL PQQKQ RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c294t-160dbadd79fce49cccc127bc1933b4de4d036dbdba64476c20d10a57dd13ca763
IEDL.DBID	RIE
ISICitedReferencesCount	4
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001433294700014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2327-4662
IngestDate	Tue Sep 23 21:26:54 EDT 2025 Sat Nov 29 08:10:30 EST 2025 Tue Nov 18 21:25:26 EST 2025 Wed Aug 27 01:49:26 EDT 2025
IsPeerReviewed	false
IsScholarly	true
Issue	5
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-c294t-160dbadd79fce49cccc127bc1933b4de4d036dbdba64476c20d10a57dd13ca763
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-4028-985X 0000-0002-9423-5366 0009-0008-6093-3503
PQID	3171478310
PQPubID	2040421
PageCount	12
ParticipantIDs	crossref_citationtrail_10_1109_JIOT_2024_3487989 crossref_primary_10_1109_JIOT_2024_3487989 proquest_journals_3171478310 ieee_primary_10753356
PublicationCentury	2000
PublicationDate	2025-03-01
PublicationDateYYYYMMDD	2025-03-01
PublicationDate_xml	– month: 03 year: 2025 text: 2025-03-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE internet of things journal
PublicationTitleAbbrev	JIoT
PublicationYear	2025
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref14 ref31 ref30 ref11 ref33 ref32 ref2 ref1 ref17 Li (ref15) 2020; 39 ref19 ref18 ref24 ref23 ref25 ref20 ref22 ref21 ref28 Li (ref10) 2020; 39 Koch (ref26) ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 Wang (ref16) 2018; 38
References_xml	– ident: ref13 doi: 10.1109/JSEN.2020.3030910 – volume: 38 start-page: 129 year: 2018 ident: ref16 article-title: Fault diagnosis of power transformer based on BR-DBN publication-title: Elect. Power Autom. Equip. – ident: ref9 doi: 10.3390/s22093314 – ident: ref17 doi: 10.1109/JSEN.2024.3409768 – ident: ref32 doi: 10.1007/s11071-021-06393-4 – ident: ref3 doi: 10.1109/JIOT.2022.3168317 – ident: ref23 doi: 10.1016/j.ress.2023.109387 – ident: ref27 doi: 10.1109/CVPR.2006.100 – ident: ref22 doi: 10.1080/00207543.2022.2122621 – ident: ref28 doi: 10.1109/TII.2019.2943898 – ident: ref14 doi: 10.1016/j.ymssp.2017.08.002 – ident: ref19 doi: 10.1007/s10845-020-01579-w – ident: ref7 doi: 10.1109/TR.2023.3328597 – volume: 39 start-page: 187 issue: 24 year: 2020 ident: ref10 article-title: Fault diagnosis of rolling bearing based on an improved convolutional neural network using SFLA publication-title: J. Vib. Shock – volume: 39 start-page: 89 year: 2020 ident: ref15 article-title: Rolling bearing fault diagnosis based on DBN algorithm improved with PSO publication-title: J. Vib. Shock – ident: ref33 doi: 10.1088/1361-6501/ad57d9 – ident: ref6 doi: 10.1142/S0218539319500128 – ident: ref2 doi: 10.1109/JIOT.2024.3363837 – ident: ref18 doi: 10.1109/TII.2020.2968370 – ident: ref25 doi: 10.1145/3582688 – ident: ref20 doi: 10.1109/TIE.2016.2627020 – ident: ref12 doi: 10.1016/j.measurement.2016.04.007 – ident: ref5 doi: 10.1109/TIM.2024.3351254 – ident: ref21 doi: 10.1016/j.simpat.2022.102659 – ident: ref29 doi: 10.1109/TIM.2023.3293554 – ident: ref1 doi: 10.1109/JIOT.2024.3363610 – ident: ref30 doi: 10.3390/s17020425 – start-page: 1 volume-title: Proc. ICML Deep Learn. Workshop ident: ref26 article-title: Siamese neural networks for one-shot image recognition – ident: ref31 doi: 10.1109/ACCESS.2019.2934233 – ident: ref8 doi: 10.1109/TMECH.2023.3267699 – ident: ref4 doi: 10.1109/JIOT.2020.3004452 – ident: ref11 doi: 10.1016/j.cie.2021.107451 – ident: ref24 doi: 10.1016/j.knosys.2022.109846
SSID	ssj0001105196
Score	2.3592136
Snippet	Bearing fault diagnosis is critical for ensuring mechanical reliability and operational safety. Industrial Internet of Things (IIoT) sensors provide real-time...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	5233
SubjectTerms	Artificial neural networks Automation Classification Convolution Convolutional codes Convolutional denoising autoencoder (DAE) Data models Decoding Fault diagnosis Feature extraction Industrial applications Industrial Internet of Things Internet of Things Neural networks Noise Noise reduction Real time Roller bearings rolling bearing Rolling bearings siamese neural network signal processing small sample Training White noise
Title	Fault Diagnosis of Rolling Bearing Using Convolutional Denoising Autoencoder and Siamese Neural Network With Small Sample
URI	https://ieeexplore.ieee.org/document/10753356 https://www.proquest.com/docview/3171478310
Volume	12
WOSCitedRecordID	wos001433294700014&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/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 2327-4662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001105196 issn: 2327-4662 databaseCode: RIE dateStart: 20140101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1BS-QwFA4qHvaiq6s4ris5eFqotmnaTI6u7qAeRmFc9FbS5BULYyszHcF_73tpZldYFOylpbyUwveSfC95eR9jRxVASjQ1cpW1kbToxtroLBqWIq60KOUQpBebUOPx8P5e34TD6v4sDAD45DM4pke_l-9au6ClMuzhSK7TLF9lq0rl_WGtfwsqCbGRPOxcJrE-ubq8vsUIUMjjFGm5JiX3N3OPF1P5bwT208po85M_9JVtBP7IT3vAt9gKNNtsc6nNwENX_cZeRmYx7fh5n0lXz3lb8VCAm_9C76a7TxfgZ23zHPwPP3wOTVv796eLrqUqlw4_axrHJzUl1AKnch5oOO7zx_ld3T3wyaOZTvnEUKnhHfZn9Pv27CIKMguRFVp2UZLHrsRhTunKgtQWr0So0iK1S0vpQDqc5VyJNsidVG5F7JLYZMq5JLUGx6ddtta0DewxXgk31A6UzCorRWmMwvAQINMlZBjYiAGLlwAUNtQgJymMaeFjkVgXhFlBmBUBswH7-bfJU1-A4yPjHQLpjWGPz4AdLGEuQh-dFylpvysSWtt_p9l39kWQ3K9POTtga91sAT_Yun3u6vns0LvfK264270
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB1BQYILLdCKhbb40BNSSuI4m_WxX6sW2gVpF9Fb5NgTNdI2Qd1sJf49M46XVkJUai6JonEU6Y3tN_Z4HsBehZgyTY1cZW2kLLmxNjqLRqWMKy1LNULlxSbyyWR0eam_h8Pq_iwMIvrkM9znR7-X71q75KUy6uFErtNs-BSeZUrJuD-udbekkjAfGYa9yyTWn7-cfZtRDCjVfkrEXLOW-73Zx8up_DMG-4llvP7IX9qAV4FBioMe8tfwBJs3sL5SZxChs76F32OznHfiuM-lqxeirUQowS0Oyb_57hMGxFHb3AYPpA8fY9PW_v3Bsmu5zqWjz5rGiWnNKbUouKAHGU76DHLxs-6uxPTazOdiarjY8Cb8GJ_Mjk6jILQQWalVFyXD2JU00OW6sqi0pSuReWmJ3KWlcqgczXOuJBtiT_nQytglscly55LUGhqhtmCtaRt8B6KSbqQd5iqrrJKlMTkFiIiZLjGj0EYOIF4BUNhQhZzFMOaFj0ZiXTBmBWNWBMwG8Olvk199CY6HjDcZpHuGPT4D2F7BXIReuihSVn_PWWrt_X-afYQXp7OL8-L8bPL1A7yULP7rE9C2Ya27WeIOPLe3Xb242fWu-Af_mN8E
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=Fault+Diagnosis+of+Rolling+Bearing+Using+Convolutional+Denoising+Autoencoder+and+Siamese+Neural+Network+With+Small+Sample&rft.jtitle=IEEE+internet+of+things+journal&rft.au=Zhao%2C+Xufeng&rft.au=Chen%2C+Ying&rft.au=Yang%2C+Mengshu&rft.au=Xiang%2C+Jiawei&rft.date=2025-03-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2327-4662&rft.volume=12&rft.issue=5&rft.spage=5233&rft_id=info:doi/10.1109%2FJIOT.2024.3487989&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2327-4662&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2327-4662&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2327-4662&client=summon