Multi source heterogeneous data diagnosis method of rotating machinery based on parameter collaborative optimization of multi-scale convolutional autoencoder

In order to fully utilize the features of multi-source heterogeneous data and effectively improve the accuracy and efficiency of fault diagnosis of rotating machinery, a multi-source heterogeneous data diagnosis method based on parameter collaborative optimization multi-scale convolutional autoencod...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of Vibroengineering
1. Verfasser: Yang, Xiaoli
Format: Journal Article
Sprache:Englisch
Veröffentlicht: 28.10.2025
ISSN:1392-8716, 2538-8460
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In order to fully utilize the features of multi-source heterogeneous data and effectively improve the accuracy and efficiency of fault diagnosis of rotating machinery, a multi-source heterogeneous data diagnosis method based on parameter collaborative optimization multi-scale convolutional autoencoder (MSCAE) is proposed. Firstly, multi-scale information learning is integrated into the convolutional autoencoder (CAE) to consider the temporal and spatial feature information of the diagnostic object simultaneously. To improve the training and diagnostic efficiency of MSCAE, a quantum particle swarm optimization (QPSO) module is used to perform hyperparameter optimization on it using chaos initialization and dynamic weight strategy (DWS). Besides, the sparse attention mechanism is introduced into the MSCAE model to improve the recognition rate of key fault features hidden in the original heterogeneous signals. Finally, the confusion matrix and visualization techniques are used to achieve fault classification. The experimental results demonstrate that after 100 experiments, the proposed method has an average diagnostic accuracy of 98.5 % and strong robustness to noise, providing a new method for rotating machinery fault diagnosis based on multi-source heterogeneous data.
AbstractList In order to fully utilize the features of multi-source heterogeneous data and effectively improve the accuracy and efficiency of fault diagnosis of rotating machinery, a multi-source heterogeneous data diagnosis method based on parameter collaborative optimization multi-scale convolutional autoencoder (MSCAE) is proposed. Firstly, multi-scale information learning is integrated into the convolutional autoencoder (CAE) to consider the temporal and spatial feature information of the diagnostic object simultaneously. To improve the training and diagnostic efficiency of MSCAE, a quantum particle swarm optimization (QPSO) module is used to perform hyperparameter optimization on it using chaos initialization and dynamic weight strategy (DWS). Besides, the sparse attention mechanism is introduced into the MSCAE model to improve the recognition rate of key fault features hidden in the original heterogeneous signals. Finally, the confusion matrix and visualization techniques are used to achieve fault classification. The experimental results demonstrate that after 100 experiments, the proposed method has an average diagnostic accuracy of 98.5 % and strong robustness to noise, providing a new method for rotating machinery fault diagnosis based on multi-source heterogeneous data.
Author Yang, Xiaoli
Author_xml – sequence: 1
  givenname: Xiaoli
  surname: Yang
  fullname: Yang, Xiaoli
BookMark eNotkMtOwzAQRS1UJErpmq1_IK3tOE6yRBUvqYgNrKOJM2mNEruynUrlX_hX3MJqNLpHdzTnlsyss0jIPWcrwYu6WH8dcSWYKFai4LW8InNR5FVWScVmZM7zWmRVydUNWYZgWiZlKRVnck5-3qYhGhrc5DXSPUb0bocW3RRoBxFoZ2BnXTCBjhj3rqOup95FiMbu6Ah6byz6E20hYMosPYCH8VxDtRsGaJ1P6BGpO0Qzmu-0JCh1jOe7WdAwYCLt0Q3TOYKBwhQdWu069Hfkuoch4PJ_Lsjn0-PH5iXbvj-_bh62meZKxaxSNVQo87rKWauYyHvNtS6ZLgRw2RVQl0IzBOAKUabvewWAlShBlarTLF-Q9V-v9i4Ej31z8GYEf2o4ay6CmyS4OQtuLoLzX--8dls
Cites_doi 10.1080/00224065.2021.1960934
10.1088/1361-6501/ac41a5
10.55730/1300-0632.3909
10.1088/1361-6501/aadfb3
10.1016/j.isatra.2022.06.035
10.1088/1361-6501/ac543a
10.1016/j.compind.2019.02.004
10.1016/j.dib.2023.109049
10.1016/j.measurement.2020.108518
10.1007/s40430-023-04567-2
10.1109/TII.2018.2793246
10.3390/en12060995
10.1016/j.ress.2022.108528
10.1016/j.promfg.2019.06.075
10.1007/978-981-19-0572-8_92
10.3390/s20010176
10.1016/j.measurement.2021.109685
10.1063/5.0095530
10.1109/TIM.2022.3212542
10.1109/ACCESS.2020.3011980
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.21595/jve.2025.25194
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
EISSN 2538-8460
ExternalDocumentID 10_21595_jve_2025_25194
GroupedDBID AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
M~E
ID FETCH-LOGICAL-c166t-869a8e439830b6023fc1cc70c52a14d5a972c0eaa16ee4044f6aae827a676dc03
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001608946700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1392-8716
IngestDate Wed Oct 29 21:23:23 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c166t-869a8e439830b6023fc1cc70c52a14d5a972c0eaa16ee4044f6aae827a676dc03
OpenAccessLink https://www.extrica.com/article/25194/pdf
ParticipantIDs crossref_primary_10_21595_jve_2025_25194
PublicationCentury 2000
PublicationDate 2025-10-28
PublicationDateYYYYMMDD 2025-10-28
PublicationDate_xml – month: 10
  year: 2025
  text: 2025-10-28
  day: 28
PublicationDecade 2020
PublicationTitle Journal of Vibroengineering
PublicationYear 2025
References key-10.21595/jve.2025.25194-cit5
key-10.21595/jve.2025.25194-cit4
key-10.21595/jve.2025.25194-cit7
key-10.21595/jve.2025.25194-cit6
key-10.21595/jve.2025.25194-cit1
key-10.21595/jve.2025.25194-cit3
key-10.21595/jve.2025.25194-cit2
key-10.21595/jve.2025.25194-cit9
key-10.21595/jve.2025.25194-cit20
key-10.21595/jve.2025.25194-cit8
key-10.21595/jve.2025.25194-cit21
key-10.21595/jve.2025.25194-cit24
key-10.21595/jve.2025.25194-cit25
key-10.21595/jve.2025.25194-cit22
key-10.21595/jve.2025.25194-cit23
key-10.21595/jve.2025.25194-cit26
key-10.21595/jve.2025.25194-cit10
key-10.21595/jve.2025.25194-cit13
key-10.21595/jve.2025.25194-cit14
key-10.21595/jve.2025.25194-cit11
key-10.21595/jve.2025.25194-cit12
key-10.21595/jve.2025.25194-cit17
key-10.21595/jve.2025.25194-cit18
key-10.21595/jve.2025.25194-cit15
key-10.21595/jve.2025.25194-cit16
key-10.21595/jve.2025.25194-cit19
References_xml – ident: key-10.21595/jve.2025.25194-cit21
  doi: 10.1080/00224065.2021.1960934
– ident: key-10.21595/jve.2025.25194-cit19
– ident: key-10.21595/jve.2025.25194-cit1
– ident: key-10.21595/jve.2025.25194-cit5
  doi: 10.1088/1361-6501/ac41a5
– ident: key-10.21595/jve.2025.25194-cit3
  doi: 10.55730/1300-0632.3909
– ident: key-10.21595/jve.2025.25194-cit14
  doi: 10.1088/1361-6501/aadfb3
– ident: key-10.21595/jve.2025.25194-cit8
  doi: 10.1016/j.isatra.2022.06.035
– ident: key-10.21595/jve.2025.25194-cit2
  doi: 10.1088/1361-6501/ac543a
– ident: key-10.21595/jve.2025.25194-cit9
  doi: 10.1016/j.compind.2019.02.004
– ident: key-10.21595/jve.2025.25194-cit26
  doi: 10.1016/j.dib.2023.109049
– ident: key-10.21595/jve.2025.25194-cit15
  doi: 10.1016/j.measurement.2020.108518
– ident: key-10.21595/jve.2025.25194-cit6
  doi: 10.1007/s40430-023-04567-2
– ident: key-10.21595/jve.2025.25194-cit12
– ident: key-10.21595/jve.2025.25194-cit17
  doi: 10.1109/TII.2018.2793246
– ident: key-10.21595/jve.2025.25194-cit18
– ident: key-10.21595/jve.2025.25194-cit25
  doi: 10.3390/en12060995
– ident: key-10.21595/jve.2025.25194-cit20
  doi: 10.1016/j.ress.2022.108528
– ident: key-10.21595/jve.2025.25194-cit23
  doi: 10.1016/j.promfg.2019.06.075
– ident: key-10.21595/jve.2025.25194-cit24
  doi: 10.1007/978-981-19-0572-8_92
– ident: key-10.21595/jve.2025.25194-cit10
  doi: 10.3390/s20010176
– ident: key-10.21595/jve.2025.25194-cit22
  doi: 10.1016/j.measurement.2021.109685
– ident: key-10.21595/jve.2025.25194-cit7
  doi: 10.1063/5.0095530
– ident: key-10.21595/jve.2025.25194-cit16
  doi: 10.1109/TIM.2022.3212542
– ident: key-10.21595/jve.2025.25194-cit4
  doi: 10.1109/ACCESS.2020.3011980
– ident: key-10.21595/jve.2025.25194-cit13
– ident: key-10.21595/jve.2025.25194-cit11
SSID ssib044746104
Score 2.3474343
SecondaryResourceType online_first
Snippet In order to fully utilize the features of multi-source heterogeneous data and effectively improve the accuracy and efficiency of fault diagnosis of rotating...
SourceID crossref
SourceType Index Database
Title Multi source heterogeneous data diagnosis method of rotating machinery based on parameter collaborative optimization of multi-scale convolutional autoencoder
WOSCitedRecordID wos001608946700001&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: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2538-8460
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044746104
  issn: 1392-8716
  databaseCode: M~E
  dateStart: 20070101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtZ3NbtQwEICt0nLggkAF8VMqHzhUigyJ49jOEaFWPUDFoa32FjmOjRaxSbW7XZVL36Tv2hnHm2YpSOXAJVp5rdmsP2tmbM-MCXnvwWbnVnLmhS-YqFPNtK8NM7nXHmaIrOuQKPxFnZzoyaT8FsPGFuE6AdW2-uqqvPivqKENYGPq7D_gHoRCA3wG6PAE7PB8EPiQUpv0m_LgB8K4ddDXYagrhoPibisG100X8fZodBfnHZ7It9-TWYitdPNfCZq3Bo8SsDj4DMUkozmzckkHymYWszjDKT3-LlsA8xAAv4p_EmsRXC47rJfZxEjg-77wOSzaoctQGnHQRXE3ezI13c_peIeCh8qmfKxUwQdjuDDrbU5o46howfdJ_6TGwQ0pseTFjxUWMuXFB0yvFXcWa31K_5shG8ILYWETRFQgoEIBVRDwiOxwVZQY-Pf1-nCtdYRQWHO-v_04vmhfAyrI-Lj5EiP3ZeSHnD4jT-Og0U89-Odky7W75CZApz10ugGdInQ6QKc9dNp5uoZOB-g0QKddSwfodAM6HUNHGSPodAM6HUF_Qc6ODk8_H7N48QazmZRLpmVptANXVedpLcGr8zazVqW24CYTTWFKxW3qjMmkcwJG0EtjnObKSCUbm-YvyXbbte4VRs6V2ooSvk4bYfJUC6e4c7bQmfW1cK_JwXo8q4u-vkr1F3xvHt71LXlyNxH3yPZyfunekcd2tZwu5vsB_y0jU33a
linkProvider ISSN International Centre
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=Multi+source+heterogeneous+data+diagnosis+method+of+rotating+machinery+based+on+parameter+collaborative+optimization+of+multi-scale+convolutional+autoencoder&rft.jtitle=Journal+of+Vibroengineering&rft.au=Yang%2C+Xiaoli&rft.date=2025-10-28&rft.issn=1392-8716&rft.eissn=2538-8460&rft_id=info:doi/10.21595%2Fjve.2025.25194&rft.externalDBID=n%2Fa&rft.externalDocID=10_21595_jve_2025_25194
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1392-8716&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1392-8716&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1392-8716&client=summon