Publication:
Transfer learning enabled bearing fault detection methods based on image representations of single-dimensional signals

dc.contributor.authorDeveci, Bilgin Umut
dc.contributor.authorÇeltikoğlu, Mert
dc.contributor.authorAlbayrak, Özlem
dc.contributor.authorÜnal, Perin
dc.contributor.authorKırcı, Pınar
dc.contributor.buuauthorÇeltikoğlu, Mert
dc.contributor.buuauthorKIRCI, PINAR
dc.contributor.departmentBursa Uludağ Üniversitesi/Mühendislik Fakültesi/Bilgisayar Mühendisliği Bölümü.
dc.contributor.researcheridHXH-8622-2023
dc.contributor.researcheridCZK-0182-2022
dc.date.accessioned2024-09-30T08:57:44Z
dc.date.available2024-09-30T08:57:44Z
dc.date.issued2024-02-21
dc.description.abstractBearings are vital components in rotating machinery. Undetected bearing faults may result not only in financial loss, but also in the loss of lives. Hence, there exists an abundance of studies working on the early detection of bearing faults. The rising use of deep learning in recent years increased the number of imaging types/neural network architectures used for bearing fault classification, making it challenging to choose the most suitable 2-D imaging method and neural network. This study aims to address this challenge, by sharing the results of the training of eighteen imaging methods with four different networks using the same vibration data and training metrics. To further strengthen the results, the validation dataset size was taken as five times the training dataset size. The best results obtained is 99.89% accuracy by using Scattergram Filter Bank 1 as the image input, and ResNet-50 as the network for training. Prior to our work, Scattergram images have never been used for bearing fault classification. Ten out of 72 methods used in this work resulted in accuracies higher than 99.5%.
dc.identifier.doi10.1007/s10796-023-10371-z
dc.identifier.endpage1397
dc.identifier.issn1387-3326
dc.identifier.issue4, Special Issue SI
dc.identifier.startpage1345
dc.identifier.urihttps://doi.org/10.1007/s10796-023-10371-z
dc.identifier.urihttps://link.springer.com/article/10.1007/s10796-023-10371-z
dc.identifier.urihttps://hdl.handle.net/11452/45486
dc.identifier.volume26
dc.identifier.wos000935851400001
dc.indexed.wosWOS.SCI
dc.language.isoen
dc.publisherSpringer
dc.relation.journalInformation Systems Frontiers
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectConvolutional neural-network
dc.subjectDiagnosis
dc.subjectFrequency
dc.subjectCnn
dc.subjectRolling bearings fault determination
dc.subjectTransfer learning
dc.subjectDefect detection
dc.subjectCnn
dc.subjectDeep learning
dc.subjectGooglenet
dc.subjectResnet-50
dc.subjectSqueezenet
dc.subjectInception-resnet-v2
dc.subjectSignal processing
dc.subjectTime-frequency images
dc.subjectScattergram
dc.subjectComputer science
dc.titleTransfer learning enabled bearing fault detection methods based on image representations of single-dimensional signals
dc.typeArticle
dc.typeEarly Access
dspace.entity.typePublication
relation.isAuthorOfPublication0270c3e7-f379-4f0e-84dd-a83c2bbf0235
relation.isAuthorOfPublication.latestForDiscovery0270c3e7-f379-4f0e-84dd-a83c2bbf0235

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Celtikoglu_vd_2024.pdf
Size:
14 MB
Format:
Adobe Portable Document Format

Collections