Repository logo
 
Publication

Fusing convolutional generative adversarial encoders for 3D printer fault detection with only normal condition signals

2021-01Journal article Restricted access
Simple item page
dc.contributor.authorLi, Chuan
dc.contributor.authorCabrera, Diego
dc.contributor.authorSancho, Fernando
dc.contributor.authorSanchez, Rene-Vinicio
dc.contributor.authorCerrada, Mariela
dc.contributor.authorLong, Jianyu
dc.contributor.authorOliveira, José Valente de
dc.date.accessioned2021-09-08T10:58:11Z
dc.date.available2021-09-08T10:58:11Z
dc.date.issued2021-01
dc.description.abstractCollecting data from mechanical systems in abnormal conditions is expensive and time consuming. Consequently, fault detection approaches based on classical supervised learning working with both normal and abnormal data are not applicable in some condition-based maintenance tasks. To address this problem, this paper proposes Fusing Convolutional Generative Adversarial Encoders (fCGAE) method to create fault detection models from only normal data. Firstly, to obtain an adequate deep feature space, encoder models based on 1D convolutional neural networks are created. Then, these encoders are optimized in an unsupervised way through Bidirectional Generative Adversarial Networks. Finally, the multi-channel features collected from the system are merged with One-Class Support Vector Machine. fCGAE is applied to fault detection in 3D printers, where experimental results in two fault detection cases show excellent generalization capabilities and better performance compared to peer methods. (C) 2020 Elsevier Ltd. All rights reserved.
dc.description.sponsorshipGIDTEC Research Group of Universidad Politecnica Salesiana; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [51775112, 71801046]; National Key RD Program [2016YFE0132200]; MoST Science and Technology Partnership Program [KY201802006]; Chongqing Natural Science FoundationNatural Science Foundation of Chongqing [cstc2019jcyjzdxmX0013]; CTBU Project [KFJJ2018107, KFJJ2018075]
dc.description.versioninfo:eu-repo/semantics/publishedVersion
dc.identifier.doi10.1016/j.ymssp.2020.107108
dc.identifier.issn0888-3270
dc.identifier.urihttp://hdl.handle.net/10400.1/17056
dc.language.isoeng
dc.peerreviewedyes
dc.publisherACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
dc.subjectFault detection
dc.subject3D printers
dc.subjectCondition-based maintenance
dc.subjectConvolutional neural networks
dc.subjectAdversarial learning
dc.subject.otherEngineering
dc.titleFusing convolutional generative adversarial encoders for 3D printer fault detection with only normal condition signals
dc.typejournal article
dspace.entity.typePublication
oaire.citation.startPage107108
oaire.citation.titleMechanical Systems and Signal Processing
oaire.citation.volume147
person.familyNameLUÍS VALENTE DE OLIVEIRA
person.givenNameJOSÉ
person.identifier.ciencia-id1F12-C1D3-7717
person.identifier.orcid0000-0001-5337-5699
rcaap.rightsrestrictedAccess
rcaap.typearticle
relation.isAuthorOfPublicationbb726e73-690c-4a33-822e-c47bdac3035b
relation.isAuthorOfPublication.latestForDiscoverybb726e73-690c-4a33-822e-c47bdac3035b

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
1-s2.0-S0888327020304945-main.pdf
Size:
1.9 MB
Format:
Adobe Portable Document Format
Download

Collections

FCT2-Artigos (em revistas ou actas indexadas)