Repository logo
 
Publication

Exploiting generative adversarial networks as an oversampling method for fault diagnosis of an industrial robotic manipulator

2020Journal article Open access
Simple item page
dc.contributor.authorPu, Ziqiang
dc.contributor.authorCabrera, Diego
dc.contributor.authorSánchez, René-Vinicio
dc.contributor.authorCerrada, Mariela
dc.contributor.authorLi, Chuan
dc.contributor.authorValente de Oliveira, José
dc.date.accessioned2020-12-11T11:16:34Z
dc.date.available2020-12-11T11:16:34Z
dc.date.issued2020
dc.description.abstractData-driven machine learning techniques play an important role in fault diagnosis, safety, and maintenance of the industrial robotic manipulator. However, these methods require data that, more often that not, are hard to obtain, especially data collected from fault condition states and, without enough and appropriated (balanced) data, no acceptable performance should be expected. Generative adversarial networks (GAN) are receiving a significant interest, especially in the image analysis field due to their outstanding generative capabilities. This paper investigates whether or not GAN can be used as an oversampling tool to compensate for an unbalanced data set in an industrial manipulator fault diagnosis task. A comprehensive empirical analysis is performed taking into account six different scenarios for mitigating the unbalanced data, including classical under and oversampling (SMOTE) methods. In all of these, a wavelet packet transform is used for feature generation while a random forest is used for fault classification. Aspects such as loss functions, learning curves, random input distributions, data shuffling, and initial conditions were also considered. A non-parametric statistical test of hypotheses reveals that all GAN based fault-diagnosis outperforms both under and oversampling classical methods while, within GAN based methods, an average accuracy difference as high as 1.68% can be achieved.pt_PT
dc.description.sponsorshipFCT-through IDMEC, under LAETA, project UIDB/50022/2020.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.3390/app10217712pt_PT
dc.identifier.eissn2076-3417
dc.identifier.urihttp://hdl.handle.net/10400.1/14898
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherMDPIpt_PT
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt_PT
dc.subjectFeature extractionpt_PT
dc.subjectGenerative adversarial networkpt_PT
dc.subjectUnbalance datapt_PT
dc.subjectFault diagnosispt_PT
dc.subjectRandom forestpt_PT
dc.titleExploiting generative adversarial networks as an oversampling method for fault diagnosis of an industrial robotic manipulatorpt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.citation.issue21pt_PT
oaire.citation.startPage7712pt_PT
oaire.citation.titleApplied Sciencespt_PT
oaire.citation.volume10pt_PT
person.familyNameLUÍS VALENTE DE OLIVEIRA
person.givenNameJOSÉ
person.identifier.ciencia-id1F12-C1D3-7717
person.identifier.orcid0000-0001-5337-5699
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublicationbb726e73-690c-4a33-822e-c47bdac3035b
relation.isAuthorOfPublication.latestForDiscoverybb726e73-690c-4a33-822e-c47bdac3035b

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
applsci-10-07712-v2.pdf
Size:
9.39 MB
Format:
Adobe Portable Document Format
Download

Collections

FCT2-Artigos (em revistas ou actas indexadas)