Show simple item record

dc.contributor.authorArellano Espitia, Francisco
dc.contributor.authorSaucedo Dorantes, Juan Jose
dc.contributor.authorDelgado Prieto, Miquel
dc.contributor.authorOsornio Rios, Roque A.
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Enginyeria Electrònica
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Enginyeria Electrònica
dc.date.accessioned2020-01-23T19:21:19Z
dc.date.issued2019
dc.identifier.citationArellano, F. [et al.]. Autoencoder based feature reduction analysis applied to electromechanical systems condition monitoring. A: IEEE International Conference on Emerging Technologies and Factory Automation. "2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA): proceedings: University of Zaragoza, Zaragoza, Spain: 10-13 September, 2019". Institute of Electrical and Electronics Engineers (IEEE), 2019, p. 891-897.
dc.identifier.isbn978-1-7281-0303-7
dc.identifier.urihttp://hdl.handle.net/2117/175570
dc.description.abstractCondition monitoring in electromechanical systems represents, currently, one of the most critical challenges dealing with the advancement and modernization in intelligent manufacturing. In this regard, machine learning based algorithms widely applied in other technological fields are being considered now to face the automatic feature extraction on the electric machine monitoring. In this study, a monitoring scheme is considered for faults detection performance evaluation, where vibrations signal under different fault conditions are acquired. Thus, the common electric machine monitoring framework, that is, a set of features estimated from a limited number of measurements, is considered in front of the three main dimensionality reduction approaches: principal component analysis, linear discriminant analysis and auto-encoder based. Performance of the corresponding approaches are studied and discussed experimentally. It is revealed that, although scheme based on auto-encoder provides enhanced diagnosis results, it is still necessary to carry out a detailed study on the automatic extraction capabilities of important features for the detection of faults.
dc.format.extent7 p.
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
dc.subjectÀrees temàtiques de la UPC::Enginyeria elèctrica::Electromecànica
dc.subject.lcshArtificial intelligence
dc.subject.lcshElectromechanical devices
dc.subject.otherCondition monitoring
dc.subject.otherFault detection
dc.subject.otherDiagnostics and prognostics
dc.subject.otherDeep learning
dc.subject.otherAutoencoder
dc.titleAutoencoder based feature reduction analysis applied to electromechanical systems condition monitoring
dc.typeConference report
dc.subject.lemacIntel·ligència artificial
dc.subject.lemacDispositius electromecànics
dc.contributor.groupUniversitat Politècnica de Catalunya. MCIA - Motion Control and Industrial Applications Research Group
dc.identifier.doi10.1109/ETFA.2019.8869371
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://ieeexplore.ieee.org/document/8869371
dc.rights.accessRestricted access - publisher's policy
local.identifier.drac25969911
dc.description.versionPostprint (published version)
dc.date.lift10000-01-01
local.citation.authorArellano, F.; Saucedo, J.; Delgado Prieto, M.; Osornio, R.
local.citation.contributorIEEE International Conference on Emerging Technologies and Factory Automation
local.citation.publicationName2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA): proceedings: University of Zaragoza, Zaragoza, Spain: 10-13 September, 2019
local.citation.startingPage891
local.citation.endingPage897


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder