Mostra el registre d'ítem simple

dc.contributor.authorZurita Millán, Daniel
dc.contributor.authorSala Cardoso, Enric
dc.contributor.authorCariño Corrales, Jesús Adolfo
dc.contributor.authorDelgado Prieto, Miquel
dc.contributor.authorOrtega Redondo, Juan Antonio
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Enginyeria Electrònica
dc.date.accessioned2016-11-24T15:48:10Z
dc.date.available2018-11-24T01:30:47Z
dc.date.issued2016
dc.identifier.citationZurita, D., Sala, E., Cariño , J.A., Delgado Prieto, M., Ortega, J.A. Industrial process monitoring by means of recurrent neural networks and Self Organizing Maps. A: IEEE International Conference on Emerging Technologies and Factory Automation. "2016 IEEE 21st International Conference on Emerging Technologies and Factory Automation (ETFA): 6-9 Sept. 2016". Berlin: IEEE Press, 2016.
dc.identifier.isbn978-1-5090-1314-2
dc.identifier.urihttp://hdl.handle.net/2117/97192
dc.description.abstractIndustrial manufacturing plants often suffer from reliability problems during their day-to-day operations which have the potential for causing a great impact on the effectiveness and performance of the overall process and the sub-processes involved. Time-series forecasting of critical industrial signals presents itself as a way to reduce this impact by extracting knowledge regarding the internal dynamics of the process and advice any process deviations before it affects the productive process. In this paper, a novel industrial condition monitoring approach based on the combination of Self Organizing Maps for operating point codification and Recurrent Neural Networks for critical signal modeling is proposed. The combination of both methods presents a strong synergy, the information of the operating condition given by the interpretation of the maps helps the model to improve generalization, one of the drawbacks of recurrent networks, while assuring high accuracy and precision rates. Finally, the complete methodology, in terms of performance and effectiveness is validated experimentally with real data from a copper rod industrial plant.
dc.language.isoeng
dc.publisherIEEE Press
dc.subjectÀrees temàtiques de la UPC::Informàtica::Automàtica i control
dc.subjectÀrees temàtiques de la UPC::Informàtica::Robòtica
dc.subject.lcshArtificial intelligence
dc.subject.lcshMachinery--Monitoring.
dc.subject.othercondition monitoring
dc.subject.otherknowledge acquisition
dc.subject.otherprocess monitoring
dc.subject.otherproduction engineering computing
dc.subject.otherrecurrent neural nets
dc.subject.otherself-organising feature maps
dc.subject.otherindustrial process monitoring
dc.subject.otherrecurrent neural network
dc.subject.otherself-organizing map
dc.subject.otherindustrial manufacturing plant
dc.subject.otherreliability problem
dc.subject.otherday-to-day operation
dc.subject.othercritical industrial signal time-series forecasting
dc.subject.otherknowledge extraction
dc.subject.otherinternal dynamics
dc.subject.otherproductive process
dc.subject.otherindustrial condition monitoring approach
dc.subject.otheroperating point codification
dc.subject.othercritical signal modeling
dc.subject.othercopper rod industrial plant
dc.titleIndustrial process monitoring by means of recurrent neural networks and Self Organizing Maps
dc.typeConference report
dc.subject.lemacIntel·ligència artificial
dc.subject.lemacMaquinària -- Monitoratge
dc.contributor.groupUniversitat Politècnica de Catalunya. MCIA - Motion Control and Industrial Applications Research Group
dc.identifier.doi10.1109/ETFA.2016.7733534
dc.rights.accessOpen Access
local.identifier.drac19287331
dc.description.versionPostprint (published version)
local.citation.authorZurita, D.; Sala, E.; Cariño, J.A.; Delgado Prieto, M.; Ortega, J.A.
local.citation.contributorIEEE International Conference on Emerging Technologies and Factory Automation
local.citation.pubplaceBerlin
local.citation.publicationName2016 IEEE 21st International Conference on Emerging Technologies and Factory Automation (ETFA): 6-9 Sept. 2016


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple