Show simple item record

dc.contributor.authorCamacho-Navarro, Jhonatan
dc.contributor.authorRuiz Ordóñez, Magda
dc.contributor.authorVillamizar Mejía, Rodolfo
dc.contributor.authorMujica Delgado, Luis Eduardo
dc.contributor.authorMoreno Beltran, Gustavo Adolfo
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Matemàtiques
dc.date.accessioned2017-06-23T08:03:32Z
dc.date.available2017-06-23T08:03:32Z
dc.date.issued2017
dc.identifier.citationCamacho-Navarro, J., Ruiz, M., Villamizar, R., Mujica, L.E., Moreno, G. Ensemble learning as approach for pipeline condition assessment. A: International Conference on Damage Assessment of Structures. "DAMAS 2017: 12th International Conference on Damage Assessment of Structures : Kitakyushu, Japó: July 10-12, 2017: proceedings book". Kitakyushu: Ghent University, 2017, p. 1-9.
dc.identifier.urihttp://hdl.handle.net/2117/105753
dc.description.abstractThe algorithms commonly used for damage condition monitoring present several drawbacks related to unbalanced data, optimal training requirements, low capability to manage feature diversity and low tolerance to errors. In this work, an approach based on ensemble learning is discussed as alternative to obtain more efficient diagnosis. The main advantage of ensemble learning is the use of several algorithms at the same time for a better proficiency. Thereby, combining simplest tree decision algorithms in bagging scheme, the accuracy of damage detection is improved. It takes advantage by combining prediction of preliminary algorithms based on regression models. The methodology is experimentally validated on a carbon steel pipe section, where mass adding conditions are studied as possible failures. Data from an active system based on piezoelectric sensors are stored and characterized through the T2 and Q statistical indexes. Then, they are the inputs to the ensemble learning. The proposed methodology allows determining the condition assessment and damage localizations in the structure. The results of the studied cases show the feasibility of ensemble learning for detecting occurrence of structural damages with successful results.
dc.format.extent9 p.
dc.language.isoeng
dc.publisherGhent University
dc.rightsAttribution 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Enginyeria elèctrica
dc.subject.lcshLearning
dc.subject.lcshStructural health monitoring
dc.titleEnsemble learning as approach for pipeline condition assessment
dc.typeConference report
dc.subject.lemacAprenentatge
dc.contributor.groupUniversitat Politècnica de Catalunya. CoDAlab - Control, Modelització, Identificació i Aplicacions
dc.rights.accessOpen Access
drac.iddocument21087040
dc.description.versionPostprint (published version)
upcommons.citation.authorCamacho-Navarro, J.; Ruiz, M.; Villamizar, R.; Mujica, L.E.; Moreno, G.
upcommons.citation.contributorInternational Conference on Damage Assessment of Structures
upcommons.citation.pubplaceKitakyushu
upcommons.citation.publishedtrue
upcommons.citation.publicationNameDAMAS 2017: 12th International Conference on Damage Assessment of Structures : Kitakyushu, Japó: July 10-12, 2017: proceedings book
upcommons.citation.startingPage1
upcommons.citation.endingPage9


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Except where otherwise noted, content on this work is licensed under a Creative Commons license: Attribution 3.0 Spain