Performance comparison of artificial neural networks and expert systems applied to flow pattern identification in vertical ascendant gas-liquid flows

dc.creatorRosa, ES
dc.creatorSalgado, RM
dc.creatorOhishi, T
dc.creatorMastelari, N
dc.date2010
dc.dateSEP
dc.date2014-11-16T20:26:15Z
dc.date2015-11-26T17:26:34Z
dc.date2014-11-16T20:26:15Z
dc.date2015-11-26T17:26:34Z
dc.date.accessioned2018-03-29T00:13:44Z
dc.date.available2018-03-29T00:13:44Z
dc.identifierInternational Journal Of Multiphase Flow. Pergamon-elsevier Science Ltd, v. 36, n. 9, n. 738, n. 754, 2010.
dc.identifier0301-9322
dc.identifierWOS:000280936200004
dc.identifier10.1016/j.ijmultiphaseflow.2010.05.001
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/59241
dc.identifierhttp://www.repositorio.unicamp.br/handle/REPOSIP/59241
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/59241
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1284577
dc.descriptionInstantaneous readouts of an electrical resistivity probe are taken in an upward vertical air-water mixture. The signals are further processed to render the statistical moments and the probability density functions here used as objective flow pattern indicators. A series of 73 experimental runs have its flow pattern identified by visual inspection assisted by the analyses of the void fraction's trace and associated probability density function. The flow patterns are classified into six groups and labeled as: bubbly, spherical cap, slug, unstable slug, semi-annular and annular. This work compares and analyzes the performance of artificial neural networks, ANN, and expert systems to flow pattern identification. The employed ANNs are Multiple Layer Perceptrons, Radial Basis Functions and Probabilistic Neural Network. with single and multiple outputs. The performance is gauged by the percentage of right identifications based on experimental observation. The analysis is extended to clustering algorithms to assist the formation of knowledge base employed during the learning stages of the ANNs and expert systems. The performance of the following clustering algorithms: self organized maps. K-means and Fuzzy C-means are also tested against experimental data. (C) 2010 Elsevier Ltd. All rights reserved.
dc.description36
dc.description9
dc.description738
dc.description754
dc.descriptionPetrobras [0050.0018970.06.2-BR]
dc.descriptionPetrobras [0050.0018970.06.2-BR]
dc.languageen
dc.publisherPergamon-elsevier Science Ltd
dc.publisherOxford
dc.publisherInglaterra
dc.relationInternational Journal Of Multiphase Flow
dc.relationInt. J. Multiph. Flow
dc.rightsfechado
dc.rightshttp://www.elsevier.com/about/open-access/open-access-policies/article-posting-policy
dc.sourceWeb of Science
dc.subjectFlow pattern recognition
dc.subjectClustering algorithms
dc.subjectNeural networks
dc.subjectImpedance sensor
dc.subjectDifferential Pressure-fluctuations
dc.subject2-phase Flow
dc.subjectRegime Identification
dc.subjectVoid Fraction
dc.subjectObjective Flow
dc.subjectSlug Flow
dc.subjectTransition
dc.subjectSignals
dc.subjectClassification
dc.subjectTransform
dc.titlePerformance comparison of artificial neural networks and expert systems applied to flow pattern identification in vertical ascendant gas-liquid flows
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución