Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/349412
Full metadata record
DC FieldValueLanguage
dc.contributor.CRUESPUNIVERSIDADE ESTADUAL DE CAMPINASpt_BR
dc.contributor.authorunicampOliveira, Ricardo Coração de Leão Fontoura de-
dc.typeArtigopt_BR
dc.titleIntelligent co-simulation: neural network vs. proper orthogonal decomposition applied to a 2D diffusive problempt_BR
dc.contributor.authorBerger, Julien-
dc.contributor.authorMazuroski, Walter-
dc.contributor.authorOliveira, Ricardo C.L.F.-
dc.contributor.authorMendes, Nathan-
dc.subjectAprendizado de máquinapt_BR
dc.subject.otherlanguageMachine learningpt_BR
dc.description.abstractOne possibility to improve the accuracy of building performance simulation (BPS) tools is via co-simulation techniques, where more accurate mathematical models representing particular and complex physical phenomena are employed through data exchanging between the BPS and a specialized software where those models are available. This article performs a deeper investigation of a recently proposed co-simulation technique that presents as novelty the employment of artificial intelligence as a strategy to reduce the computational burden generally required by co-simulations. Basically, the strategy, known as intelligentco-simulation, constructs new mathematical models through a learning procedure (training period) that is performed using the input–output data generated by a standard co-simulation, where the models of specialized software are employed. Once the learning phase is complete, the specialized software is disconnected from the BPS and the simulation goes on by using the synthesized models, requiring a much lower computational cost and with a low impact on the accuracy of the results. The synthesis of accurate-and-fast models is performed through machine learning techniques and the purpose of this paper is precisely a deep investigation of two techniques – recurrent neural networks and proper orthogonal decomposition reduction method, whose main goal is to reduce the training time period and to improve the accuracy. The case study focuses on a co-simulation between Domus and CFX programs, performing a two-dimensional diffusive heat transfer problem through a building envelope. The results show that for a standard co-simulation of 14 h, the intelligent co-simulation provided a reduction of 90% in the computer run time with accuracy error at the order ofpt_BR
dc.relation.ispartofJournal of building performance simulationpt_BR
dc.publisher.cityAbingdonpt_BR
dc.publisher.countryReino Unidopt_BR
dc.publisherTaylor & Francispt_BR
dc.date.issued2018-
dc.language.isoengpt_BR
dc.description.volume11pt_BR
dc.description.issuenumber5pt_BR
dc.description.firstpage568pt_BR
dc.description.lastpage587pt_BR
dc.rightsFechadopt_BR
dc.sourceSCOPUSpt_BR
dc.identifier.issn1940-1493pt_BR
dc.identifier.eissn1940-1507pt_BR
dc.identifier.doi10.1080/19401493.2017.1414879pt_BR
dc.identifier.urlhttps://www.tandfonline.com/doi/full/10.1080/19401493.2017.1414879pt_BR
dc.description.sponsorshipCONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO - CNPQpt_BR
dc.description.sponsorshipCOORDENAÇÃO DE APERFEIÇOAMENTO DE PESSOAL DE NÍVEL SUPERIOR - CAPESpt_BR
dc.description.sponsorshipFUNDAÇÃO ARAUCÁRIA DE APOIO AO DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO DO ESTADO DO PARANÁ - FApt_BR
dc.description.sponsordocumentnumber307658/2013-9pt_BR
dc.description.sponsordocumentnumbernão tempt_BR
dc.description.sponsordocumentnumbernão tempt_BR
dc.date.available2020-09-16T16:13:51Z-
dc.date.accessioned2020-09-16T16:13:51Z-
dc.description.provenanceSubmitted by Mariana Aparecida Azevedo (mary1@unicamp.br) on 2020-09-16T16:13:51Z No. of bitstreams: 0. Added 1 bitstream(s) on 2021-01-08T19:03:16Z : No. of bitstreams: 1 2-s2.0-85041530580.pdf: 6482591 bytes, checksum: b73ebfee34e08fb264b9eef9f8160a8a (MD5)en
dc.description.provenanceMade available in DSpace on 2020-09-16T16:13:51Z (GMT). No. of bitstreams: 0 Previous issue date: 2018en
dc.identifier.urihttp://repositorio.unicamp.br/jspui/handle/REPOSIP/349412-
dc.contributor.departmentDepartamento de Sistemas e Energiapt_BR
dc.contributor.unidadeFaculdade de Engenharia Elétrica e de Computaçãopt_BR
dc.subject.keywordWhole building energy simulationpt_BR
dc.subject.keywordCo-simulationpt_BR
dc.subject.keywordIntelligent co-simulationpt_BR
dc.subject.keywordProper orthogonal decomposition (POD)pt_BR
dc.subject.keywordRecurrent neural networkpt_BR
dc.identifier.source2-s2.0-85041530580pt_BR
dc.creator.orcid0000-0002-8225-7058pt_BR
dc.type.formArtigopt_BR
Appears in Collections:FEEC - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
2-s2.0-85041530580.pdf6.33 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.