dc.contributor.author | Ahmed, Shady E | |
dc.contributor.author | Rahman, Sk. Mashfiqur | |
dc.contributor.author | San, Omer | |
dc.contributor.author | Rasheed, Adil | |
dc.contributor.author | Navon, Ionel M | |
dc.date.accessioned | 2020-01-13T10:58:11Z | |
dc.date.available | 2020-01-13T10:58:11Z | |
dc.date.created | 2019-12-24T01:18:00Z | |
dc.date.issued | 2019 | |
dc.identifier.issn | 1070-6631 | |
dc.identifier.uri | http://hdl.handle.net/11250/2635931 | |
dc.description.abstract | Generating a digital twin of any complex system requires modeling and computational approaches that are efficient, accurate, and modular. Traditional reduced order modeling techniques are targeted at only the first two, but the novel nonintrusive approach presented in this study is an attempt at taking all three into account effectively compared to their traditional counterparts. Based on dimensionality reduction using proper orthogonal decomposition (POD), we introduce a long short-term memory neural network architecture together with a principal interval decomposition (PID) framework as an enabler to account for localized modal deformation. As an effective partitioning tool for breaking the Kolmogorov barrier, our PID framework, therefore, can be considered a key element in the accurate reduced order modeling of convective flows. Our applications for convection-dominated systems governed by Burgers, Navier-Stokes, and Boussinesq equations demonstrate that the proposed approach yields significantly more accurate predictions than the POD-Galerkin method and could be a key enabler toward near real-time predictions of unsteady flows. | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | AIP Publishing | nb_NO |
dc.title | Memory embedded non-intrusive reduced order modeling of non-ergodic flows | nb_NO |
dc.type | Journal article | nb_NO |
dc.type | Peer reviewed | nb_NO |
dc.description.version | publishedVersion | nb_NO |
dc.source.volume | 31 | nb_NO |
dc.source.journal | Physics of Fluids | nb_NO |
dc.source.issue | 126602 | nb_NO |
dc.identifier.doi | https://doi.org/10.1063/1.5128374 | |
dc.identifier.cristin | 1763796 | |
dc.description.localcode | Published by AIP Publishing. Locked until 23.12.2020 due to copyright restrictions. This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. The following article appeared in Journal of Applied Physics and may be found at http://aip.scitation.org/doi/10.1063/1.4954218 | nb_NO |
cristin.unitcode | 194,63,25,0 | |
cristin.unitname | Institutt for teknisk kybernetikk | |
cristin.ispublished | true | |
cristin.fulltext | preprint | |
cristin.qualitycode | 2 | |