On the use of deep learning and computational fluid dynamics for the estimation of uniform momentum source components of propellers
Visualitza/
Impacte
Scholar |
Altres documents de l'autoria: Martinez Cuenca, Raul; Luis Gómez, Jaume; Iserte, Sergio; chiva, sergio
Metadades
Mostra el registre complet de l'elementcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7035
comunitat-uji-handle3:10234/8617
comunitat-uji-handle4:
INVESTIGACIONMetadades
Títol
On the use of deep learning and computational fluid dynamics for the estimation of uniform momentum source components of propellersData de publicació
2023-12Editor
Cell PressISSN
2589-0042Cita bibliogràfica
Raúl Martínez-Cuenca, Jaume Luis-Gómez, Sergio Iserte, Sergio Chiva, On the use of deep learning and computational fluid dynamics for the estimation of uniform momentum source components of propellers, iScience, Volume 26, Issue 12, 2023, 108297, ISSN 2589-0042, https://doi.org/10.1016/j.isci.2023.108297. (https://www.sciencedirect.com/science/article/pii/S258900422302374X)Tipus de document
info:eu-repo/semantics/articleVersió de l'editorial
https://www.sciencedirect.com/science/article/pii/S258900422302374XVersió
info:eu-repo/semantics/publishedVersionParaules clau / Matèries
Resum
This article proposes a novel method based on Deep Learning for the resolution of uniform momentum source terms in the Reynolds-Averaged Navier-Stokes equations. These source terms can represent several industrial ... [+]
This article proposes a novel method based on Deep Learning for the resolution of uniform momentum source terms in the Reynolds-Averaged Navier-Stokes equations. These source terms can represent several industrial devices (propellers, wind turbines, and so forth) in Computational Fluid Dynamics simulations. Current simulation methods require huge computational power, rely on strong assumptions or need additional information about the device that is being simulated. In this first approach to the new method, a Deep Learning system is trained with hundreds of Computational Fluid Dynamics simulations with uniform momemtum sources so that it can compute the one representing a given propeller from a reduced set of flow velocity measurements near it. Results show an overall relative error below the 5% for momentum sources for uniform sources and a moderate error when describing real propellers. This work will allow to simulate more accurately industrial devices with less computational cost. [-]
Publicat a
iScience, vol. 26, núm. 12, (2023)Entitat finançadora
Universitat Jaume I | Agencia Estatal de Investigación | Generalitat Valenciana | European Social Funds | Ministerio de Universidades
Codi del projecte o subvenció
UJI-B2021-70 | PID2021-128405OB-I00 | APOSTD/2020/026 | FPU21/03740
Drets d'accés
info:eu-repo/semantics/openAccess
Apareix a les col.leccions
- EMC_Articles [822]