On the use of deep learning and computational fluid dynamics for the estimation of uniform momentum source components of propellers

Raúl Martínez-Cuenca; Jaume Luis-Gómez; Sergio Iserte; Sergio Chiva

doi:10.1016/j.isci.2023.108297

On the use of deep learning and computational fluid dynamics for the estimation of uniform momentum source components of propellers

iScience. 2023 Oct 27;26(12):108297. doi: 10.1016/j.isci.2023.108297. eCollection 2023 Dec 15.

Authors

Raúl Martínez-Cuenca¹, Jaume Luis-Gómez¹, Sergio Iserte², Sergio Chiva¹

Affiliations

¹ Department of Mechanical Engineering and Construction, Universitat Jaume I, 12071 Castelló de la Plana, Comunitat Valenciana, Spain.
² Department of Computer Science, Barcelona Supercomputing Center - Centro Nacional de Supercomputación (BSC-CNS), 08034 Barcelona, Cataluña, Spain.

Abstract

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.

Keywords: Artificial intelligence; Industrial engineering.