Solving Navier-Stokes equations with mixed equation physics informed neural networks [Navier-Stokes denklemlerinin karma denklemli fizik bilgili nöral ağlarla çözümü]

Warning The system is temporarily closed to updates for reporting purpose.

Akpinar, Sila and Vardar, Emre and Yeşilyurt, Serhat and Kaya, Kamer (2023) Solving Navier-Stokes equations with mixed equation physics informed neural networks [Navier-Stokes denklemlerinin karma denklemli fizik bilgili nöral ağlarla çözümü]. In: 31st Signal Processing and Communications Applications Conference (SIU), Istanbul, Turkiye

[thumbnail of Solving_Navier-Stokes_Equations_With_Mixed_Equation_Physics_Informed_Neural_Networks.pdf] PDF
Solving_Navier-Stokes_Equations_With_Mixed_Equation_Physics_Informed_Neural_Networks.pdf
Restricted to Registered users only

Download (1MB) | Request a copy

Abstract

This paper presents a study on the implementation and testing of mixed-precision and mixed-equation approaches for optimizing the performance of physics-informed neural networks. Mixed-equation approach involves utilizing equations in a multi-step manner, which leads to a significant reduction in computational costs during the network's training while capturing complex physical phenomena. Specifically, we demonstrate the effectiveness of the proposed methodology in approximating the Navier-Stokes equations for incompressible flow around a 2D cylinder.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: fluid dynamics; Navier-Stokes equations; physics-informed neural networks; scientific machine learning
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Serhat Yeşilyurt
Date Deposited: 17 Sep 2023 13:27
Last Modified: 07 Feb 2024 11:49
URI: https://research.sabanciuniv.edu/id/eprint/47929

Actions (login required)

View Item
View Item