The principle of minimum pressure gradient: An alternative basis for physics-informed learning of incompressible fluid mechanics
AIP Advances · 01.04.2024 · 14 (4)
DOI: 10.1063/5.0197860 ↗Kurz gefasst
Fachartikel in der Zeitschrift AIP Advances, online erschienen am 08.04.2024. Verfasst von H. Alhussein und 1 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Recent advances in the application of physics-informed learning in the field of fluid mechanics have been predominantly grounded in the Newtonian framework, primarily leveraging Navier–Stokes equations or one of their various derivatives to train a neural network. Here, we propose an alternative approach based on variational methods. The proposed approach uses the principle of minimum pressure gradient combined with the continuity constraint to train a neural network and predict the flow field in incompressible fluids. We describe the underlying principles of the proposed approach, then use a demonstrative example to illustrate its implementation, and show that it reduces the computational time per training epoch when compared to the conventional approach.
Zitieren
APA
Alhussein, H., & Daqaq, M. (2024). The principle of minimum pressure gradient: An alternative basis for physics-informed learning of incompressible fluid mechanics. AIP Advances, 14(4). https://doi.org/10.1063/5.0197860
Vancouver
Alhussein H, Daqaq M. The principle of minimum pressure gradient: An alternative basis for physics-informed learning of incompressible fluid mechanics. AIP Advances. 2024;14(4). doi:10.1063/5.0197860
BibTeX
@article{Alhussein2024,
author = {Alhussein, H. and Daqaq, M.},
title = {The principle of minimum pressure gradient: An alternative basis for physics-informed learning of incompressible fluid mechanics},
journal = {AIP Advances},
year = {2024},
volume = {14},
number = {4},
doi = {10.1063/5.0197860}
}
EUVIMED