Current and emerging deep-learning methods for the simulation of fluid dynamics
Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences · 2023-07 · 479 (2275)
DOI: 10.1098/rspa.2023.0058 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, online erschienen am 19.07.2023. Verfasst von Mario Lino und 3 weiteren Autor:innen. Die Arbeit wurde bisher 80-mal zitiert (Crossref) und nennt 208 Literaturangaben. Gefördert von: Department of Bioengineering, Imperial College London, Department of Aeronautics, Imperial College London.
Abstract (Originalsprache)
Over the last decade, deep learning (DL), a branch of machine learning, has experienced rapid progress. Powerful tools for tasks that have been traditionally complex to automate have been developed, such as image synthesis and natural language processing. In the context of simulating fluid dynamics, this has led to a series of novel DL methods for replacing or augmenting conventional numerical solvers. We broadly classify these methods into physics- and data-driven methods. Physics-driven methods, generally, tune a DL model to provide an analytical and differentiable solution to a given fluid dynamics problem by minimizing the residuals of the governing partial differential equations. Data-driven methods provide a fast and approximate solution to any fluid dynamics problem that shares some physical properties with the observations used when tuning the DL model’s parameters. Meanwhile, the symbiosis of numerical solvers and DL has led to promising results in turbulence modelling and accelerating iterative solvers. However, these methods present some challenges. Exclusively data-driven flow simulators often suffer from poor extrapolation, error accumulation in time-dependent simulations, as well as difficulties in training against turbulent flows. Substantial effort is, therefore, being invested into approaches that may improve the current state of the art.
Förderung
- Department of Bioengineering, Imperial College London
- Department of Aeronautics, Imperial College London
Zitieren
APA
Lino, M., Fotiadis, S., Bharath, A. A., & Cantwell, C. D. (2023). Current and emerging deep-learning methods for the simulation of fluid dynamics. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 479(2275). https://doi.org/10.1098/rspa.2023.0058
Vancouver
Lino M, Fotiadis S, Bharath AA, Cantwell CD. Current and emerging deep-learning methods for the simulation of fluid dynamics. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2023;479(2275). doi:10.1098/rspa.2023.0058
BibTeX
@article{Lino2023,
author = {Lino, Mario and Fotiadis, Stathi and Bharath, Anil A. and Cantwell, Chris D.},
title = {Current and emerging deep-learning methods for the simulation of fluid dynamics},
journal = {Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences},
year = {2023},
volume = {479},
number = {2275},
doi = {10.1098/rspa.2023.0058}
}
EUVIMED