A Review of Physics-Informed Machine Learning in Fluid Mechanics
Energies · 28.02.2023 · 16 (5) · 2343
DOI: 10.3390/en16052343 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energies, online erschienen am 28.02.2023. Verfasst von Pushan Sharma und 3 weiteren Autor:innen. Die Arbeit wurde bisher 274-mal zitiert (Crossref) und nennt 129 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DOE Basic Energy Science, NASA Early Stage Innovation Program, Stanford Institute for Human-centered Artificial Intelligence Graduate Fellowship.
Abstract (Originalsprache)
Physics-informed machine-learning (PIML) enables the integration of domain knowledge with machine learning (ML) algorithms, which results in higher data efficiency and more stable predictions. This provides opportunities for augmenting—and even replacing—high-fidelity numerical simulations of complex turbulent flows, which are often expensive due to the requirement of high temporal and spatial resolution. In this review, we (i) provide an introduction and historical perspective of ML methods, in particular neural networks (NN), (ii) examine existing PIML applications to fluid mechanics problems, especially in complex high Reynolds number flows, (iii) demonstrate the utility of PIML techniques through a case study, and (iv) discuss the challenges and opportunities of developing PIML for fluid mechanics.
Förderung
- DOE Basic Energy Science
- NASA Early Stage Innovation Program
- Stanford Institute for Human-centered Artificial Intelligence Graduate Fellowship
Zitieren
APA
Sharma, P., Chung, W. T., Akoush, B., & Ihme, M. (2023). A Review of Physics-Informed Machine Learning in Fluid Mechanics. Energies, 16(5), 2343. https://doi.org/10.3390/en16052343
Vancouver
Sharma P, Chung WT, Akoush B, Ihme M. A Review of Physics-Informed Machine Learning in Fluid Mechanics. Energies. 2023;16(5):2343. doi:10.3390/en16052343
BibTeX
@article{Sharma2023,
author = {Sharma, Pushan and Chung, Wai Tong and Akoush, Bassem and Ihme, Matthias},
title = {A Review of Physics-Informed Machine Learning in Fluid Mechanics},
journal = {Energies},
year = {2023},
volume = {16},
number = {5},
pages = {2343},
doi = {10.3390/en16052343}
}
EUVIMED