Grad–Shafranov equilibria via data-free physics informed neural networks
Physics of Plasmas · 01.03.2024 · 31 (3)
DOI: 10.1063/5.0188634 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics of Plasmas, online erschienen am 25.03.2024. Verfasst von Byoungchan Jang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: U.S. Department of Energy.
Abstract (Originalsprache)
A large number of magnetohydrodynamic (MHD) equilibrium calculations are often required for uncertainty quantification, optimization, and real-time diagnostic information, making MHD equilibrium codes vital to the field of plasma physics. In this paper, we explore a method for solving the Grad–Shafranov equation by using physics-informed neural networks (PINNs). For PINNs, we optimize neural networks by directly minimizing the residual of the partial differential equation as a loss function. We show that PINNs can accurately and effectively solve the Grad–Shafranov equation with several different boundary conditions, making it more flexible than traditional solvers. This method is flexible as it does not require any mesh and basis choice, thereby streamlining the computational process. We also explore the parameter space by varying the size of the model, the learning rate, and boundary conditions to map various tradeoffs such as between reconstruction error and computational speed. Additionally, we introduce a parameterized PINN framework, expanding the input space to include variables such as pressure, aspect ratio, elongation, and triangularity in order to handle a broader range of plasma scenarios within a single network. Parameterized PINNs could be used in future work to solve inverse problems such as shape optimization.
Förderung
- U.S. Department of Energy
Zitieren
APA
Jang, B., Kaptanoglu, A. A., Gaur, R., Pan, S., Landreman, M., & Dorland, W. (2024). Grad–Shafranov equilibria via data-free physics informed neural networks. Physics of Plasmas, 31(3). https://doi.org/10.1063/5.0188634
Vancouver
Jang B, Kaptanoglu AA, Gaur R, Pan S, Landreman M, Dorland W. Grad–Shafranov equilibria via data-free physics informed neural networks. Physics of Plasmas. 2024;31(3). doi:10.1063/5.0188634
BibTeX
@article{Jang2024,
author = {Jang, Byoungchan and Kaptanoglu, Alan A. and Gaur, Rahul and Pan, Shaowu and Landreman, Matt and Dorland, William},
title = {Grad–Shafranov equilibria via data-free physics informed neural networks},
journal = {Physics of Plasmas},
year = {2024},
volume = {31},
number = {3},
doi = {10.1063/5.0188634}
}
EUVIMED