Saved in:
Bibliographic Details
Main Authors: Zhou, Cuizhi, Zhu, Kaien
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.16636
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916857184780288
author Zhou, Cuizhi
Zhu, Kaien
author_facet Zhou, Cuizhi
Zhu, Kaien
contents The equilibrium reconstruction of plasma is a core step in real-time diagnostic tasks in fusion research. This paper explores a multi-stage Physics-Informed Neural Networks(PINNs) approach to solve the Grad-Shafranov equation, achieving high-precision solutions with an error magnitude of $O(10^{-8})$ between the output of the second-stage neural network and the analytical solution. Our results demonstrate that the multi-stage PINNs provides a reliable tool for plasma equilibrium reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16636
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physics-Informed Neural Networks for High-Precision Grad-Shafranov Equilibrium Reconstruction
Zhou, Cuizhi
Zhu, Kaien
Plasma Physics
The equilibrium reconstruction of plasma is a core step in real-time diagnostic tasks in fusion research. This paper explores a multi-stage Physics-Informed Neural Networks(PINNs) approach to solve the Grad-Shafranov equation, achieving high-precision solutions with an error magnitude of $O(10^{-8})$ between the output of the second-stage neural network and the analytical solution. Our results demonstrate that the multi-stage PINNs provides a reliable tool for plasma equilibrium reconstruction.
title Physics-Informed Neural Networks for High-Precision Grad-Shafranov Equilibrium Reconstruction
topic Plasma Physics
url https://arxiv.org/abs/2507.16636