Fast equilibrium reconstruction by deep learning on EAST tokamak
A deep neural network is developed and trained on magnetic measurements (input) and EFIT poloidal magnetic flux (output) on the EAST tokamak. In optimizing the network architecture, we use automatic optimization to search for the best hyperparameters, which helps in better model generalization. We c...
Main Authors: | Jingjing Lu, Youjun Hu, Nong Xiang, Youwen Sun |
---|---|
Format: | Article |
Language: | English |
Published: |
AIP Publishing LLC
2023-07-01
|
Series: | AIP Advances |
Online Access: | http://dx.doi.org/10.1063/5.0152318 |
Similar Items
-
On local geometric properties of a tokamak equilibrium
by: Youwen Sun
Published: (2024-05-01) -
The effects of toroidal equilibrium flow on the stabilization of ballooning modes in tokamaks
by: Yanqiang Hu, et al.
Published: (2020-07-01) -
All superconducting tokamak: EAST
by: Jiansheng Hu, et al.
Published: (2023-04-01) -
Experimental characteristics of lost fast negative ions on EAST tokamak
by: Z.X. Zhang, et al.
Published: (2025-01-01) -
Reconstruction of tokamak plasma safety factor profile using deep learning
by: Xishuo Wei, et al.
Published: (2023-01-01)