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: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2023-07-01
|
| Series: | AIP Advances |
| Online Access: | http://dx.doi.org/10.1063/5.0152318 |