Deep neural network Grad─Shafranov solver constrained with measured magnetic signals
Abstract
A neural network solving the Grad─Shafranov equation constrained with measured magnetic signals to reconstruct magnetic equilibria in real time is developed. The database created to optimize the neural network's free parameters contains offline EFIT results as the output of the network from 1118 KSTAR experimental discharges of two different campaigns. Input data to the network constitute magnetic signals measured by a Rogowski coil (plasma current), magnetic pickup coils (normal and tangential components of magnetic fields) and flux loops (poloidal magnetic fluxes). The developed neural networks fully reconstruct not only the poloidal flux function [ image ] but also the toroidal current density function [ image ] with the offline EFIT quality. To preserve the robustness of the networks against missing input data, an imputation scheme is utilized to eliminate the required additional training sets with a large number of possible combinations of the missing inputs.
 Publication:

Nuclear Fusion
 Pub Date:
 January 2020
 DOI:
 10.1088/17414326/ab555f
 arXiv:
 arXiv:1911.02882
 Bibcode:
 2020NucFu..60a6034J
 Keywords:

 neural network;
 Grad─Shafranov equation;
 EFIT;
 poloidal flux;
 toroidal current;
 imputation;
 KSTAR;
 Physics  Plasma Physics;
 Computer Science  Machine Learning
 EPrint:
 doi:10.1088/17414326/ab555f