Experiment data-driven modeling of tokamak discharge in EAST

TL;DR

This paper presents a deep learning model trained on EAST tokamak data to predict discharge diagnostic signals from control inputs, offering an alternative to traditional physics-based models with high accuracy.

Contribution

The study introduces a data-driven deep learning approach for modeling tokamak discharges using control signals, achieving high similarity with experimental data.

Findings

Achieved up to 95% similarity for stored energy W_mhd

Successfully modeled electron density n_e and loop voltage V_loop

Demonstrated the feasibility of data-driven discharge modeling

Abstract

A model for tokamak discharge through deep learning has been done on a superconducting long-pulse tokamak (EAST). This model can use the control signals (i.e. Neutral Beam Injection (NBI), Ion Cyclotron Resonance Heating (ICRH), etc) to model normal discharge without the need for doing real experiments. By using the data-driven methodology, we exploit the temporal sequence of control signals for a large set of EAST discharges to develop a deep learning model for modeling discharge diagnostic signals, such as electron density $n_{e}$, store energy $W_{mhd}$ and loop voltage $V_{loop}$. Comparing the similar methodology, we use Machine Learning techniques to develop the data-driven model for discharge modeling rather than disruption prediction. Up to 95% similarity was achieved for $W_{mhd}$. The first try showed promising results for modeling of tokamak discharge by using the data-driven methodology. The data-driven methodology provides an alternative to physical-driven modeling for tokamak discharge modeling.