25–29 May 2026
La Biodola - Isola d'Elba (Italy)
Europe/Rome timezone
NB: The submission deadline for the Student Paper Awards is Monday, 11 May.

Real-Time Plasma Density Prediction and Control Framework for Pellet Injection on EAST Tokamak

27 May 2026, 11:05
1h
Elena Room (Hotel Hermitage)

Elena Room

Hotel Hermitage

Poster presentation AI, Machine Learning, Real Time Simulation, Intelligent Signal Processing AI, Machine Learning, Real Time Simulation, Intelligent Signal Processing - PS

Speaker

Yucheng Wang

Description

Precise control of plasma density is critical for high-performance steady-state operation in fusion devices. The candidate fueling method for density control for future tokamak will be pellet injection. However, pellet injection introduces rapid, highly non-linear density perturbations that challenge the latency and accuracy limitations of traditional feedback systems. This study presents a real-time density evolution prediction and controlling architecture for the EAST Tokamak. The core challenge addressed is the requirement to process high-dimensional multi-physics diagnostic data—including magnetic equilibrium parameters, radiation profiles, and Dα signals—and generating reliable future density estimation within the 10ms control cycle required for active feedback.

To achieve this, we deploy a lightweight, attention-based LSTM model optimized for low-latency inference. The system integrates a rolling-window mechanism that synchronizes data acquisition, pre-processing, and model inference of 100Hz. This design ensures that the prediction of density evolution, particularly the sharp rise and decay following pellet ablation, is computed and fed into a Model Predictive Control (MPC) solver within the allocated time budget. Off-line test results with EAST experiment data demonstrate that the system successfully captures complex non-linear dynamics with negligible computational lag. By overcoming the trade-off between model complexity and real-time responsiveness, this framework enables precise, automated trajectory tracking and oscillation suppression during high-frequency pellet injection scenarios.

Block diagram of the Real-Time Prediction & Plasma Control System (RT-PCS) on EAST. The framework illustrates the closed-loop data flow from tokamak to the Attention-based LSTM and MPC controller, ensuring density prediction and control signal generation within a strict 10ms cycle.

Minioral Yes
IEEE Member No
Are you a student? Yes

Author

Yucheng Wang

Co-authors

Bingjia Xiao (Institute of Plasma Physics,Chinese Academy of Sciences) Jilei Hou (Institute of Plasma Physics, Chinese Academy of Science) Kai Wu (Institute of Plasma Physics, Chinese Academy of Science) Qiping Yuan (ASIPP) Wenhui Hu (Institute of Plasma Physics, Chinese Academy of Science) Dr Zhengping Luo

Presentation materials

There are no materials yet.