4 papers
FusionMAE: large-scale pretrained model to optimize and simplify diagnostic and control of fusion plasma
Zongyu Yang, Zhenghao Yang, Wenjing Tian +14
In magnetically confined fusion device, the complex, multiscale, and nonlinear dynamics of plasmas necessitate the integration of extensive diagnostic systems to effectively monito…
High-Fidelity Data-Driven Dynamics Model for Reinforcement Learning-based Control in HL-3 Tokamak
Niannian Wu, Zongyu Yang, Rongpeng Li +11
The success of reinforcement learning (RL)-based control in tokamaks, an emerging technique for controlled nuclear fusion with improved flexibility, typically requires substantial…
EFIT-mini: An Embedded, Multi-task Neural Network-driven Equilibrium Inversion Algorithm
Guohui Zheng, Songfen Liu, Huasheng Xie +11
Equilibrium reconstruction, which infers internal magnetic fields, plasmas current, and pressure distributions in tokamaks using diagnostic and coil current data, is crucial for co…
Real-time equilibrium reconstruction by neural network based on HL-3 tokamak
Guohui Zheng, Songfen Liu, Zongyu Yang +5
A neural network model, EFITNN, has been developed capable of real-time magnetic equilibrium reconstruction based on HL-3 tokamak magnetic measurement signals. The model processes…