5 papers
AI Surrogate Modeling for Real-Time Tokamak Equilibrium Prediction: Benchmarking Neural Architectures and Validation on EXL-50U
Guoyang Shi, Zitong Zhang, Siqi Ding +5
Fast and reliable plasma equilibrium prediction is essential for real-time tokamak operation and control, but conventional Grad-Shafranov (GS) solvers are often too costly for real…
State-Space Model-Enabled Reinforcement Learning for Magnetic Configuration Controlon EXL-50U
Pei Guo, Zhengyuan Chen, Jianguo Chen +17
Accurate feedback control of the plasma current () and centroid position is essential for the stable operation of spherical torus (ST) plasmas. Conventional propor…
Physics-informed Neural Operator Learning for Nonlinear Grad-Shafranov Equation
Siqi Ding, Zitong Zhang, Guoyang Shi +7
As artificial intelligence emerges as a transformative enabler for fusion energy commercialization, fast and accurate solvers become increasingly critical. In magnetic confinement…
Achievement of 1 MA Discharges in Hydrogen-Boron Plasmas on EXL-50U
Yuejiang Shi
One mega ampere (MA) plasma discharges were achieved on the EXL-50U spherical torus (ST) in hydrogen-boron (p-B) plasmas with toroidal fields up to 1 T at major radii up to 0.6m. A…
Overview of EXL-50 Research Progress and Future Plan
Yuejiang Shi, Yumin Wang, Bing Liu +37
XuanLong-50 (EXL-50) is the first medium-size spherical torus (ST) in China, with the toroidal field at major radius at 50 cm around 0.5T. CS-free and non-inductive current drive v…