-
State-Space Model-Enabled Reinforcement Learning for Magnetic Configuration Controlon EXL-50U
Authors:
Pei Guo,
Zhengyuan Chen,
Jianguo Chen,
Xuanhe Wang,
Guoyang Shi,
Siqi Ding,
Yapeng Zhang,
Lei Xing,
Yong Liu,
Xiang Gu,
Tiantian Sun,
Xiuchun Lun,
Jia Li,
Zhengxiong Wang,
Huasheng Xie,
Hanyue Zhao,
Yuejiang Shi,
Xianming Song,
Tianyuan Liu,
EXL-50U Team
Abstract:
Accurate feedback control of the plasma current ($I_p$) and centroid position $(R_c,Z_c)$ is essential for the stable operation of spherical torus (ST) plasmas. Conventional proportional-integral-derivative (PID) controllers require extensive manual tuning and struggle with the fast, strongly coupled dynamics that arise as plasma performance improves. Reinforcement learning (RL) has recently emerg…
▽ More
Accurate feedback control of the plasma current ($I_p$) and centroid position $(R_c,Z_c)$ is essential for the stable operation of spherical torus (ST) plasmas. Conventional proportional-integral-derivative (PID) controllers require extensive manual tuning and struggle with the fast, strongly coupled dynamics that arise as plasma performance improves. Reinforcement learning (RL) has recently emerged as a promising alternative to such complex magnetic control problems, yet its practical deployment on ST devices remains challenging. This paper presents a practical RL controller for the EXL-50U ST, trained within a rigid RZIP state-space model (SSM) that enables efficient offline policy learning. A lightweight plasma position reconstructor is developed to estimate $(R_c,Z_c)$ from magnetic probe signals within the real-time control cycle. The trained policy is seamlessly deployed on the EXL-50U plasma control system, achieving stable regulation of $I_p$ and $(R_c,Z_c)$ and sustaining discharges up to 650 ms under RL control. These results demonstrate the feasibility and practical potential of model-informed RL for magnetic configuration control in ST devices, offering a promising direction beyond conventional PID-based schemes.
△ Less
Submitted 21 August, 2026;
originally announced August 2026.
-
A Novel Numerical Algorithms Optimization Method with Machine Learning Frameworks: Application on Real-time Plasmas Equilibrium Reconstruction in EXL-50U Spherical Torus
Authors:
G. H. Zheng,
S. F. Liu,
X. Gu,
Y. P. Zhang,
J. Li,
Y. Liu,
X. C. Lun,
L. Xing,
J. G. Chen,
Z. Y. Chen,
Y. Yu,
D. Guo,
Z. Y. Yang,
H. S. Xie,
X. M. Song,
Y. J. Shi,
EXL-50U Team
Abstract:
This work proposes for the first time a novel optimization method for numerical algorithms, which takes advantages of machine learning frameworks PyTorch and TensorRT, leveraging their modularity, low development threshold, and automatic tuning characteristics to achieve a real-time plasmas reconstruction algorithm called PTEFIT as an application in tokamak-based controlled fusion that combines pe…
▽ More
This work proposes for the first time a novel optimization method for numerical algorithms, which takes advantages of machine learning frameworks PyTorch and TensorRT, leveraging their modularity, low development threshold, and automatic tuning characteristics to achieve a real-time plasmas reconstruction algorithm called PTEFIT as an application in tokamak-based controlled fusion that combines performance, flexibility, and usability. The algorithm has been deployed and routinely operated on the EXL-50U spherical tokamak, with an average inference time of only 0.268ms per time slice at $129\times 129$ resolution, and has successfully driven feedback control of the maximum radial position of plasmas and isoflux control. We believe that its design philosophy has sufficient potential to accelerate development and optimization in GPU parallel computing, and is expected to be extended to other numerical algorithms.
△ Less
Submitted 18 January, 2026;
originally announced January 2026.
-
Development of high-frequency magnetic probe for plasma diagnostics of XuanLong-50
Authors:
Mingyuan Wang,
Xiuchun Lun,
Xiaokun Bo,
Bing Liu,
Adi Liu,
Yuejiang Shi
Abstract:
A high-frequency magnetic probe has been designed and developed on XuanLong-50 (EXL-50) spherical torus to measure high-frequency magnetic field fluctuations caused by energetic ions and electrons in the plasma. The magnetic loop, radio filters, radio-frequency (RF) limiter, and data acquisition system of the probe are described in detail. The results of the preliminary test show that the probe ca…
▽ More
A high-frequency magnetic probe has been designed and developed on XuanLong-50 (EXL-50) spherical torus to measure high-frequency magnetic field fluctuations caused by energetic ions and electrons in the plasma. The magnetic loop, radio filters, radio-frequency (RF) limiter, and data acquisition system of the probe are described in detail. The results of the preliminary test show that the probe can have a frequency response within the 1- 180 MHz range. The fluctuation data from the EXL-50 plasma were analyzed in the time-frequency domain using fast Fourier transforms. Using this diagnostic system, distinct high-frequency instabilities were detected. In particular, significant frequency chirping was observed, which is consistent with the bump on tail drive instability predicted by the Berk-Breizman model.
△ Less
Submitted 9 August, 2022;
originally announced August 2022.