arXiv subjects

Zhengyuan Chen

Publications and source records attributed to Zhengyuan Chen.

4 recordsLinked to original sources

arXiv2026

State-Space Model-Enabled Reinforcement Learning for Magnetic Configuration Controlon EXL-50U

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.

physics.plasm-ph↗

arXiv2026

Advantage-level Aggregation Reinforcement Learning for X-point Target Magnetic Configuration Control in an EXL-50U Experiment-Calibrated Simulation Environment

Managing divertor heat loads is a central challenge for compact, high-power tokamaks. To increase local flux expansion and decouple the dissipation volume from the core, EHL-2 adopts the X-point target (XPT) divertor. This requires the secondary X-point to remain on the divertor leg; displacement degrades the topology and exhaust geometry. Current experiments, including EXL-50U discharges, rely on precomputed feedforward waveforms with PID loops on global quantities. Lacking dedicated closed-loop feedback for the secondary null, XPT operation is repeatable but not routine. We formulate XPT feedback as a multi-objective reinforcement learning (RL) control problem in a free-boundary environment calibrated to EXL-50U discharge #13906. To address strong coupling among plasma current, shape, and null constraints - where reward scalarisation collapses objective-specific temporal credit - we develop Advantage Aggregation (AdvA). AdvA preserves objective-wise temporal credit before worst-objective-aware nonlinear scalarisation and introduces a residual correction to policy updates. AdvA-PPO is evaluated against Reward-PPO and a feedforward-plus-PID baseline under nominal operation, measurement uncertainties, and unseen initial equilibria. On a 500 ms rollout, AdvA-PPO raises the mean worst-channel score from 0.23 to 0.81 over Reward-PPO, reducing X-point flux RMSE by ~20x. Under combined measurement uncertainties, it is the only learned controller completing the horizon while retaining a usable XPT shape. Multi-initialization fine-tuning enables a single AdvA-PPO policy to complete full-horizon operation across divertor and limiter initial equilibria. These results provide a simulation-based foundation for future real-time XPT validation on EXL-50U.

physics.plasm-ph↗

arXiv2026

Reinforcement learning for vertical position control on the EXL-50U spherical tokamak

Vertical position control is essential for sustaining high-performance operation in spherical tokamaks, where increased plasma elongation introduces stringent requirements on fast and robust stabilization. This work presents an experimentally validated reinforcement-learning(RL)-based vertical position control framework for the EXL-50U spherical tokamak. A high-fidelity discharge-reconstructed simulation environment is developed by integrating physics-based plasma-circuit models with experimental equilibrium information, enabling systematic controller synthesis and sim-to-real evaluation. Within this framework, RL is benchmarked in simulation against operational proportional--integral--derivative (PID) and model-based linear quadratic regulator (LQR) controllers under identical plant dynamics, actuator constraints, and measurement imperfections.Simulation results show that RL achieves tracking accuracy comparable to PID with consistently lower vertical-stabilization coil effort, while lightweight integral compensation improves robustness against residual model--plant mismatch. The RL controller is subsequently deployed on EXL-50U for closed-loop experiments. Across more than ten discharges with RL takeover, stable vertical regulation is achieved within the controlled windows. For seven representative discharges, RL maintains millimetre-scale tracking accuracy comparable to the operational PID controller (MAE typically ~ 1-5 mm) while consistently reducing actuator effort. These results demonstrate the feasibility of learning-based plasma control on a real spherical tokamak and establish a practical pathway toward future fusion control systems.

physics.plasm-ph↗

arXiv2025

EFIT-mini: An Embedded, Multi-task Neural Network-driven Equilibrium Inversion Algorithm

Equilibrium reconstruction, which infers internal magnetic fields, plasmas current, and pressure distributions in tokamaks using diagnostic and coil current data, is crucial for controlled magnetic confinement nuclear fusion research. However, traditional numerical methods often fall short of real-time control needs due to time-consuming computations or iteration convergence issues. This paper introduces EFIT-mini, a novel algorithm blending machine learning with numerical simulation. It employs a multi-task neural network to replace complex steps in numerical equilibrium inversion, such as magnetic surface boundary identification, combining the strengths of both approaches while mitigating their individual drawbacks. The neural network processes coil currents and magnetic measurements to directly output plasmas parameters, including polynomial coefficients for $p'$ and $ff'$, providing high-precision initial values for subsequent Picard iterations. Compared to existing AI-driven methods, EFIT-mini incorporates more physical priors (e.g., least squares constraints) to enhance inversion accuracy. Validated on EXL-50U tokamak discharge data, EFIT-mini achieves over 98% overlap in the last closed flux surface area with traditional methods. Besides, EFIT-mini's neural network and full algorithm compute single time slices in just 0.11ms and 0.36ms at 129$\times$129 resolution, respectively, representing a three-order-of-magnitude speedup. This innovative approach leverages machine learning's speed and numerical algorithms' explainability, offering a robust solution for real-time plasmas shape control and potential extension to kinetic equilibrium reconstruction. Its efficiency and versatility position EFIT-mini as a promising tool for tokamak real-time monitoring and control, as well as for providing key inputs to other real-time inversion algorithms.

physics.plasm-ph↗