AI 中文总结
本研究针对EXL-50U球形托卡马克开发了基于强化学习的垂直位置控制框架，经仿真和实验验证，其跟踪精度与PID相当且执行器工作量更低，为聚变控制系统提供了实用路径。
AI 中文摘要
垂直位置控制对于维持球形托卡马克的高性能运行至关重要，等离子体拉长度的增加对快速且鲁棒的稳定性控制提出了严格要求。本研究针对EXL-50U球形托卡马克，提出了经实验验证的基于强化学习（RL）的垂直位置控制框架。通过将基于物理的等离子体-电路模型与实验平衡信息相结合，构建了高保真的放电重构仿真环境，可用于系统的控制器合成及仿真到真实场景的评估。在该框架内，在相同的对象动力学、执行器约束和测量条件下，对RL与已投入运行的比例-积分-微分（PID）控制器、基于模型的线性二次调节器（LQR）控制器进行了仿真基准测试。结果表明，RL实现了与PID相当的跟踪精度，同时垂直稳定线圈的工作量始终更低，而轻量级积分补偿提高了对剩余模型-对象失配的鲁棒性。随后将RL控制器部署到EXL-50U上进行闭环实验，在十多次由RL接管的放电实验中，均在控制窗口内实现了稳定的垂直调节。对于七次代表性放电，RL保持了与运行中PID控制器相当的毫米级跟踪精度（平均绝对误差通常约为1-5毫米），同时始终降低了执行器工作量。这些结果证明了在真实球形托卡马克上实现基于学习的等离子体控制的可行性，为未来的聚变控制系统建立了实用路径。
英文摘要
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.
