Enabling Integrated AI Control on DIII-D: A Control System Design with State-of-the-art Experiments
Andrew Rothstein, Hiro Joseph Farre-Kaga, Jalal Butt, Ricardo Shousha, Keith Erickson, Takuma Wakatsuki, Azarakhsh Jalalvand, Peter Steiner, Sangkyeun Kim, and Egemen Kolemen
我们介绍了使用DIII-D中MAchiNe学习(PACMAN)预测和控制的一般算法的设计和应用。 基于机器渮魏(ML)的预测器和控制器在实现传统控制器失败的机制方面显示出巨大的希望,例如撕裂模式免费场景,无ELM场景和稳定的高级托卡马克条件。 这里介绍的架构部署在DIII-D上,以促进从诊断处理到最终执行命令的高级控制实验的端到端实现。 本文介绍了算法的详细设计,并解释了每个设计点背后的动机。 我们还描述了DIII-D中几个成功的ML控制实验,包括针对高级非感应等离子体的强化学习控制器,宽基静态H模式ELM预测器,Alfvén Eigenmode控制器,模型预测控制等离子体配置文件控制器和状态机泪模式预测器控制器。 还有关于实时机器学习控制器设计和实现的指导原则的讨论。
We present the design and application of a general algorithm for Prediction And Control using MAchiNe learning (PACMAN) in DIII-D. Machine learing (ML)-based predictors and controllers have shown great promise in achieving regimes in which traditional controllers fail, such as tearing mode free scenarios, ELM-free scenarios and stable advanced tokamak conditions. The architecture presented here was deployed on DIII-D to facilitate the end-to-end implementation of advanced control experiments, fr...
