用于托卡马克边缘等离子体的循环一致且不确定性感知神经代理

中文摘要 AI 辅助

边界和偏滤器等离子体决定了托卡马克如何排出能量和粒子，设定热通量、靶条件和脱附起始点。预测这些量对于当前和未来设备的运行至关重要，但解析它们的边缘模拟对于参数扫描、优化或实时控制来说太慢。机器学习代理提供了一种快速替代方案，但大多数是单向的。我们引入了一种用于边缘等离子体的循环一致神经代理，结合了条件U-Net正向模型和基于冻结正向网络的基于优化的逆方法。正向模型将五个控制参数映射到SOLPS-ITER网格上的二维等离子体状态场；逆方法强制正向和逆预测之间的一致性，这是一种无需推理时的真实标签的自监督质量检查。多层感知器的集合还预测外侧中平面和偏滤器靶处的电子温度和密度分布，并带有不确定性估计，标记出需要更多模拟的地方。正向模型对所有场实现了归一化均方根误差低于2.6%且皮尔逊相关系数高于0.95。循环一致性正则化将平均循环$R^2$从0.59提高到0.99，而不会降低正向精度，并能够恢复核心燃料注入率；所有五个控制参数的恢复皮尔逊$r\geq0.97$。$k$-d树热启动产生的数据库完成率高于95%，而冷启动时大约有30%的完全失败。该模型有大约$4\times10^6$个参数，能在毫秒内产生完整的二维预测，比SOLPS-ITER快五到六个数量级，可实现实时控制、参数扫描、不确定性分析和数字孪生。

英文摘要

The boundary and divertor plasma govern how a tokamak exhausts power and particles, setting heat fluxes, target conditions, and the onset of detachment. Predicting these quantities is essential for operating current and future devices, but edge simulations that resolve them are too slow for parameter scans, optimization, or real-time control. Machine-learning surrogates offer a fast alternative, yet most are forward-only: they cannot recover input parameters from observations or assess the reliability of their predictions. We introduce a cycle-consistent neural surrogate for edge plasmas, combining a conditional U-Net forward model with an optimization-based inverse method built on the frozen forward network. The forward model maps five control parameters to two-dimensional plasma-state fields on the SOLPS-ITER mesh; the inverse method enforces consistency between forward and inverse predictions, a self-supervised quality check needing no ground-truth labels at inference. An ensemble of multilayer perceptrons also predicts electron temperature and density profiles at the outboard midplane and divertor targets, with uncertainty estimates that flag where more simulations are needed. The forward model achieves normalized root-mean-square errors below 2.6% and Pearson correlations above 0.95 for all fields. Cycle-consistency regularization raises the average cyclical $R^2$ from 0.59 to 0.99 without degrading forward accuracy and enables recovery of the core fueling rate; all five control parameters are recovered with Pearson $r\ge0.97$. A $k$-d tree warm start yields a database completion rate above 95%, versus roughly 30% outright failures when cold-started. With about $4\times10^6$ parameters, the model produces full 2D predictions in milliseconds, five to six orders of magnitude faster than SOLPS-ITER, enabling real-time control, parameter scans, uncertainty analysis, and digital twins.

发表机构

• Fusion Energy Division, Oak Ridge National Laboratory（奥克勒斯国家实验室等离子体能源部）
• DIFFER - Dutch Institute for Fundamental Energy Research（荷兰基础能源研究所）

机构由 AI 辅助整理，请以论文原文为准。