Tag
本文提出一个物理接地的多模态智能体框架，用于磁约束聚变装置中性束注入离子源的非平稳自适应调控，在EXL-50U平台455次放电的时序回放中验证了符号化物理量优于波形图像，并在监督运行下实现86.80%的束提取率。
A physics-informed self-supervised learning framework is introduced for calibrating and reconstructing positions in multi-wire parallel plate avalanche counters using only detector geometry and charge constraints, eliminating the need for labeled data or dedicated calibration runs.