Data-Driven Control for Radiative Collapse Avoidance in Large Helical Device
Data-Driven Control for Radiative Collapse Avoidance in Large Helical Device
复制标题
DOI：
10.1585/pfr.17.2402042
复制
发表时间：
2022-03
影响因子：
0.8
通讯作者：
T. Yokoyama;Hiroshi Yamada;S. Masuzaki;B. Peterson;R. Sakamoto;M. Goto;T. Oishi;G. Kawamura;M. Kobayashi;T. Tsujimura;Y. Mizuno;J. Miyazawa;K. Mukai;N. Tamura;G. Motojima;K. Ida
中科院分区：
文献类型：
--
作者：
T. Yokoyama;Hiroshi Yamada;S. Masuzaki;B. Peterson;R. Sakamoto;M. Goto;T. Oishi;G. Kawamura;M. Kobayashi;T. Tsujimura;Y. Mizuno;J. Miyazawa;K. Mukai;N. Tamura;G. Motojima;K. Ida
利用大螺旋装置（LHD）中的高密度等离子体实验，利用机器学习模型开发了一种辐射塌缩预测器。该模型是基于崩溃的可能性，这是量化的艾德由稀疏建模所选择的参数，包括nee，CIV，OV和Te，边缘。实现该模型的控制系统已与单板计算机应用此预测模型的铲运机实验。控制器计算崩溃的可能性，并实时调节气体燃料供应和提升电子回旋共振加热。在氢等离子体密度上升实验中，高密度等离子体被控制系统保持，同时避免辐射崩溃。这一结果表明，基于塌陷似然的预测器具有实时预测辐射塌陷的能力。
A radiative collapse predictor has been developed using a machine-learning model with high-density plasma experiments in the Large Helical Device (LHD). The model is based on the collapse likelihood, which is quantified by the parameters selected by the sparse modeling, including ¯ n e , CIV, OV, and T e , edge . The control system implementing this model has been constructed with a single-board computer to apply this predictor model to the LHD experiment. The controller calculates the collapse likelihood and regulates gas-pu ff fueling and boosts electron cyclotron resonance heating in real-time. In density ramp-up experiments with hydrogen plasma, high-density plasma has been maintained by the control system while avoiding radiative collapse. This result has shown that the predictor based on the collapse likelihood has the capability to predict a radiative collapse in real-time.