Real-time prediction of high-density EAST disruptions using random forest
Real-time prediction of high-density EAST disruptions using random forest
复制标题
使用随机森林实时预测高密度 EAST 中断
DOI：
10.1088/1741-4326/abf74d
复制
发表时间：
2021-04
期刊：
影响因子：
3.3
通讯作者：
Li J. G.
中科院分区：
文献类型：
--
作者：
Hu W. H.;Rea C.;Yuan Q. P.;Erickson K. G.;Chen D. L.;Shen B.;Huang Y.;Xiao J. Y.;Chen J. J.;Duan Y. M.;Y. Zhang;Zhuang H. D.;Xu J. C.;Montes K. J.;Granetz R. S.;Zeng L.;Qian J. P.;Xiao B. J.;Li J. G.
提出了一种基于随机森林的高密度干扰实时预测方法，并首次应用于EAST托卡马克等离子体控制系统。基于随机森林（DPRF）的破坏预测器以背驮式模式运行，并在2019-2020年的实验活动中积极利用专门的实验，以测试其对即将到来的高密度破坏的实时预测能力。在专门的实验中，减缓系统由DPRF提供的预设警报触发，并将氖气注入等离子体中，以成功地减轻中断损害。DPRF的平均计算时间为~ 250 μs，这也是一个非常相关的结果，因为该算法不仅提供了即将发生中断的概率，即中断性，而且还提供了所谓的特征贡献，即实时解释中断性驱动因素的可解释性估计。DPRF是用干扰数据集训练的，其中电子密度至少达到格林沃尔德密度极限的80%，使用的是EAST PCS常规可用的零维信号。通过离线分析，找到了DPRF干扰信号的最优报警阈值，该阈值允许成功报警率为92%，虚警率为9.9%。通过分析误报原因，我们发现一部分（~ 15%）的误分类是由于等离子体约束从H-模式到l模式的突然转变造成的，这种转变经常发生在EAST高密度放电期间。通过对DPRF特征贡献的分析，可以发现环路电压信号是产生虚警的主要原因，应加入更能表征约束背跃迁特征的等离子体信号以避免虚警。
A real-time disruption predictor using random forest was developed for high-density disruptions and used in the plasma control system (PCS) of the EAST tokamak for the first time. The disruption predictor via random forest (DPRF) ran in piggyback mode and was actively exploited in dedicated experiments during the 2019–2020 experimental campaign to test its real-time predictive capabilities in oncoming high-density disruptions. During dedicated experiments, the mitigation system was triggered by a preset alarm provided by DPRF and neon gas was injected into the plasma to successfully mitigate disruption damage. DPRF’s average computing time of ∼250 μs is also an extremely relevant result, considering that the algorithm provides not only the probability of an impending disruption, i.e. the disruptivity, but also the so-called feature contributions, i.e. explainability estimates to interpret in real time the drivers of the disruptivity. DPRF was trained with a dataset of disruptions in which the electron density reached at least 80% of the Greenwald density limit, using the zero-dimensional signal routinely available to the EAST PCS. Through offline analysis, an optimal warning threshold on the DPRF disruptivity signal was found, which allows for a successful alarm rate of 92% and a false alarm rate of 9.9%. By analyzing the false alarm causes, we find that a fraction (∼15%) of the misclassifications are due to sudden transitions of plasma confinement from H- to L-mode, which often occur during high-density discharges in EAST. By analyzing DPRF feature contributions, it emerges that the loop voltage signal is that main cause of such false alarms: plasma signals more apt to characterize the confinement back-transition should be included to avoid false alarms.
登录
查看更多内容
影响因子：
3.3
作者：
A. Sengupta;P. Ranjan
通讯作者：
A. Sengupta;P. Ranjan
J-TEXT 托卡马克密度极限破坏的预测
影响因子：
2.2
作者：
Y.N.Wei;T.K.Ma;M.Zhang;G.Zhuang
通讯作者：
G.Zhuang
影响因子：
3.3
作者：
K. Montes;C. Rea;R. A. Tinguely;R. Sweeney;J. Zhu;R. Granetz
通讯作者：
K. Montes;C. Rea;R. A. Tinguely;R. Sweeney;J. Zhu;R. Granetz
影响因子：
3.3
作者：
A. Piccione-;J. Berkery;S. Sabbagh;Y. Andreopoulos
通讯作者：
A. Piccione-;J. Berkery;S. Sabbagh;Y. Andreopoulos
影响因子：
2.2
作者：
Alcator C-Mod;C. Rea;R. Granetz;K. Montes;R. A. Tinguely;N. Eidietis;J. Hanson;B. Sammuli
通讯作者：
Alcator C-Mod;C. Rea;R. Granetz;K. Montes;R. A. Tinguely;N. Eidietis;J. Hanson;B. Sammuli