A semi-supervised machine learning detector for physics events in tokamak discharges
A semi-supervised machine learning detector for physics events in tokamak discharges
复制标题
DOI：
10.1088/1741-4326/abcdb9
复制
发表时间：
2020-11
期刊：
影响因子：
3.3
通讯作者：
K. Montes;C. Rea;R. A. Tinguely;R. Sweeney;J. Zhu;R. Granetz
中科院分区：
文献类型：
--
作者：
K. Montes;C. Rea;R. A. Tinguely;R. Sweeney;J. Zhu;R. Granetz
物理事件数据库已被用于各种聚变研究应用中，包括标度律和中断避免算法的开发，但它们的构建可能是耗时和繁琐的。本文提出了一种新的应用程序的标签传播半监督学习算法，以加速这一过程中检测不同的事件在一个大的数据集中的放电，给出了一些手动标记的例子。H-L反向跃迁和初始旋转锁定模式的高检测准确度（>85%）在DIII-D的数百次放电数据集上得到证明，手动识别的事件中只有三次放电最初由用户标记。较低但合理的性能（1075%）也证明了核心辐射崩溃，一个事件，在数据集中的患病率低得多。此外，性能灵敏度的分析表明，相同的算法参数集是最佳的每个事件。这表明，该方法可以应用于检测各种其他事件不包括在本文中，给定的事件是很好地描述了一组0 D信号鲁棒地提供了许多放电。新事件的分析程序进行了演示，显示自动事件检测，随着用户策略性地添加手动标记的例子，保真度不断提高。还显示了在Alcator C-Mod和EAST上的检测，证明了这在多托卡马克数据集上使用的潜力。
Databases of physics events have been used in various fusion research applications, including the development of scaling laws and disruption avoidance algorithms, yet they can be time-consuming and tedious to construct. This paper presents a novel application of the label spreading semi-supervised learning algorithm to accelerate this process by detecting distinct events in a large dataset of discharges, given few manually labeled examples. A high detection accuracy (>85%) for H–L back transitions and initially rotating locked modes is demonstrated on a dataset of hundreds of discharges from DIII-D with manually identified events for which only three discharges are initially labeled by the user. Lower yet reasonable performance (∼75%) is also demonstrated for the core radiative collapse, an event with a much lower prevalence in the dataset. Additionally, analysis of the performance sensitivity indicates that the same set of algorithmic parameters is optimal for each event. This suggests that the method can be applied to detect a variety of other events not included in this paper, given that the event is well described by a set of 0D signals robustly available on many discharges. Procedures for analysis of new events are demonstrated, showing automatic event detection with increasing fidelity as the user strategically adds manually labeled examples. Detections on Alcator C-Mod and EAST are also shown, demonstrating the potential for this to be used on a multi-tokamak dataset.