Real-Time Estimation of Vertical Instability Growth Rate for EAST Plasma With MLP
Real-Time Estimation of Vertical Instability Growth Rate for EAST Plasma With MLP
复制标题
DOI：
10.1109/tps.2023.3321377
复制
发表时间：
2023-10
影响因子：
1.5
通讯作者：
B. N. Liu;W. H. Hu;Y. Huang;Z. Luo;Y. H. Wang;Q. Yuan;R. R. Zhang-R.;B. Xiao
中科院分区：
文献类型：
--
作者：
B. N. Liu;W. H. Hu;Y. Huang;Z. Luo;Y. H. Wang;Q. Yuan;R. R. Zhang-R.;B. Xiao
垂直不稳定性（VI）是通过先进托克马克实现聚变能的主要挑战之一。垂直位移事件（VDE）是由垂直位移事件（VDE）引起的。VDE不仅对面向等离子体的部件造成严重的热负荷，而且对第一壁产生巨大的机械负荷。VI增长率不仅是VI识别的重要参数，也是垂直位移主动控制的重要参数。在这项工作中，多层感知器（MLP）模型估计等离子体VI增长率（$\gamma $）的实验先进超导托卡马克（EAST）。与传统的求解刚性等离子体响应模型方程的方法相比，该模型在计算速度上具有很大的优势。在该模型中，38个磁探针测量除以等离子体电流（$I_{p}$）归一化作为输入特征。同时，以等离子体平衡参数为输入特征，对神经网络进行训练，以供比较。结果表明，预测精度略低于原始模型。平均绝对误差（MAE）从1.02 $\text{s}^{-1}$增加到1.68 $\text{s}^{-2}$，均方误差（MSE）从1.89 $\text{s}^{-2}$增加到10.03 $\text{s}^{-2}$。最后，讨论了与神经网络的可解释性有关的问题。
Vertical instability (VI) is one of the main challenges for fusion energy realization through advanced tokamak. The disruption caused by VI is known as vertical displacement event (VDE). VDE not only causes serious thermal load to the plasma-facing components but also generates huge mechanical load to the first wall. VI growth rate is a crucial parameter not only for VI identification but also for active control of vertical displacement. In this work, the multilayer perceptron (MLP) model is employed to estimate the plasma VI growth rate ( $\gamma $ ) of the experimental advanced superconducting tokamak (EAST). This model shows great advantages in calculation speed compared with the conventional way of solving rigid plasma response model equations. In this model, 38 magnetic probe measurements divided by plasma current ( $I_{p}$ ) for normalization are taken as input features. Meanwhile, the neural network was trained by taking plasma equilibrium parameters as input features for comparison. The results demonstrate a slightly lower prediction accuracy than the original model. The mean absolute error (MAE) increased from 1.02 to 1.68 $\text{s}^{-1}$ , and the mean square error (MSE) increased from 1.89 to 10.03 $\text{s}^{-2}$ . Finally, issues related to the interpretability of neural networks are discussed.