An advanced plasma current tomography method based on Bayesian inference and neural networks for real-time application
An advanced plasma current tomography method based on Bayesian inference and neural networks for real-time application
复制标题
一种基于贝叶斯推理和神经网络的实时应用的先进等离子体电流断层扫描方法
DOI：
10.1088/1361-6587/ac978a
复制
发表时间：
2022-10
影响因子：
2.2
通讯作者：
Jiangang Li
中科院分区：
文献类型：
--
作者：
Zijie Liu;Zhengping Luo;Tianbo Wang;Yao Huang;Yuehang Wang;Qingze Yu;Wangyi Rui;Qiping Yuan;Bingjia Xiao;Jiangang Li
抽象的。针对实验先进超导托卡马克（EAST）等离子体电流层析成像，提出了一种基于贝叶斯概率论和神经网络的等离子体电流层析成像方法。它不同于现有的基于条件自回归（CAR）先验的层析成像方法。具体地，CAR先验被替换为高级平方指数（ASE）核函数先验。因此，所提出的方法可以克服CAR先验的不足，其中计算的核心电流低于参考电流，并且在诊断中引入噪声后不确定性变得严重。ASE核先验是从平方指数核函数，通过整合有用的信息，从参考放电。ASE核先验采用非平稳超参数，并将电流剖面引入超参数中，使得电流剖面的形状在空间上更加灵活。为了提供合适的参考放电，还训练神经网络模型。每个时间片的执行时间小于1 ms，这表明它在未来的实时等离子体反馈控制的应用潜力。
Abstract. An advanced plasma current tomography method is established for the Experimental Advanced Superconducting Tokamak (EAST), which combines Bayesian probability theory and neural networks. It is different from the existing current tomography method based on a conditional autoregressive (CAR) prior. Specifically, the CAR prior is replaced with an advanced squared exponential (ASE) kernel function prior. Therefore, the proposed method can overcome the deficiencies of the CAR prior, where the calculated core current is lower than the reference current and the uncertainty becomes severe after introducing noise in the diagnostics. The ASE kernel prior is developed from the squared exponential kernel function by integrating the useful information from the reference discharge. The ASE kernel prior adopts nonstationary hyperparameters and introduces the current profile into the hyperparameters, which can make the shape of the current profile more flexible in space. To provide a suitable reference discharge, a neural network model is also trained. The execution time is less than 1 ms for each time slice, which indicates its potential for application in future real-time plasma feedback control.
登录
查看更多内容
影响因子：
3.3
作者：
M. Hole;G. V. von Nessi;J. Svensson;L. Appel
通讯作者：
M. Hole;G. V. von Nessi;J. Svensson;L. Appel
影响因子：
0.9
作者：
M. Rampp;R. Preuss;R. Fischer
通讯作者：
M. Rampp;R. Preuss;R. Fischer
影响因子：
3.3
作者：
Y. Park;S. Sabbagh;J. Berkery;J. Bialek;Y. Jeon;S. Hahn;N. Eidietis;T. Evans;S. Yoon
通讯作者：
Y. Park;S. Sabbagh;J. Berkery;J. Bialek;Y. Jeon;S. Hahn;N. Eidietis;T. Evans;S. Yoon
影响因子：
3.3
作者：
S. Sabbagh;S. Kaye;J. Menard;F. Paoletti;M. Bell;R. Bell;J. Bialek;M. Bitter;E. Fredrickson-E.-Fredr
通讯作者：
S. Sabbagh;S. Kaye;J. Menard;F. Paoletti;M. Bell;R. Bell;J. Bialek;M. Bitter;E. Fredrickson-E.-Fredr
影响因子：
2.2
作者：
M. Hole;G. V. von Nessi;M. Fitzgerald;K. McClements;J. Svensson
通讯作者：
M. Hole;G. V. von Nessi;M. Fitzgerald;K. McClements;J. Svensson