An advanced plasma current tomography method based on Bayesian inference and neural networks for real-time application

doi:10.1088/1361-6587/ac978a

	An advanced plasma current tomography method based on Bayesian inference and neural networks for real-time application
	Liu, Zijie 1,2,3; Luo, Zhengping 1; Wang, Tianbo 3; Huang, Yao 1; Wang, Yuehang 1; Yu, Qingze 1; Rui, Wangyi 1; Yuan, Qiping 1; Xiao, Bingjia 1,2; Li, Jiangang 1,2
刊名	PLASMA PHYSICS AND CONTROLLED FUSION
	2022-12-01
卷号	64
关键词	plasma current tomography Bayesian inference neural network
ISSN号	0741-3335
DOI	10.1088/1361-6587/ac978a
通讯作者	Luo, Zhengping(zhengping.luo@ipp.ac.cn) ; Wang, Tianbo(wangtianbo@swip.ac.cn)
英文摘要	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.
资助项目	National MCF Energy R&D Program of China[2018YFE0302100] ; National MCF Energy R&D Program of China[2018YFE0301105] ; National Natural Science Foundation of China[11875291] ; National Natural Science Foundation of China[11805236] ; National Natural Science Foundation of China[11905256] ; National Natural Science Foundation of China[12075285]
WOS关键词	EQUILIBRIUM RECONSTRUCTION ; MHD EQUILIBRIUM
WOS研究方向	Physics
语种	英语
出版者	IOP Publishing Ltd
WOS记录号	WOS:000874229300001
资助机构	National MCF Energy R&D Program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/129865]
专题	中国科学院合肥物质科学研究院
通讯作者	Luo, Zhengping; Wang, Tianbo
作者单位	1.Chinese Acad Sci, Inst Plasma Phys, POB 1126, Hefei 230031, Peoples R China 2.Univ Sci & Technol China, Hefei 230031, Peoples R China 3.CNNC, Southwestern Inst Phys, Chengdu 610200, Peoples R China
推荐引用方式 GB/T 7714	Liu, Zijie,Luo, Zhengping,Wang, Tianbo,et al. An advanced plasma current tomography method based on Bayesian inference and neural networks for real-time application[J]. PLASMA PHYSICS AND CONTROLLED FUSION,2022,64.
APA	Liu, Zijie.,Luo, Zhengping.,Wang, Tianbo.,Huang, Yao.,Wang, Yuehang.,...&Li, Jiangang.(2022).An advanced plasma current tomography method based on Bayesian inference and neural networks for real-time application.PLASMA PHYSICS AND CONTROLLED FUSION,64.
MLA	Liu, Zijie,et al."An advanced plasma current tomography method based on Bayesian inference and neural networks for real-time application".PLASMA PHYSICS AND CONTROLLED FUSION 64(2022).