Fast estimation of ion temperature from EAST charge exchange recombination spectroscopy using neural network

Baoyue CHAI (柴宝玥); Yingying LI (李颖颖); Ze CHEN (陈泽); Wei TAO (陶巍); Yixuan ZHOU (周艺轩); Shifeng MAO (毛世峰); Zhengping LUO (罗正平); Yi YU (余羿); Bo LYU (吕波); Minyou YE (叶民友)

doi:10.1088/2058-6272/ab2674

Plasma Science and Technology > 2019 > 21(10): 105103. > DOI: 10.1088/2058-6272/ab2674

Baoyue CHAI (柴宝玥), Yingying LI (李颖颖), Ze CHEN (陈泽), Wei TAO (陶巍), Yixuan ZHOU (周艺轩), Shifeng MAO (毛世峰), Zhengping LUO (罗正平), Yi YU (余羿), Bo LYU (吕波), Minyou YE (叶民友). Fast estimation of ion temperature from EAST charge exchange recombination spectroscopy using neural network[J]. Plasma Science and Technology, 2019, 21(10): 105103. DOI: 10.1088/2058-6272/ab2674

Citation:

PDF (998 KB)

Fast estimation of ion temperature from EAST charge exchange recombination spectroscopy using neural network

¹ Department of Engineering and Applied Physics, University of Science and Technology of China, Hefei 230026, People's Republic of China
² Institute of Plasma Physics, Chinese Academy of Sciences, Hefei 230031, People's Republic of China

Funds: This work is supported by National Natural Science Foundation of China (No. 11535013), the National Key Research and Development Program of China (Nos. 2017YFA0402500, 2018YFE0302100), and the Users with Excellence Project of Hefei Science Center CAS (No. 2018HSC-UE010).

More Information

Received Date: February 19, 2019
Revised Date: June 02, 2019
Accepted Date: June 02, 2019

Graphical Abstract

Abstract

Abstract

Ion temperature, as one of the most critical plasma parameters, can be diagnosed by charge exchange recombination spectroscopy (CXRS). Iterative least-squares fitting is conventionally used to analyze CXRS spectra to identify the active charge exchange component, which is the result of local interaction between impurity ions with a neutral beam. Due to the limit of the time consumption of the conventional approach (∼100 ms per frame), the Experimental Advanced Superconducting Tokamak CXRS data is now analyzed in-between shots. To explore the feasibility of real-time measurement, neural networks are introduced to perform fast estimation of ion temperature. Based on the same four-layer neural network architecture, two neural networks are trained for two central chords according to the ion temperature data acquired from the conventional method. Using the TensorFlow framework, the training procedures are performed by an error back-propagation algorithm with the regularization via the weight decay method. Good agreement in the deduced ion temperature is shown for the neural networks and the conventional approach, while the data processing time is reduced by 3 orders of magnitude (∼0.1 ms per frame) by using the neural networks.
- CXRS,
- neural network,
- ion temperature,
- EAST

FullText(HTML)

References (31)

References

[1]	Li Y Y et al 2014 Rev. Sci. Instrum. 85 11E428
[2]	Zhang Y et al 2015 Fusion Eng. Des. 96–97 840
[3]	Ye M Y et al 2015 Fusion Eng. Des. 96–97 1017
[4]	Li Y Y et al 2016 Rev. Sci. Instrum. 87 11E501
[5]	Fonck R J, Darrow D S and Jaehnig K P 1984 Phys. Rev. A 29 3288
[6]	Isler R C 1994 Plasma Phys. Control. Fusion 36 171
[7]	Seraydarian R P et al 1986 Rev. Sci. Instrum. 57 155
[8]	Tunklev M et al 1999 Plasma Phys. Control. Fusion 41 985
[9]	Litaudon X 2011 Fusion Sci. Technol. 59 469
[10]	Kobayashi S et al 2007 Plasma Fusion Res. 2 S1049
[11]	Yoshida M et al 2009 Fusion Eng. Des. 84 2206
[12]	Podestà M and Bell R E 2012 Rev. Sci. Instrum. 83 033503
[13]	Podestà M and Bell R E 2016 Plasma Phys. Control. Fusion 58 125016
[14]	Heesterman P J L et al 2003 Rev. Sci. Instrum. 74 1783
[15]	Joffrin E et al 2003 Plasma Phys. Control. Fusion 45 A367
[16]	Yu D L et al 2009 Fusion Sci. Technol. 56 1521
[17]	Ma Q et al 2015 J. Quant. Spectrosc. Radiat. Transf. 166 74
[18]	Bishop C M 1994 Rev. Sci. Instrum. 65 1803
[19]	Bishop C M, Roach C M and von Hellermann M G 1993 Plasma Phys. Control. Fusion 35 765
[20]	Baker D R, Groebner R J and Burrell K H 1994 Plasma Phys.Control. Fusion 36 109
[21]	Svensson J, von Hellermann M and König RWT 1999 Plasma Phys. Control. Fusion 41 315
[22]	Kurihara K et al 2008 Fusion Eng. Des. 83 959
[23]	Xie Y H et al 2014 Rev. Sci. Instrum. 85 02B315
[24]	Viezzer E et al 2011 Plasma Phys. Control. Fusion 53 035002
[25]	McCulloch W S and Pitts W H 1943 Bull. Math. Biophys.5 115
[26]	Rosenblatt F 1958 Psychol. Rev. 65 386
[27]	TensorFlow https://github.com/tensorflow
[28]	Huang G B 2003 IEEE Trans. Neural Networks 14 274
[29]	Reed R 1993 IEEE Trans. Neural Networks 4 740
[30]	Lang K J and Hinton G E 1990 Dimensionality reduction and prior knowledge in E-set recognition ed D S Touretzky Advances in Neural Information Processing Systems 2 (San Francisco: Morgan Kaufmann) vol 1990, 178
[31]	Rumelhart D E, Hinton G E and Williams R J 1986 Nature 323 533

[1]	Maria YOUNUS, N U REHMAN, M SHAFIQ, M NAEEM, M ZAKA-UL-ISLAM, M ZAKAULLAH. Evolution of plasma parameters in an Ar–N₂/ He inductive plasma source with magnetic pole enhancement[J]. Plasma Science and Technology, 2017, 19(2): 25402-025402. DOI: 10.1088/2058-6272/19/2/025402
[2]	NI Gengsong (倪耿松), QIAN Muyang (钱沐杨), YANG Congying (杨丛影), LIU Sanqiu (刘三秋), WANG Dezhen (王德真). N₂ Mole Fraction Dependence of Plasma Bullet Propagation in Premixed He/N₂ Plasma Needle Discharge at Atmospheric Pressure[J]. Plasma Science and Technology, 2016, 18(7): 751-758. DOI: 10.1088/1009-0630/18/7/09
[3]	A. K. FEROUANI, M. LEMERINI, L. MERAD, M. HOUALEF. Numerical Modelling Point-to-Plane of Negative Corona Discharge in N₂ Under Non-Uniform Electric Field[J]. Plasma Science and Technology, 2015, 17(6): 469-474. DOI: 10.1088/1009-0630/17/6/06
[4]	ZHENG Dianchun(郑殿春), WANG Jia(王佳), CHEN Chuntian(陈春天), ZHAO Dawei(赵大伟), ZHANG Chunxi(张春喜), YANG Jiaxiang(杨嘉祥). Dynamic Characteristics of SF₆ -N ₂ -CO ₂ Gas Mixtures in DC Discharge Process[J]. Plasma Science and Technology, 2014, 16(9): 848-855. DOI: 10.1088/1009-0630/16/9/08
[5]	Djilali BENYOUCEF, Mohammed YOUSFI. Ar ⁺ /Ar, O₂ ⁺ /O₂ and N₂ ⁺ /N ₂ Elastic Momentum Collision Cross Sections: Calculation and Validation Using the Semi-Classical Model[J]. Plasma Science and Technology, 2014, 16(6): 588-592. DOI: 10.1088/1009-0630/16/6/09
[6]	LIU Xuan(刘璇), GE Jie(葛婕), YANG Yi(杨轶), SONG Yixu(宋亦旭), REN Tianling(任天令). Feature Scale Simulation of PECVD of SiO ₂ in SiH ₄ /N₂ O Mixture[J]. Plasma Science and Technology, 2014, 16(4): 385-389. DOI: 10.1088/1009-0630/16/4/15
[7]	YOU Zuowei(尤左伟), DAI Zhongling(戴忠玲), WANG Younian(王友年). Simulation of Capacitively Coupled Dual-Frequency N ₂, O₂, N ₂ /O ₂Discharges: Effects of External Parameters on Plasma Characteristics[J]. Plasma Science and Technology, 2014, 16(4): 335-343. DOI: 10.1088/1009-0630/16/4/07
[8]	XIN Yu(信裕), DING Hongbin(丁洪斌). Ab initio Calculations of Electron-Impact Excitation Cross Sections for N₂[J]. Plasma Science and Technology, 2014, 16(2): 104-109. DOI: 10.1088/1009-0630/16/2/04
[9]	DI Lanbo, LI Xiaosong, ZHAO Tianliang, CHANG Dalei, LIU Qianqian, ZHU Aimin. Tuning Effect of N₂ on Atmospheric-Pressure Cold Plasma CVD of TiO₂ Photocatalytic Films[J]. Plasma Science and Technology, 2013, 15(1): 64-69. DOI: 10.1088/1009-0630/15/1/11
[10]	YU Yiqing(虞一青), XIN Yu(辛煜), LU Wenqi(陆文琪), NING Zhaoyuan(宁兆元). Abnormal Enhancement of N₂⁺ Emission Induced by Lower Frequencies in N₂ Dual-Frequency Capacitively Coupled Plasmas[J]. Plasma Science and Technology, 2012, 14(3): 222-226. DOI: 10.1088/1009-0630/14/3/07

Cited By

Cited by

Periodical cited type(7)

1.	Chen, S., Li, Z., Gao, Y. et al. Preparation of few-layer graphene by annealing Ni film with low carbon content deposited by direct current magnetron sputtering. Vacuum, 2024. DOI:10.1016/j.vacuum.2024.113421
2.	Li, Q., Qi, Y., Cheng, W. et al. Combined effects of electron doping and surface polarity on the ferromagnetism in Gd implanted polar ZnO wafers. Journal of Alloys and Compounds, 2023. DOI:10.1016/j.jallcom.2022.167319
3.	Li, Q., Ying, M. Ion implantation induced d0 ferromagnetism in oxide semiconductors. Defect-Induced Magnetism in Oxide Semiconductors, 2023. DOI:10.1016/B978-0-323-90907-5.00019-1
4.	Zhang, H., Liu, Y., Chen, Q. Research Progress on Optoelectronic Thin Films Deposited by HiPIMS: Discharge Characteristics and Parameter Adjustment \| [HiPIMS 沉积光电薄膜研究进展：放电特性和参数调控]. Zhongguo Biaomian Gongcheng/China Surface Engineering, 2022, 35(5): 93-104. DOI:10.11933/j.issn.1007-9289.20211231004
5.	Bai, X., Cai, Q., Zhang, X. Research Progress of Crystalline Thin Films by High Power Impulse Magnetron Sputtering at a Low Temperature \| [高能脉冲磁控溅射低温制备晶态薄膜的研究进展]. Zhongguo Biaomian Gongcheng/China Surface Engineering, 2022, 35(5): 105-115. DOI:10.11933/j.issn.1007-9289.20211213002
6.	Li, Q., Zhang, M., Yan, W. et al. Effects of electron doping on the d0 magnetism in N-implanted ZnO and ZnAlO films. Ceramics International, 2022, 48(14): 19831-19836. DOI:10.1016/j.ceramint.2022.03.258
7.	Egbo, K.O., Chibueze, T.C., Raji, A.T. et al. Effects of acceptor doping and oxygen stoichiometry on the properties of sputter-deposited p-type rocksalt NixZn1-xO (0.3≤x≤1.0) alloys. Journal of Alloys and Compounds, 2022. DOI:10.1016/j.jallcom.2022.164224

Other cited types(0)

Get Citation

PDF

XML

Article views (436) PDF downloads (112) Cited by(7)

Turn off MathJax

Article Contents

Abstract

References

Fast estimation of ion temperature from EAST charge exchange recombination spectroscopy using neural network