Advanced Search+
Hanyu ZHANG, Lina ZHOU, Yueqiang LIU, Guangzhou HAO, Shuo WANG, Xu YANG, Yutian MIAO, Ping DUAN, Long CHEN. Deep learning approaches to recover the plasma current density profile from the safety factor based on Grad–Shafranov solutions across multiple tokamaks[J]. Plasma Science and Technology, 2024, 26(5): 055101. DOI: 10.1088/2058-6272/ad13e3
Citation: Hanyu ZHANG, Lina ZHOU, Yueqiang LIU, Guangzhou HAO, Shuo WANG, Xu YANG, Yutian MIAO, Ping DUAN, Long CHEN. Deep learning approaches to recover the plasma current density profile from the safety factor based on Grad–Shafranov solutions across multiple tokamaks[J]. Plasma Science and Technology, 2024, 26(5): 055101. DOI: 10.1088/2058-6272/ad13e3

Deep learning approaches to recover the plasma current density profile from the safety factor based on Grad–Shafranov solutions across multiple tokamaks

More Information
  • Many magnetohydrodynamic stability analyses require generation of a set of equilibria with a fixed safety factor q-profile while varying other plasma parameters. A neural network (NN)-based approach is investigated that facilitates such a process. Both multilayer perceptron (MLP)-based NN and convolutional neural network (CNN) models are trained to map the q-profile to the plasma current density J-profile, and vice versa, while satisfying the Grad–Shafranov radial force balance constraint. When the initial target models are trained, using a database of semi-analytically constructed numerical equilibria, an initial CNN with one convolutional layer is found to perform better than an initial MLP model. In particular, a trained initial CNN model can also predict the q- or J-profile for experimental tokamak equilibria. The performance of both initial target models is further improved by fine-tuning the training database, i.e. by adding realistic experimental equilibria with Gaussian noise. The fine-tuned target models, referred to as fine-tuned MLP and fine-tuned CNN, well reproduce the target q- or J-profile across multiple tokamak devices. As an important application, these NN-based equilibrium profile convertors can be utilized to provide a good initial guess for iterative equilibrium solvers, where the desired input quantity is the safety factor instead of the plasma current density.

  • [1]
    Shafranov V D 1958 Sov. Phys. - JETP 6 545
    [2]
    Lütjens H, Bondeson A and Sauter O 1996 Comput. Phys. Commun. 97 219 doi: 10.1016/0010-4655(96)00046-X
    [3]
    Kates-Harbeck J, Svyatkovskiy A and Tang W 2019 Nature 568 526 doi: 10.1038/s41586-019-1116-4
    [4]
    Zheng W et al 2018 Nucl. Fusion 58 056016 doi: 10.1088/1741-4326/aaad17
    [5]
    Dormido-Canto S et al 2013 Nucl. Fusion 53 113001 doi: 10.1088/0029-5515/53/11/113001
    [6]
    Montes K J et al 2019 Nucl. Fusion 59 096015 doi: 10.1088/1741-4326/ab1df4
    [7]
    Pau A et al 2019 Nucl. Fusion 59 106017 doi: 10.1088/1741-4326/ab2ea9
    [8]
    Rea C et al 2019 Nucl. Fusion 59 096016 doi: 10.1088/1741-4326/ab28bf
    [9]
    Fu Y C et al 2020 Phys. Plasmas 27 022501 doi: 10.1063/1.5125581
    [10]
    Zheng W et al 2022 Plasma Sci. Technol. 24 124003 doi: 10.1088/2058-6272/ac9e46
    [11]
    Guo B H et al 2021 Plasma Phys. Control. Fusion 63 025008 doi: 10.1088/1361-6587/abcbab
    [12]
    Piccione A et al 2020 Nucl. Fusion 60 046033 doi: 10.1088/1741-4326/ab7597
    [13]
    Zhu J X et al 2021 Nucl. Fusion 61 026007 doi: 10.1088/1741-4326/abc664
    [14]
    Zhao Y F et al 2022 Plasma Phys. Control. Fusion 64 045010 doi: 10.1088/1361-6587/ac4524
    [15]
    Degrave J et al 2022 Nature 602 414 doi: 10.1038/s41586-021-04301-9
    [16]
    Gaudio P et al 2014 Plasma Phys. Control. Fusion 56 114002 doi: 10.1088/0741-3335/56/11/114002
    [17]
    Li H et al 2021 Plasma Sci. Technol. 23 115102 doi: 10.1088/2058-6272/ac15ec
    [18]
    Citrin J et al 2015 Nucl. Fusion 55 092001 doi: 10.1088/0029-5515/55/9/092001
    [19]
    Meneghini O et al 2017 Nucl. Fusion 57 086034 doi: 10.1088/1741-4326/aa7776
    [20]
    Boyer M D and Chadwick J 2021 Nucl. Fusion 61 046024 doi: 10.1088/1741-4326/abe08b
    [21]
    Dong J L et al 2021 Plasma Sci. Technol. 23 085101 doi: 10.1088/2058-6272/ac0685
    [22]
    Lister J B and Saurenmann H 1991 Nucl. Fusion 31 1291 doi: 10.1088/0029-5515/31/7/005
    [23]
    van Milligen B P, Tribaldos V and Jiménez J A 1995 Phys. Rev. Lett. 75 3594 doi: 10.1103/PhysRevLett.75.3594
    [24]
    Joung S et al 2020 Nucl. Fusion 60 016034 doi: 10.1088/1741-4326/ab555f
    [25]
    Kaltsas D A and Throumoulopoulos G N 2022 Phys. Plasmas 29 022506 doi: 10.1063/5.0073033
    [26]
    Liu Y Q et al 2022 Nucl. Fusion 62 126067 doi: 10.1088/1741-4326/ac9d4c
    [27]
    Wai J T, Boyer M D and Kolemen E 2022 Nucl. Fusion 62 086042 doi: 10.1088/1741-4326/ac77e6
    [28]
    Liu Y Q et al 2020 Plasma Phys. Control. Fusion 62 045001 doi: 10.1088/1361-6587/ab6f56
    [29]
    Snyder P B et al 2004 Nucl. Fusion 44 320 doi: 10.1088/0029-5515/44/2/014
    [30]
    Sauter O, Angioni C and Lin-Liu Y R 1999 Phys. Plasmas 6 2834 doi: 10.1063/1.873240
    [31]
    Yang X et al 2016 Plasma Phys. Control. Fusion 58 114006 doi: 10.1088/0741-3335/58/11/114006
    [32]
    Liu Y Q et al 2017 Phys. Plasmas 24 056111 doi: 10.1063/1.4978884
    [33]
    Xia G L et al 2019 Nucl. Fusion 59 126035 doi: 10.1088/1741-4326/ab415d
    [34]
    Wan B N et al 2014 IEEE Trans. Plasma Sci. 42 495 doi: 10.1109/TPS.2013.2296939
    [35]
    Wan Y X et al 2017 Nucl. Fusion 57 102009 doi: 10.1088/1741-4326/aa686a
    [36]
    Zhuang G et al 2019 Nucl. Fusion 59 112010 doi: 10.1088/1741-4326/ab0e27
    [37]
    Liu Y Q 2010 Nucl. Fusion 50 095008 doi: 10.1088/0029-5515/50/9/095008
    [38]
    Zhou L N et al 2016 Plasma Phys. Control. Fusion 58 115003 doi: 10.1088/0741-3335/58/11/115003
    [39]
    Zhou L N et al 2021 Plasma Phys. Control. Fusion 63 065007 doi: 10.1088/1361-6587/abf446
    [40]
    Wroblewski D, Jahns G L and Leuer J A 1997 Nucl. Fusion 37 725 doi: 10.1088/0029-5515/37/6/I02
    [41]
    Yoshino R 2003 Nucl. Fusion 43 1771 doi: 10.1088/0029-5515/43/12/021
    [42]
    Pan S J and Yang Q A 2010 IEEE Trans. Knowl. Data Eng. 22 1345 doi: 10.1109/TKDE.2009.191
    [43]
    Zheng W et al 2023 Commun Phys. 6 181 doi: 10.1038/s42005-023-01296-9
  • Related Articles

    [1]Rajesh Prakash GURAGAIN, Hom Bahadur BANIYA, Santosh DHUNGANA, Ganesh Kuwar CHHETRI, Binita SEDHAI, Niroj BASNET, Aavash SHAKYA, Bishnu Prasad PANDEY, Suman Prakash PRADHAN, Ujjwal Man JOSHI, Deepak Prasad SUBEDI. Effect of plasma treatment on the seed germination and seedling growth of radish (Raphanus sativus)[J]. Plasma Science and Technology, 2022, 24(1): 015502. DOI: 10.1088/2058-6272/ac3476
    [2]M M RASHID, Mamunur RASHID, M M HASAN, M R TALUKDER. Rice plant growth and yield: foliar application of plasma activated water[J]. Plasma Science and Technology, 2021, 23(7): 75503-075503. DOI: 10.1088/2058-6272/abf549
    [3]Sahar A FADHLALMAWLA, Abdel-Aleam H MOHAMED, Jamal Q M ALMARASHI, Tahar BOUTRAA. The impact of cold atmospheric pressure plasma jet on seed germination and seedlings growth of fenugreek (Trigonella foenum-graecum)[J]. Plasma Science and Technology, 2019, 21(10): 105503. DOI: 10.1088/2058-6272/ab2a3e
    [4]N C ROY, M M HASAN, A H KABIR, M A REZA, M R TALUKDER, A N CHOWDHURY. Atmospheric pressure gliding arc discharge plasma treatments for improving germination, growth and yield of wheat[J]. Plasma Science and Technology, 2018, 20(11): 115501. DOI: 10.1088/2058-6272/aac647
    [5]Jinkui FENG (冯金奎), Decheng WANG (王德成), Changyong SHAO (邵长勇), Lili ZHANG (张丽丽), Xin TANG (唐欣). Effects of cold plasma treatment on alfalfa seed growth under simulated drought stress[J]. Plasma Science and Technology, 2018, 20(3): 35505-035505. DOI: 10.1088/2058-6272/aa9b27
    [6]LI Ling (李玲), LI Jiangang (李建刚), SHEN Minchong (申民翀), HOU Jinfeng (侯金凤), SHAO Hanliang (邵汉良), DONG Yuanhua (董元华), JIANG Jiafeng (蒋佳峰). Improving Seed Germination and Peanut Yields by Cold Plasma Treatment[J]. Plasma Science and Technology, 2016, 18(10): 1027-1033. DOI: 10.1088/1009-0630/18/10/10
    [7]TONG Jiayun(童家赟), HE Rui(何瑞), ZHANG Xiaoli(张晓丽), ZHAN Ruoting(詹若挺), CHEN Weiwen(陈蔚文), YANG Size(杨思泽). Effects of Atmospheric Pressure Air Plasma Pretreatment on the Seed Germination and Early Growth of Andrographis paniculata[J]. Plasma Science and Technology, 2014, 16(3): 260-266. DOI: 10.1088/1009-0630/16/3/16
    [8]DONG Xiaoyu(董晓宇), YUAN Yulian(袁玉莲), TANG Qian(唐乾), DOU Shaohua(窦少华), DI Lanbo(底兰波), ZHANG Xiuling(张秀玲). Parameter Optimization for Enhancement of Ethanol Yield by Atmospheric Pressure DBD-Treated Saccharomyces cerevisiae[J]. Plasma Science and Technology, 2014, 16(1): 73-78. DOI: 10.1088/1009-0630/16/1/16
    [9]JIANG Jiafeng(蒋佳峰), HE Xin(何昕), LI Ling(李玲), LI Jiangang(李建刚), SHAO Hanliang(邵汉良), XU Qilai(徐启来), YE Renhong(叶仁宏), DONG Yuanhua(董元华). Effect of Cold Plasma Treatment on Seed Germination and Growth of Wheat[J]. Plasma Science and Technology, 2014, 16(1): 54-58. DOI: 10.1088/1009-0630/16/1/12
    [10]LI Xiaoling (李晓玲), WAN Baonian (万宝年), GUO Zhirong (郭智荣), ZHONG Guoqiang (钟国强), HU Liqun (胡立群), LIN Shiyao (林士耀), ZHANG Xinjun (张新军), DING Siye (丁斯晔), LU Bo (吕波). Neutron Yields Based on Transport Calculation in EAST ICRF Minority Heating Plasmas[J]. Plasma Science and Technology, 2013, 15(5): 411-416. DOI: 10.1088/1009-0630/15/5/03

Catalog

    Article views (71) PDF downloads (42) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return