Neural network based fast prediction of β N limits in HL-2M

Zhao, Y. F.; Liu, Y. Q.; Wang, S.; Hao, G. Z.; Wang, Z. X.; Yang, Z. Y.; Li, B.; Li, J. X.; Chen, H. T.; Xu, M.; Duan, X. R.

doi:10.1088/1361-6587/ac4524

Neural network based fast prediction of β _N limits in HL-2M

Journal Article · 16 February 2022 · Plasma Physics and Controlled Fusion

DOI:https://doi.org/10.1088/1361-6587/ac4524· OSTI ID:1979304

; ; ; ; Wang, Z. X.; Yang, Z. Y.; Li, B.; Li, J. X.; Chen, H. T.; Xu, M.; Duan, X. R.

Artificial neural networks (NNs) are trained, based on the numerical database, to predict the no-wall and ideal-wall β_N limits, due to onset of the n = 1 (n is the toroidal mode number) ideal external kink instability, for the HL-2M tokamak. The database is constructed by toroidal computations utilizing both the equilibrium code CHEASE (Lütjens et al 1992 Comput. Phys. Commun. 69 287) and the stability code MARS-F (Liu et al 2000 Phys. Plasmas 7 3681). The stability results show that (1) the plasma elongation generally enhances both β_N limits, for either positive or negative triangularity plasmas; (2) the effect is more pronounced for positive triangularity plasmas; (3) the computed no-wall β_N limit linearly scales with the plasma internal inductance, with the proportionality coefficient ranging between 1 and 5 for HL-2M; (4) the no-wall limit substantially decreases with increasing pressure peaking factor. Furthermore, both the NN model and the convolutional neural network (CNN) model are trained and tested, producing consistent results. The trained NNs predict both the no-wall and ideal-wall limits with as high as 95% accuracy, compared to those directly computed by the stability code. Additional test cases, produced by the Tokamak Simulation Code (Jardin et al 1993 Nucl. Fusion 33 371), also show reasonable performance of the trained NNs, with the relative error being within 10%. The constructed database provides effective references for the future HL-2M operations. The trained NNs can be used as a real-time monitor for disruption prevention in the HL-2M experiments, or serve as part of the integrated modeling tools for ideal kink stability analysis.

Research Organization:: General Atomics, San Diego, CA (United States)

Sponsoring Organization:: USDOE Office of Science (SC)

DOE Contract Number:: FC02-04ER54698; FG02-95ER54309

OSTI ID:: 1979304

Journal Information:: Plasma Physics and Controlled Fusion, Vol. 64, Issue 4; ISSN 0741-3335

Publisher:: IOP Science

Country of Publication:: United States

Language:: English

References (37)

Modelling resistive wall modes in ITER with self-consistent inclusion of drift kinetic resonances Liu, Yueqiang; Chu, M. S.; Chapman, I. T. Nuclear Fusion, Vol. 49, Issue 3 https://doi.org/10.1088/0029-5515/49/3/035004	journal	February 2009
Synergism between cross-section and profile shaping in beta optimization of tokamak equilibria with negative central shear Turnbull, A. D.; Taylor, T. S.; Chu, M. S. Nuclear Fusion, Vol. 38, Issue 10 https://doi.org/10.1088/0029-5515/38/10/305	journal	October 1998
Reconstruction of current profile parameters and plasma shapes in tokamaks Lao, L. L.; St. John, H.; Stambaugh, R. D. Nuclear Fusion, Vol. 25, Issue 11 https://doi.org/10.1088/0029-5515/25/11/007	journal	November 1985
Feedforward beta control in the KSTAR tokamak by deep reinforcement learning Seo, Jaemin; Na, Y. -S.; Kim, B. Nuclear Fusion, Vol. 61, Issue 10 https://doi.org/10.1088/1741-4326/ac121b	journal	September 2021
Plasma-Resistivity-Induced Strong Damping of the Kinetic Resistive Wall Mode He, Yuling; Liu, Yueqiang; Liu, Yue Physical Review Letters, Vol. 113, Issue 17 https://doi.org/10.1103/PhysRevLett.113.175001	journal	October 2014
Active control of the resistive wall mode with power saturation Li, Li; Liu, Yue; Liu, Yueqiang Physics of Plasmas, Vol. 19, Issue 1 https://doi.org/10.1063/1.3672512	journal	January 2012
Disruption prediction using a full convolutional neural network on EAST Guo, B. H.; Shen, B.; Chen, D. L. Plasma Physics and Controlled Fusion, Vol. 63, Issue 2 https://doi.org/10.1088/1361-6587/abcbab	journal	December 2020
TSC simulation of Ohmic discharges in TFTR Jardin, S. C.; Bell, M. G.; Pomphrey, N. Nuclear Fusion, Vol. 33, Issue 3 https://doi.org/10.1088/0029-5515/33/3/I01	journal	March 1993
Stabilization of the external kink and the resistive wall mode Chu, M. S.; Okabayashi, M. Plasma Physics and Controlled Fusion, Vol. 52, Issue 12 https://doi.org/10.1088/0741-3335/52/12/123001	journal	October 2010
Progress toward fully noninductive discharge operation in DIII-D using off-axis neutral beam injection Ferron, J. R.; Holcomb, C. T.; Luce, T. C. Physics of Plasmas, Vol. 20, Issue 9 https://doi.org/10.1063/1.4821072	journal	September 2013
Real-time capable first principle based modelling of tokamak turbulent transport Citrin, J.; Breton, S.; Felici, F. Nuclear Fusion, Vol. 55, Issue 9 https://doi.org/10.1088/0029-5515/55/9/092001	journal	July 2015
Hybrid neural network for density limit disruption prediction and avoidance on J-TEXT tokamak Zheng, W.; Hu, F. R.; Zhang, M. Nuclear Fusion, Vol. 58, Issue 5 https://doi.org/10.1088/1741-4326/aaad17	journal	March 2018
Modeling active control of resistive wall mode with power saturation and sensor noise on HL-2M Wang, S.; Liu, Y. Q.; Xia, G. L. Plasma Physics and Controlled Fusion, Vol. 63, Issue 5 https://doi.org/10.1088/1361-6587/abf315	journal	April 2021
Optimization of DIII-D advanced tokamak discharges with respect to the β limit Ferron, J. R.; Casper, T. A.; Doyle, E. J. Physics of Plasmas, Vol. 12, Issue 5 https://doi.org/10.1063/1.1871247	journal	May 2005
Real-time capable modeling of neutral beam injection on NSTX-U using neural networks Boyer, M. D.; Kaye, S.; Erickson, K. Nuclear Fusion, Vol. 59, Issue 5 https://doi.org/10.1088/1741-4326/ab0762	journal	March 2019
MHD-Limits to Plasma Confinement Troyon, F.; Gruber, R.; Saurenmann, H. Plasma Physics and Controlled Fusion, Vol. 26, Issue 1A https://doi.org/10.1088/0741-3335/26/1A/319	journal	January 1984
Hybrid deep-learning architecture for general disruption prediction across multiple tokamaks Zhu, J. X.; Rea, C.; Montes, K. Nuclear Fusion, Vol. 61, Issue 2 https://doi.org/10.1088/1741-4326/abc664	journal	December 2020
Robust control of resistive wall modes in tokamaks Liu, Yueqiang; Bondeson, A. Plasma Physics and Controlled Fusion, Vol. 44, Issue 5 https://doi.org/10.1088/0741-3335/44/5/101	journal	May 2002
Machine learning control for disruption and tearing mode avoidance Fu, Yichen; Eldon, David; Erickson, Keith Physics of Plasmas, Vol. 27, Issue 2 https://doi.org/10.1063/1.5125581	journal	February 2020
Self-consistent core-pedestal transport simulations with neural network accelerated models Meneghini, O.; Smith, S. P.; Snyder, P. B. Nuclear Fusion, Vol. 57, Issue 8 https://doi.org/10.1088/1741-4326/aa7776	journal	July 2017
Access to sustained high-beta with internal transport barrier and negative central magnetic shear in DIII-D Garofalo, A. M.; Doyle, E. J.; Ferron, J. R. Physics of Plasmas, Vol. 13, Issue 5 https://doi.org/10.1063/1.2185010	journal	May 2006
Stabilization of resistive wall modes in ITER by active feedback and toroidal rotation Liu, Yueqiang; Bondeson, A.; Gribov, Y. Nuclear Fusion, Vol. 44, Issue 2 https://doi.org/10.1088/0029-5515/44/2/003	journal	January 2004
Effect of Trapped Energetic Particles on the Resistive Wall Mode Hao, G. Z.; Wang, A. K.; Liu, Y. Q. Physical Review Letters, Vol. 107, Issue 1 https://doi.org/10.1103/PhysRevLett.107.015001	journal	July 2011
Physical understanding of the instability spectrum and the feedback control of resistive wall modes in reversed field pinch Wang, Z. R.; Guo, S. C. Nuclear Fusion, Vol. 51, Issue 5 https://doi.org/10.1088/0029-5515/51/5/053004	journal	April 2011
Neural network based prediction of no-wall β _N limits due to ideal external kink instabilities Liu, Yueqiang; Lao, Lang; Li, Li Plasma Physics and Controlled Fusion, Vol. 62, Issue 4 https://doi.org/10.1088/1361-6587/ab6f56	journal	February 2020
Stabilization of external modes in tokamaks by resistive walls and plasma rotation Bondeson, A.; Ward, D. J. Physical Review Letters, Vol. 72, Issue 17 https://doi.org/10.1103/PhysRevLett.72.2709	journal	April 1994
Stabilization of resistive wall modes in tokamaks by drift kinetic effects combined with magnetic feedback Xia, Guoliang; Liu, Yueqiang; Liu, Yue Nuclear Fusion, Vol. 55, Issue 9 https://doi.org/10.1088/0029-5515/55/9/093007	journal	July 2015
Predicting disruptive instabilities in controlled fusion plasmas through deep learning Kates-Harbeck, Julian; Svyatkovskiy, Alexey; Tang, William Nature, Vol. 568, Issue 7753 https://doi.org/10.1038/s41586-019-1116-4	journal	April 2019
The component development status of HL-2M tokamak Li, Qiang Fusion Engineering and Design, Vol. 96-97 https://doi.org/10.1016/j.fusengdes.2015.06.106	journal	October 2015
MHD beta limits for advanced scenarios on JET Bondeson, A.; Liu, D. -H; Söldner, F. X. Nuclear Fusion, Vol. 39, Issue 11 https://doi.org/10.1088/0029-5515/39/11/303	journal	November 1999
Long Short-Term Memory Hochreiter, Sepp; Schmidhuber, Jürgen Neural Computation, Vol. 9, Issue 8 https://doi.org/10.1162/neco.1997.9.8.1735	journal	November 1997
A disruption predictor based on a 1.5-dimensional convolutional neural network in HL-2A Yang, Zongyu; Xia, Fan; Song, Xianming Nuclear Fusion, Vol. 60, Issue 1 https://doi.org/10.1088/1741-4326/ab4b6f	journal	November 2019
Axisymmetric MHD equilibrium solver with bicubic Hermite elements Lütjens, H.; Bondeson, A.; Roy, A. Computer Physics Communications, Vol. 69, Issue 2-3 https://doi.org/10.1016/0010-4655(92)90167-W	journal	March 1992
Feedback stabilization of nonaxisymmetric resistive wall modes in tokamaks. I. Electromagnetic model Liu, Y. Q.; Bondeson, A.; Fransson, C. M. Physics of Plasmas, Vol. 7, Issue 9 https://doi.org/10.1063/1.1287744	journal	September 2000
First plasma scenario development for HL-2M Song, X. M.; Li, J. X.; Leuer, J. A. Fusion Engineering and Design, Vol. 147 https://doi.org/10.1016/j.fusengdes.2019.111254	journal	October 2019
Three-Dimensional Drift Kinetic Response of High- β Plasmas in the DIII-D Tokamak Wang, Z. R.; Lanctot, M. J.; Liu, Y. Q. Physical Review Letters, Vol. 114, Issue 14 https://doi.org/10.1103/PhysRevLett.114.145005	journal	April 2015
Chapter 3: MHD stability, operational limits and disruptions Hender, T. C.; Wesley, J. C.; Bialek, J. Nuclear Fusion, Vol. 47, Issue 6 https://doi.org/10.1088/0029-5515/47/6/S03	journal	June 2007

Similar Records

Modeling active control of resistive wall mode with power saturation and sensor noise on HL-2M

Journal Article · 2021 · Plasma Physics and Controlled Fusion · OSTI ID:1849029

Wang, S.; Liu, Y. Q.; Xia, G. L.; +8 more

Neural network based prediction of no-wall β _N limits due to ideal external kink instabilities

Journal Article · 2020 · Plasma Physics and Controlled Fusion · OSTI ID:1658371

Liu, Yueqiang; Lao, Lang; Li, Li; +1 more

Effects of NBI-induced energetic ions on internal kink stability in HL-2M

Journal Article · 2023 · Physics of Plasmas · OSTI ID:2418884

Dong, G. Q.; Liu, Y. Q.; Hao, G. Z.; +6 more

Related Subjects

Physics

Neural network based fast prediction of β N limits in HL-2M

Citation Formats

References (37)

Similar Records

Related Subjects

Neural network based fast prediction of β _N limits in HL-2M