Open Access
Issue
Published:
15 July 2022
Intelligent control for predicting and mitigating major disruptions in magnetic confinement fusion
Download citation
806
Views
55
Downloads
0
Crossref
N/A
WoS
0
Scopus
N/A
CSCD
Magnetic confinement fusion is believed to be one of the promising paths that provides us with an infinite supply of an environment-friendly energy source, naturally contributing to a green economy and low-carbon development. Nevertheless, the major disruption of high temperature plasmas, a big threat to fusion devices, is still in the way of mankind accessing to fusion energy. Although a bunch of individual techniques have been proved to be feasible for the control, mitigation, and prediction of disruptions, complicated experimental environments make it hard to decide on specific control strategies. The traditional control approach, designing a series of independent controllers in a nested structure, cannot meet the needs of real-time complicated plasma control, which requires extended engineering expertise and complicated evaluation of system states referring to multiple plasma parameters. Fortunately, artificial intelligence (AI) offers potential solutions towards entirely resolving this troublesome issue. To simplify the control system, a radically novel idea for designing controllers via AI is brought forward in this work. Envisioned intelligent controllers should be developed to replace the traditional nested structure. The successful development of intelligent control is expected to effectively predict and mitigate major disruptions, which would definitely enhance fusion performance, and thus offers inspiring odds to improve the accessibility of sustainable fusion energy.
menu
Intelligent control for predicting and mitigating major disruptions in magnetic confinement fusion
Abstract
Magnetic confinement fusion is believed to be one of the promising paths that provides us with an infinite supply of an environment-friendly energy source, naturally contributing to a green economy and low-carbon development. Nevertheless, the major disruption of high temperature plasmas, a big threat to fusion devices, is still in the way of mankind accessing to fusion energy. Although a bunch of individual techniques have been proved to be feasible for the control, mitigation, and prediction of disruptions, complicated experimental environments make it hard to decide on specific control strategies. The traditional control approach, designing a series of independent controllers in a nested structure, cannot meet the needs of real-time complicated plasma control, which requires extended engineering expertise and complicated evaluation of system states referring to multiple plasma parameters. Fortunately, artificial intelligence (AI) offers potential solutions towards entirely resolving this troublesome issue. To simplify the control system, a radically novel idea for designing controllers via AI is brought forward in this work. Envisioned intelligent controllers should be developed to replace the traditional nested structure. The successful development of intelligent control is expected to effectively predict and mitigate major disruptions, which would definitely enhance fusion performance, and thus offers inspiring odds to improve the accessibility of sustainable fusion energy.
References(19)
Aymar, R., Barabaschi, P., Shimomura, Y. (2002). The ITER design. Plasma Physics and Controlled Fusion, 44: 519–565.
Hender, T. C., Wesley, J. C., Bialek, J., Bondeson, A., Boozer, A. H., Buttery, R. J., Garofalo, A., Goodman, T. P., Granetz, R. S., Gribov, Y., et al. (2007). Chapter 3: MHD stability, operational limits and disruptions. Nuclear Fusion, 47: S128.
Liu, T., Yang, J. F., Hao, G. Z., Liu, Y. Q., Wang, Z. X., Zheng, S., Wang, A. K., He, H. D. (2017). Multiple MHD instabilities in high-βN toroidal plasmas with reversed magnetic shear. Plasma Physics and Controlled Fusion, 59: 065009.
Wang, Z. X., Wei, L., Yu, F. (2015). Nonlinear evolution of neo-classical tearing modes in reversed magnetic shear tokamak plasmas. Nuclear Fusion, 55: 043005.
Liu, T., Wang, Z. X., Hu, Z. Q., Wei, L., Li, J. Q., Kishimoto, Y. (2016). On the threshold of magnetic island width in nonlinear mutual destabilization of tearing mode and ion temperature gradient mode. Physics of Plasmas, 23: 102508.
Wei, L., Wang, Z. X., Wang, J. L., Yang, X. F. (2016). Nonlinear evolution of multi-helicity neo-classical tearing modes in rotating tokamak plasmas. Nuclear Fusion, 56: 106015.
Tang, W. K., Wang, Z. X., Wei, L., Wang, J. L., Lu, S. S. (2020). Control of neoclassical tearing mode by synergetic effects of resonant magnetic perturbation and electron cyclotron current drive in reversed magnetic shear tokamak plasmas. Nuclear Fusion, 60: 026015.
Liu, T., Wei, L., Wang, F., Wang, Z. X. (2021). Coriolis force effect on suppression of neo-classical tearing mode triggered explosive burst in reversed magnetic shear tokamak plasmas. Chinese Physics Letters, 38: 045204.
Tang, W. K., Wei, L., Wang, Z. X., Wang, J. L., Liu, T., Zheng, S. (2019). Effects of resonant magnetic perturbation on locked mode of neoclassical tearing modes. Plasma Science and Technology, 21: 065103.
Wang, Z. X., Tang, W. K., Wei, L. (2022). A brief review: Effects of resonant magnetic perturbation on classical and neoclassical tearing modes in tokamaks. Plasma Science and Technology, 24: 033001.
Liu, T., Wang, Z. X., Wang, J. L., Wei, L. (2018). Suppression of explosive bursts triggered by neo-classical tearing mode in reversed magnetic shear tokamak plasmas via ECCD. Nuclear Fusion, 58: 076026.
Liu, T., Wang, Z. X., Wei, L., Wang, J. L. (2022). Prevention of electron cyclotron current drive triggering explosive bursts in reversed magnetic shear tokamak plasmas for disruption avoidance. Nuclear Fusion, 62: 056018.
Zhang, Y., Wang, X. J., Zhang, X. D., Xu, H. D., Gu, S., Zhou, T. F., Shi, T. H., Liu, H. Q., Wang, X. J., Wang, H. H., et al. (2021). Tearing mode stabilization by electron cyclotron resonant heating in EAST tokamak experiments. Nuclear Fusion, 61: 096028.
Wang, Z. R., Logan, N. C., Munaretto, S., Liu, Y. Q., Sun, Y. W., Gu, S., Park, J. K., Hanson, J. M., Hu, Q. M., Strait, T., et al. (2019). Identification of multiple eigenmode growth rates in DIII-D and EAST tokamak plasmas. Nuclear Fusion, 59: 024001.
Liu, T., Wang, Z. R., Boyer, M. D., Munaretto, S., Wang, Z. X., Park, B. H., Logan, N. C., Yang, S. M., Park, J. K. (2021). Identification of multiple eigenmode growth rates towards real time detection in DIII-D and KSTAR tokamak plasmas. Nuclear Fusion, 61: 056009.
Kates-Harbeck, J., Svyatkovskiy, A., Tang, W. (2019). Predicting disruptive instabilities in controlled fusion plasmas through deep learning. Nature, 568: 526–531.
Degrave, J., Felici, F., Buchli, J., Neunert, M., Tracey, B., Carpanese, F., Ewalds, T., Hafner, R., Abdolmaleki, A., de las Casas, D., et al. (2022). Magnetic control of tokamak plasmas through deep reinforcement learning. Nature, 602: 414–419.
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., et al. (2022). Neural network based fast prediction of βN limits in HL-2M. Plasma Physics and Controlled Fusion, 64: 045010.
Li, H., Li, J. Q., Fu, Y. L., Wang, Z. X., Jiang, M. (2022). Simulation prediction of micro-instability transition and associated particle transport in tokamak plasmas. Nuclear Fusion, 62: 036014.
Publication history
Copyright
Acknowledgements
This work is supported by the National Natural Science Foundation of China (Grant Nos. 11925501 and 12105034), the China Postdoctoral Science Foundation (Grant No. 2021M690526).
Rights and permissions
The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
FEEDBACK 
TOP