Ion temperature gradient control using reinforcement learning technique

T. Wakatsuki

doi:10.1088/1741-4326/abe68d

2021-03-18

PRE

DOI：10.1088/1741-4326/abe68d

原文链接

原文求助

摘要

En 中文

Plasma with an internal transport barrier (ITB) is desirable for a steady-state tokamak reactor because of its high confinement quality and high bootstrap current fraction. However, the local pressure gradient tends to be steep and the plasma often becomes unstable. In this study, an ion temperature gradient control system based on neutral beam injection (NBI) is developed using the reinforcement learning technique. The response characteristics of an ion temperature gradient to NBI are non-linear and sensitive to experimental conditions, which makes it difficult to develop a robust control system. Our control system is trained for plasmas with a wide range of ITB strengths. Using the reinforcement learning technique, the system acquires a robust control feature through several thousand iterations of trial and error in an integrated transport simulation hosted by TOPICS. The control system is composed of neural networks (NNs) whose input variables are the ion temperature gradient, the current NBI power, and the NBI powers for several previous control time steps. The trained system can determine a control output which is suitable for the response characteristics inferred from the input variables. The trained control system is tested in the TOPICS simulation using plasma models based on two experimental plasmas of JT-60U with different ITB strengths. It is shown that the ion temperature gradient can be appropriately controlled for both plasmas, which supports the expectation that this system is applicable to real experiments.

Keyword:

control

reinforcement learning

JT-60U

期刊

Nuclear Fusion

IF:

论文数:

9.3K

被引数:

2.2W

机构

national institutes for quantum science & technology

学者数:

3.4K

论文数: 2.7K

被引数: 0

引用论文

Integrated modeling applications for tokamak experiments with OMFIT 利用OMFIT进行托卡马克实验的集成建模应用

NUCLEAR FUSION

IF4

2015-07-01

332

PREAI

Meneghini, O.; Smith, S. P.; Lao, L. L.; Izacard, O.; Ren, Q.; Park, J. M.; Candy, J.; Wang, Z.; Luna, C. J.; Izzo, V. A.; Grierson, B. A.; Snyder, P. B.; Holland, C.; Penna, J.; Lu, G.; Raum, P.; McCubbin, A.; Orlov, D. M.; Belli, E. A.; Ferraro, N. M.; Prater, R.; Osborne, T. H.; Turnbull, A. D.; Staebler, G. M.

Sustaining Community-School Relationships Around Shared Visions of Climate Justice and Science Teaching

Connected Science Learning

IF0

2023-12-13

PREAI

David Segura; Daniel Morales-Doyle; Susan Nelson; Amy Levingston; Karen Canales

Firm reputation and incentives to “milk” pending patents

International Journal of Industrial Organization

IF0

2015-11-01

OAAI

Johannes Koenen; Martin Peitz

Profile control simulations and experiments on TCV: a controller test environment and results using a model-based predictive controller TCV上的轮廓控制仿真和实验: 使用基于模型的预测控制器的控制器测试环境和结果

NUCLEAR FUSION

IF4

2017-10-27

OAAI

Maljaars, E.; Felici, F.; Blanken, T. C.; Galperti, C.; Sauter, O.; de Baar, M. R.; Carpanese, F.; Goodman, T. P.; Kim, D.; Kim, S. H.; Kong, M.; Mavkov, B.; Merle, A.; Moret, J. M.; Nouailletas, R.; Scheffer, M.; Teplukhina, A. A.; Vu, N. M. T.

Enhanced reproducibility of L-mode plasma discharges via physics-model-based q-profile feedback control in DIII-D 通过diii-d中基于物理模型的q轮廓反馈控制增强了L模式等离子体放电的可重复性

NUCLEAR FUSION

IF4

2017-08-09

OAAI

Schuster, E.; Wehner, W. P.; Barton, J. E.; Boyer, M. D.; Luce, T. C.; Ferron, J. R.; Holcomb, C. T.; Walker, M. L.; Humphreys, D. A.; Solomon, W. M.; Penaflor, B. G.; Johnson, R. D.

Safety factor profile control with reduced central solenoid flux consumption during plasma current ramp-up phase using a reinforcement learning technique

NUCLEAR FUSION

IF4

2019-05-08

PREAI

Wakatsuki, T.; Suzuki, T.; Hayashi, N.; Oyama, N.; Ide, S.

Higher vibrational states of OH/OD in the bulk of congruent LiNbO₃and in proton/deuteron exchanged layers at the surface of LiNbO₃

Journal of Physics: Condensed Matter

IF0

1999-01-01

PREAI

A Grone; S Kapphan

The CRONOS suite of codes for integrated tokamak modelling

NUCLEAR FUSION

IF4

2010-03-16

253

PREAI

Artaud, J. F.; Basiuk, V.; Imbeaux, F.; Schneider, M.; Garcia, J.; Giruzzi, G.; Huynh, P.; Aniel, T.; Albajar, F.; Ane, J. M.; Becoulet, A.; Bourdelle, C.; Casati, A.; Colas, L.; Decker, J.; Dumont, R.; Eriksson, L. G.; Garbet, X.; Guirlet, R.; Hertout, P.; Hoang, G. T.; Houlberg, W.; Huysmans, G.; Joffrin, E.; Kim, S. H.; Koechl, F.; Lister, J.; Litaudon, X.; Maget, P.; Masset, R.; Pegourie, B.; Peysson, Y.; Thomas, P.; Tsitroneand, E.; Turco, F.

Real-time physics-model-based simulation of the current density profile in tokamak plasmas

NUCLEAR FUSION

IF4

2011-08-08

121

OAAI

Felici, F.; Sauter, O.; Coda, S.; Duval, B. P.; Goodman, T. P.; Moret, J-M.; Paley, J. I.

The European Integrated Tokamak Modelling (ITM) effort: achievements and first physics results 欧洲综合托卡马克建模 (ITM) 工作: 成就和第一个物理结果

NUCLEAR FUSION

IF4

2014-03-20

OAAI

Falchetto, G. L.; Coster, D.; Coelho, R.; Scott, B. D.; Figini, L.; Kalupin, D.; Nardon, E.; Nowak, S.; Alves, L. L.; Artaud, J. F.; Basiuk, V.; Bizarro, Jao P. S.; Boulbe, C.; Dinklage, A.; Farina, D.; Faugeras, B.; Ferreira, J.; Figueiredo, A.; Huynh, Ph; Imbeaux, F.; Ivanova-Stanik, I.; Jonsson, T.; Klingshirn, H-J; Konz, C.; Kus, A.; Marushchenko, N. B.; Pereverzev, G.; Owsiak, M.; Poli, E.; Peysson, Y.; Reimer, R.; Signoret, J.; Sauter, O.; Stankiewicz, R.; Strand, P.; Voitsekhovitch, I.; Westerhof, E.; Zok, T.; Zwingmann, W.

查看更多内容