REAL-TIME CONTROL OF A TOKAMAK PLASMA USING NEURAL NETWORKS

被引：21

作者：

BISHOP, CM ^{[1
]}

HAYNES, PS ^{[1
]}

SMITH, MEU ^{[1
]}

TODD, TN ^{[1
]}

TROTMAN, DL ^{[1
]}

机构：

[1] AEA TECHNOL,CULHAM LAB,ABINGDON OX14 3DB,OXON,ENGLAND

来源：

NEURAL COMPUTATION | 1995年 / 7卷 / 01期

关键词：

D O I：

10.1162/neco.1995.7.1.206

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we present results from the first use of neural networks for real-time control of the high-temperature plasma in a tokamak fusion experiment. The tokamak is currently the principal experimental device for research into the magnetic confinement approach to controlled fusion. In an effort to improve the energy confinement properties of the high-temperature plasma inside tokamaks, recent experiments have focused on the use of noncircular cross-sectional plasma shapes. However, the accurate generation of such plasmas represents a demanding problem involving simultaneous control of several parameters on a time scale as short as a few tens of microseconds. Application of neural networks to this problem requires fast hardware, for which we have developed a fully parallel custom implementation of a multilayer perceptron, based on a hybrid of digital and analogue techniques.

引用

页码：206 / 217

页数：12

共 50 条

[1] Real-time flow control using neural networks
Chan, HL
Rad, AB
[J]. ISA TRANSACTIONS, 2000, 39 (01) : 93 - 101
[2] Real-time software for the COMPASS tokamak plasma control
Valcarcel, D. F.
Duarte, A. S.
Neto, A.
Carvalho, I. S.
Carvalho, B. B.
Fernandes, H.
Sousa, J.
Sartori, F.
Janky, F.
Cahyna, P.
Hron, M.
Panek, R.
[J]. FUSION ENGINEERING AND DESIGN, 2010, 85 (3-4) : 470 - 473
[3] Plasma density control in real-time on the COMPASS tokamak
Janky, F.
Hron, M.
Havlicek, J.
Varavin, M.
Zacek, F.
Seidl, J.
Panek, R.
[J]. FUSION ENGINEERING AND DESIGN, 2015, 96-97 : 637 - 640
[4] Modified neural networks for rapid recovery of tokamak plasma parameters for real time control
Sengupta, A
Ranjan, P
[J]. REVIEW OF SCIENTIFIC INSTRUMENTS, 2002, 73 (07): : 2566 - 2577
[5] Neural networks for real-time control
Narendra, KS
[J]. PROCEEDINGS OF THE 36TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-5, 1997, : 1026 - 1031
[6] Real-Time Motor Control using Recurrent Neural Networks
Huh, Dongsung
Todorov, Emanuel
[J]. ADPRL: 2009 IEEE SYMPOSIUM ON ADAPTIVE DYNAMIC PROGRAMMING AND REINFORCEMENT LEARNING, 2009, : 42 - 49
[7] Plasma models for real-time control of advanced tokamak scenarios
Moreau, D.
Mazon, D.
Walker, M. L.
Ferron, J. R.
Burrell, K. H.
Flanagan, S. M.
Gohil, P.
Groebner, R. J.
Hyatt, A. W.
La Haye, R. J.
Lohr, J.
Turco, F.
Schuster, E.
Ou, Y.
Xu, C.
Takase, Y.
Sakamoto, Y.
Ide, S.
Suzuki, T.
[J]. NUCLEAR FUSION, 2011, 51 (06)
[8] Real-time plasma control tools for advanced tokamak operation
Varandas, C. A. F.
Sousa, J.
Rodrigues, A. P.
Carvalho, B. B.
Fernandes, H.
Batista, A. J.
Cruz, N.
Combo, A.
Pereira, R. C.
[J]. PLASMA AND FUSION SCIENCE, 2006, 875 : 385 - +
[9] Development of real-time plasma analysis and control algorithms for the TCV tokamak using SIMULINK
Felici, F.
Le, H. B.
Paley, J. I.
Duval, B. P.
Coda, S.
Moret, J. -M.
Bortolon, A.
Federspiel, L.
Goodman, T. P.
Hommen, G.
Karpushov, A.
Piras, F.
Pitzschke, A.
Romero, J.
Sevillano, G.
Sauter, O.
Vijvers, W.
[J]. FUSION ENGINEERING AND DESIGN, 2014, 89 (03) : 165 - 176
[10] Real-time control of manufacturing cells using dynamic neural networks
Rovithakis, GA
Gaganis, VI
Perrakis, SE
Christodoulou, MA
[J]. AUTOMATICA, 1999, 35 (01) : 139 - 149

← 1 2 3 4 5 →