Real-time Control of a Tokamak Plasma Using Neural Networks

Chris M. Bishop; Paul S.  Haynes; Mike E U  Smith; Tom N.  Todd; David L.  Trotman; Colin G.  Windsor

Real-time Control of a Tokamak Plasma Using Neural Networks

Chris M. Bishop, Paul S. Haynes, Mike E U Smith, Tom N. Todd, David L. Trotman, Colin G. Windsor

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents results from the first use of neural networks for the real-time feedback control of high temperature plasmas in a tokamak fusion experiment. The tokamak is currently the principal experimental device for research into the magnetic confinement approach to controlled fusion. In the tokamak, hydrogen plasmas, at temperatures of up to 100 Million K, are confined by strong magnetic fields. Accurate control of the position and shape of the plasma boundary requires real-time feedback control of the magnetic field structure on a time-scale of a few tens of microseconds. Software simulations have demonstrated that a neural network approach can give significantly better performance than the linear technique currently used on most tokamak experiments. The practical application of the neural network approach requires high-speed hardware, for which a fully parallel implementation of the multilayer perceptron, using a hybrid of digital and analogue technology, has been developed.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 7 (NIPS 1994)
Publisher	MIT Press
Pages	1007-1014
Number of pages	8
Volume	7
Publication status	Published - 1994

Access to Document

1005-real-time-control-of-a-tokamak-plasma-using-neural-networksFinal published version, 1.43 MB

http://papers.nips.cc/paper/1005-real-time-control-of-a-tokamak-plasma-using-neural-networks

Fingerprint Dive into the research topics of 'Real-time Control of a Tokamak Plasma Using Neural Networks'. Together they form a unique fingerprint.

Cite this

@inproceedings{26547877ab65460db4d710be10a3a160,

title = "Real-time Control of a Tokamak Plasma Using Neural Networks",

abstract = "This paper presents results from the first use of neural networks for the real-time feedback control of high temperature plasmas in a tokamak fusion experiment. The tokamak is currently the principal experimental device for research into the magnetic confinement approach to controlled fusion. In the tokamak, hydrogen plasmas, at temperatures of up to 100 Million K, are confined by strong magnetic fields. Accurate control of the position and shape of the plasma boundary requires real-time feedback control of the magnetic field structure on a time-scale of a few tens of microseconds. Software simulations have demonstrated that a neural network approach can give significantly better performance than the linear technique currently used on most tokamak experiments. The practical application of the neural network approach requires high-speed hardware, for which a fully parallel implementation of the multilayer perceptron, using a hybrid of digital and analogue technology, has been developed. ",

author = "Bishop, {Chris M.} and Haynes, {Paul S.} and Smith, {Mike E U} and Todd, {Tom N.} and Trotman, {David L.} and Windsor, {Colin G.}",

year = "1994",

language = "English",

volume = "7",

pages = "1007--1014",

booktitle = "Advances in Neural Information Processing Systems 7 (NIPS 1994)",

publisher = "MIT Press",

}

TY - GEN

T1 - Real-time Control of a Tokamak Plasma Using Neural Networks

AU - Bishop, Chris M.

AU - Haynes, Paul S.

AU - Smith, Mike E U

AU - Todd, Tom N.

AU - Trotman, David L.

AU - Windsor, Colin G.

PY - 1994

Y1 - 1994

N2 - This paper presents results from the first use of neural networks for the real-time feedback control of high temperature plasmas in a tokamak fusion experiment. The tokamak is currently the principal experimental device for research into the magnetic confinement approach to controlled fusion. In the tokamak, hydrogen plasmas, at temperatures of up to 100 Million K, are confined by strong magnetic fields. Accurate control of the position and shape of the plasma boundary requires real-time feedback control of the magnetic field structure on a time-scale of a few tens of microseconds. Software simulations have demonstrated that a neural network approach can give significantly better performance than the linear technique currently used on most tokamak experiments. The practical application of the neural network approach requires high-speed hardware, for which a fully parallel implementation of the multilayer perceptron, using a hybrid of digital and analogue technology, has been developed.

AB - This paper presents results from the first use of neural networks for the real-time feedback control of high temperature plasmas in a tokamak fusion experiment. The tokamak is currently the principal experimental device for research into the magnetic confinement approach to controlled fusion. In the tokamak, hydrogen plasmas, at temperatures of up to 100 Million K, are confined by strong magnetic fields. Accurate control of the position and shape of the plasma boundary requires real-time feedback control of the magnetic field structure on a time-scale of a few tens of microseconds. Software simulations have demonstrated that a neural network approach can give significantly better performance than the linear technique currently used on most tokamak experiments. The practical application of the neural network approach requires high-speed hardware, for which a fully parallel implementation of the multilayer perceptron, using a hybrid of digital and analogue technology, has been developed.

M3 - Conference contribution

VL - 7

SP - 1007

EP - 1014

BT - Advances in Neural Information Processing Systems 7 (NIPS 1994)

PB - MIT Press

ER -