Abstract
One of the most promising approaches to achieving fusion of the light elements, as a potential large-scale energy source for the next century, is based on the magnetic confinement of an ionised high temperature plasma. Most of the current research in magnetic confinement makes use of toroidal plasma configurations in experiments known as tokamaks. Theoretical results have predicted that the characteristics of a tokamak plasma can be made more favourable to fusion if the cross-section of the plasma is appropriately shaped. However, the accurate generation of such plasmas, and the real-time control of their position and shape, represents a demanding problem involving the simultaneous adjustment of the currents through several control coils on time scales as short as a few tens of microseconds. In this paper, we present results from the first use of neural networks for the control of the high temperature plasma in a tokamak fusion experiment. This application requires the use of 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. Our results demonstrate that the network is indeed capable of fast plasma control in accordance with the predictions of software simulations.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Lawson JD. Some criteria for a power producing thermonuclear reactor. Proc Phys Soc 1957; B70 (6).
Shafranov VD. On magnetohydrodynamical equilibrium configurations. Sov Phys JETP 1958; 8: (710).
Osborne TH, Fukumoto H, Hosogane N, et al. Plasma shape and position control on DIIID. Bull Am Phys Soc 1986; 31: 1502.
Wind H. Proceedings of the CERN Computing and Data Processing School, 1972, CERN-72-21, 53.
Braams BJ, Jilge W, Lackner K. Fast determination of plasma parameters through function parameterization. Nuclear Fusion 1986; 26: 699–708.
Gruber O, Gernhardt J, McCarthy P, Lackner K, Seidel U, Schneider W, Woyke W, Zehrfeld HP. Proceedings of the 17th Symposium on Fusion Technology, Rome, Italy, 1992; 2: 1042–1046.
Hofmann F, Tonetti G. Fast identification of plasma boundary and X-points in elongated tokamaks. Nuclear Fusion 1988; 28: 519.
Lister JB, Marmillod P, Moret JM. Control systems for the TCV tokamak. Report LRP 332/87, Centre de Researche en Physique des Plasmas, Laussanne, 1987.
Lister JB, Schnurrenberger H. Fast non-linear extraction of plasma parameters using a neural network mapping. Nuclear Fusion 1991; 31: 1291–1300.
Bishop CM, Cox P, Haynes PS, Roach CM, Smith MEU, Todd TN, Trotman DL. A neural network approach to tokamak equilibrium control. In Neural Network Applications (JG Taylor, ed.). Springer-Verlag, 1992; 114–128.
Lagin L, Bell R, Davis S, Eck T, Jardin S, Kessel C, Mcenerney J, Okabayashi M, Popyack J, Sauthoff N. Application of neural networks for real-time calculations of plasma equilibrium parameters for PBX-M. Proceedings of the 17th. Symposium on Fusion Technology, Rome, Italy, 1993; 2: 1057–1061.
Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks 1989; 2: 359–366.
Press WH, Flannery BP, Teukolsky SA, Vetterling WT. Numerical Recipes in C: The Art of Scientific Computing (2nd Ed.), Cambridge University Press, 1992.
Fukunaga K. Statistical Pattern Recognition (2nd Ed.). Academic Press, 1990.
Bishop CM, Haynes PS, Roach CM, Smith MEU, Todd TN, Trotman DL. Hardware implementation of a neural network for plasma position control in COMPASS-D. Proceedings of the 17th. Symposium on Fusion Technology, Rome, Italy, 1993; 2: 997–1001.
Bishop CM, Roach CM, von Hellerman M. Automatic analysis of JET charge exchange spectra using neural networks. Plasma Physics and Controlled Fusion 1993; 35: 765–773.
Bishop CM, Strachan IGD, O'Rourke J, Maddison G, Thomas PR. Reconstruction of tokamak density profiles using feedforward networks. Neural Computing and Applications 1993; 1: 4–16.
Bartlett DV, Bishop CM. Development of neural network techniques for the analysis of JET ECE data. Proceedings of the 8th International Workshop on ECE and ECRH, 1992.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Bishop, C.M., Haynes, P.S., Smith, M.E.U. et al. Fast feedback control of a high temperature fusion plasma. Neural Comput & Applic 2, 148–159 (1994). https://doi.org/10.1007/BF01415011
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01415011