Abstract
The tokamak is currently the principal magnetic confinement system for controlled fusion research. In seeking to understand the physics of the high temperature plasma inside the tokamak, it is important to have detailed information on the spatial distribution of electron density. One technique for density measurement uses laser interferometry, which gives line-integral information along chords through the plasma. This requires an inversion procedure to extract spatially local density information. In this paper we make use of feedforward networks to extract local density profiles from the line-integral data obtained from the multichannel interferometer on the JET (Joint European Torus) tokamak. An important feature of our approach is the use of profile data from a second high resolution diagnostic system, called LIDAR, to train the network. The LIDAR system provides data at high spatial resolution but with a low repetition rate, and therefore has a complementary rôle to interferometry which operates at a high sampling rate but with much lower spatial resolution. Results show that the neural network is able to extract significantly more detailed profile information than the conventional Abel inversion method currently used on JET.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bishop CM, Cox PM, Haynes PS, Roach CM, Smith MEU, Todd TN, Trotman DL. A neural network approach to tokamak equilibrium control. Proceedings of the NCM'91 Conference: Applications of Neural Networks. London: Springer-Verlag, 1991
Allen L, Bishop CM. Neural network approach to energy confinement scaling in tokamaks. AEA Technology, UK, Report AEA-FUS-120, 1991 accepted for publication in plasma
Bishop CM, Roach CM. Fast curve fitting using neural networks. (submitted to Review of Scientific Instruments)
Braithwaite G, Gottardi N, Magayar G, O'Rourke J, Ryan J, Veron D. The JET Polari-interferometer.Review of Scientific Instruments 1989;60: 2825
Salzmann H, Bundgaard J, Gadd C, Gowers C, Hansen KB, Hirsch K, Nielsen P, Reed K, Schrodter C, Weisberg K. The LIDAR Thomson Scattering Diagnostic on JET.Review of Scientific Instruments 1989;59: 1451
Hadamard J. Lectures on the Cauchy Problem in Linear Partial Differential Equations. Yale University Press, 1923
Morozov VA. Methods for Solving Incorrectly Posed Problems. New York: Springer-Verlag, 1984
Tikhonov AN, Arsenin VY. Solution of Ill Posed Problems. New York: Wiley, 1977
Bishop CM. Curvature-Driven Smoothing in Backpropagation Neural Networks.Proceedings of the International Neural Network Conference, Paris, 1990, Vol 2, 749–752; Taylor JG and Manion CLT, editors, Theory and Applications of Neural Networks, London: Springer-Verlag, 1990, 139–148 (submitted toNeural Networks)
Bishop CM. Improving the Generalisation Properties of Radial Basis Function Neural Networks.Neural Computation 19912(4): 579–588
Christiansen JP. Integrated Analysis of Data from JET. J Computat Phys 1987;73: 85
Cottrell GW, Munro P, Zipser D. Learning Internal Representations from Gray-Scale Images.Proceedings of the 9th Annual Conference of the Cognitive Science Society, 1987, 461–473
Hornik K, Stinchcombe M, White H. Multilayer Feedforward Networks are Universal Approximators.Neural Networks 1989;2(5): 359–366
Baldi P, Hornik K. Neural Networks and Principal Component Analysis: Learning from Examples Without Local Minima.Neural Networks 1989;2: 53–58
Battiti R, Masulli F. BFGS Optimization for Faster and Automated Supervised Learning.Proceedings International Neural Network Conference, Paris, Vol 2, 1990, 757–760
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Bishop, C., Strachan, I., O'Rourke, J. et al. Reconstruction of tokamak density profiles using feedforward networks. Neural Comput & Applic 1, 4–16 (1993). https://doi.org/10.1007/BF01411370
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01411370