Tokamak disruption alarm based on a neural network model of the high- beta limit

An artificial neural network, combining signals from a large number of plasma diagnostics, was used to estimate the high- beta disruption boundary in the DIII-D tokamak. It is shown that inclusion of many diagnostic measurements results in a much more accurate prediction of the disruption boundary than that provided by the traditional Troyon limit. A trained neural network constitutes a non-linear, non-parametric model of the disruption boundary. Through the analysis of the input-output sensitivities, the relative statistical significance of various diagnostic measurements (plasma parameters) for the determination of the disruption boundary is directly assessed and the number of diagnostics used by the neural network model is reduced to the necessary minimum. The neural network is trained to map the disruption boundary throughout most of the discharge. As a result, it can predict the high- beta disruption boundary on a time-scale of the order of 100 ms (much longer than the precursor growth time), which makes this approach ideally suitable for real time application in a disruption avoidance scheme. Owing to the relative simplicity of the required computations, the neural network is easily implemented in a real time system. A prototype of the neural network disruption alarm was installed within the DIII-D digital plasma control system, and its real time operation, with a typical time resolution of 10 ms, was demonstrated

[1]  Patrick K. Simpson,et al.  Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations , 1990 .

[2]  C. Bishop.  Neural networks and their applications , 1994 .

[3]  L. Lao,et al.  Improved confinement and stability in the DIII‐D tokamak obtained through modification of the current profile* , 1993 .

[4]  J. R. Ferron.  A high speed data acquisition and processing system for real time data analysis and control , 1992 .

[5]  Chris M. Bishop,et al.  Real-Time Control of a Tokamak Plasma Using Neural Networks , 1995, Neural Computation.

[6]  H. Nordman,et al.  Impurity effects on ηi mode stability and transport , 1992 .

[7]  Lloyd,et al.  Feedback stabilization of disruption precursors in a tokamak. , 1990, Physical review letters.

[8]  E. J. Strait,et al.  Stability of high beta tokamak plasmas , 1994 .

[9]  J. Manickam,et al.  β limit disruptions in the Tokamak Fusion Test Reactor , 1995 .

[10]  E. D. Fredrickson,et al.  High poloidal beta equilibria in the Tokamak Fusion Test Reactor limited by a natural inboard poloidal field null , 1991 .

[11]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[12]  F C Schuller,et al.  Disruptions in tokamaks , 1995 .

[13]  T. Todd.  The avoidance and control of tokamak disruptions , 1992 .

[14]  R. E. Hatcher,et al.  Control of plasma shape and performance of the PBX‐M tokamak experiment in high‐βt /high‐βp regimes , 1990 .

[15]  Dariusz Wróblewski.  Neural network evaluation of tokamak current profiles for real time control , 1997 .

[16]  J. T. Scoville,et al.  Locked modes in DIII-D and a method for prevention of the low density mode , 1991 .

[17]  J. Lister,et al.  Fast non-linear extraction of plasma equilibrium parameters using a neural network mapping , 1991 .

[18]  L. Lao,et al.  Reconstruction of current profile parameters and plasma shapes in tokamaks , 1985 .

[19]  Wendell Horton,et al.  Neural network prediction of some classes of tokamak disruptions , 1996 .

[20]  Y. Kamada,et al.  MHD behaviour in high- beta p and high- beta N discharges in JT-60U , 1995 .

[21]  A. Morris.  MHD instability control, disruptions, and error fields in tokamaks , 1992 .

[22]  Raffaele Martone,et al.  Identification of noncircular plasma equilibria using a neural network approach , 1994 .