 |
 |
 |
Instituto de Fisica Universidade de Sao Paulo, SP, Brazil
Institute for Fusion Studies - University of Texas, Austin, TX, USA
Y. J. Tajima
Department of Physics and Astronomy - Swarthmore College -
Swarthmore, PA, USA
Abstract. A feed-forward neural network is used to forecast major and minor
disruptions in TEXT tokamak discharges. Using the experimental data of soft
X-ray signals as input data, the neural net is trained with one disruptive
plasma discharge, while a different disruptive discharge is used for
validation. After proper training, the net works with the same set of weights,
it is then used to forecast disruptions in two other different plasma
discharges. It is observed that the neural net is capable of predicting the
onset of a disruption up to 3.12 ms in advance. From what we observe in the
predictive behavior of our network, speculations are made whether the
disruption triggering mechanism is associated with an increase in the m = 2
magnetic island, that disturbs the central part of the plasma column
afterwards, or the initial perturbation has first occurred in the central part
of the plasma column and then the m = 2 MHD mode is destabilized.
IAEA 2001
