Development of a neural network technique for KSTAR Thomson scattering diagnostics

Abstract

Neural networks provide powerful approaches of dealing with nonlinear data and have been successfully applied to fusion plasma diagnostics and control systems. Controlling tokamak plasmas in real time is essential to measure the plasma parameters in situ. However, the χ² method traditionally used in Thomson scattering diagnostics hampers real-time measurement due to the complexity of the calculations involved. In this study, we applied a neural network approach to Thomson scattering diagnostics in order to calculate the electron temperature, comparing the results to those obtained with the χ² method. The best results were obtained for 10³ training cycles and eight nodes in the hidden layer. Our neural network approach shows good agreement with the χ² method and performs the calculation twenty times faster.