论文信息 - A Comparison between Soft Computing and Statistic Approaches to Identify Plasma Columns in Tokamak Reactors

A Comparison between Soft Computing and Statistic Approaches to Identify Plasma Columns in Tokamak Reactors

This paper is concerned with the application of novel techniques of data interpretation for reconstructing plasma shape in Tokamak reactors for nuclear fusion applications. In particular, Artificial Neural Networks have been taken into account to estimate the distance of the plasma boundary from the fist wall of the vacuum vessel in ITER configuration. In addition, a comparison with Principal Component Analysis and Functional Parameterization is presented. Finally, in order to reduce the computational complexity, non linear techniques for ranking sensors is exploited.

[1] Yinghua Lin,et al. Nonlinear system input structure identification: two stage fuzzy curves and surfaces , 1998, IEEE Trans. Syst. Man Cybern. Part A.

[2] N. L. Johnson,et al. Multivariate Analysis , 1958, Nature.

[3] Francesco Carlo Morabito,et al. Are Hybrid Fuzzy-Neural Systems Actually Useful in Plasma Engineering? , 1998 .

[4] Christopher M. Bishop,et al. Neural Network for Pattern Recognition , 1995 .

[5] Francesco Carlo Morabito,et al. A fuzzy-neural approach to real time plasma boundary reconstruction in tokamak reactors , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[6] Makoto Matsukawa,et al. Application of regression analysis to deriving measurement formulas for feedback control of plasma shape in JT-60 , 1992 .