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 particolar Artificial Neural Networks have been taken into account to estimate the distance of the plasma boundary from the first wall of the vacuum vessel in the ITER configuration. In addition, a comparison with Principal Component Analysis and Functional Parametrization is presented. Finally, in order to reduce the computational complexity, non linear techniques for ranking sensors is exploited
A comparison between soft computing and statistic approaches to identify plasma columns in tokamak reactors / Calcagno, S; Greco, A; Morabito, F. C.; Versaci, Mario. - (2006), pp. 1716182.835-1716182.842. (Intervento presentato al convegno International Joint Conference on Neural Networks 2006, IJCNN '06 tenutosi a Vancouver, Canada nel July, 2016).
A comparison between soft computing and statistic approaches to identify plasma columns in tokamak reactors
Calcagno S;Morabito F. C.;VERSACI Mario
2006-01-01
Abstract
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 particolar Artificial Neural Networks have been taken into account to estimate the distance of the plasma boundary from the first wall of the vacuum vessel in the ITER configuration. In addition, a comparison with Principal Component Analysis and Functional Parametrization is presented. Finally, in order to reduce the computational complexity, non linear techniques for ranking sensors is exploitedI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
