In this paper we present a novel tool which can be advantageously used within commonly used plasma shape identification procedures with the aim of carrying out a guided dimensionality reduction of the available pattern of measurements. The tool is referred to as Fuzzy Curve being related to Fuzzy Systems Theory. The use of fuzzy curves is compared to standard linear correlation analysis and to a ranking technique used within Neural Network approaches. The results of the study show that the fuzzy curves yield relevant insights about the nonlinear extremely simplified identification model. Whilke this model is not adequately accurate for copying with actual identification requirements, it can yet be used to have very fast information on the evolution of a discharge as well as to reduce the computational complexity of the training step required by standard identification procedures.

The Use of Fuzzy Curves for the Reconstruction of the Plasma Shape and the Selection of the Magnetic Sensors / Versaci, Mario; Morabito, Francesco Carlo. - 1:(1996), pp. 937-940. (Intervento presentato al convegno Symposium on Fusion Technology (SOFT96) tenutosi a Lisbona (Portugal) nel September 1996).

The Use of Fuzzy Curves for the Reconstruction of the Plasma Shape and the Selection of the Magnetic Sensors

VERSACI, Mario;MORABITO, Francesco Carlo
1996-01-01

Abstract

In this paper we present a novel tool which can be advantageously used within commonly used plasma shape identification procedures with the aim of carrying out a guided dimensionality reduction of the available pattern of measurements. The tool is referred to as Fuzzy Curve being related to Fuzzy Systems Theory. The use of fuzzy curves is compared to standard linear correlation analysis and to a ranking technique used within Neural Network approaches. The results of the study show that the fuzzy curves yield relevant insights about the nonlinear extremely simplified identification model. Whilke this model is not adequately accurate for copying with actual identification requirements, it can yet be used to have very fast information on the evolution of a discharge as well as to reduce the computational complexity of the training step required by standard identification procedures.
1996
0444827625
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12318/14174
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact