Improvement of filamentary plasma identification via neural networks

Author

Formisano, Alessandro ; Martone, Raffaele

Author_Institution

Dipt. di Ingegneria dell´´Inf., Seconda Univ. di Napoli, Italy

Volume

37

Issue

5

fYear

2001

fDate

9/1/2001 12:00:00 AM

Firstpage

3727

Lastpage

3731

Abstract

The identification of plasma shape and position for control purposes in thermonuclear fusion devices is usually performed via external magnetic measurements. The result should be available in a few ms to guarantee an effective control action. Fast solution of such inverse problem can be achieved via Equivalent Currents (EC) method or Artificial Neural Networks (ANN). Anyway, in the case of EC, their location become critical during the dynamical evolution of the fusion event. ANN may be beneficial in optimally locating, in real time, the EC for various plasma configurations

Keywords

Tokamak devices; identification; inverse problems; neural nets; plasma diagnostics; Tokamak; artificial neural network; equivalent currents method; filamentary plasma identification; inverse problem; magnetic measurement; plasma control; plasma position; plasma shape; thermonuclear fusion device; Artificial neural networks; Fusion reactors; Magnetic field measurement; Magnetic flux; Magnetosphere; Neural networks; Plasma applications; Plasma devices; Plasma measurements; Plasma properties;

fLanguage

English

Journal_Title

Magnetics, IEEE Transactions on

Publisher

ieee

ISSN

0018-9464

Type

jour

DOI

10.1109/20.952700

Filename

952700