A neural network approach for the detection of the locking position in RFX

Citation
O. Barana et al., A neural network approach for the detection of the locking position in RFX, FUSION ENG, 55(1), 2001, pp. 9-20
Citations number
29
Categorie Soggetti
Nuclear Emgineering
Journal title
FUSION ENGINEERING AND DESIGN
ISSN journal
09203796 → ACNP
Volume
55
Issue
1
Year of publication
2001
Pages
9 - 20
Database
ISI
SICI code
0920-3796(200105)55:1<9:ANNAFT>2.0.ZU;2-#
Abstract
In the RFX (reversed field experiment), one of the most important reversed field pinch (RFP) devices in the fusion community, wall locked modes have a lways been present. Recently, a new technique has demonstrated the possibil ity of inducing a continuous rotation of the modes with respect to the wall . The non-linear coupling of the m = 0 and m = 1 modes has been used to dec ouple the modes themselves, and the mode rotation has been induced by means of a pre-programmed waveform of a toroidal magnetic field rotating ripple. Consequently, a feedback system for detecting the locked mode position alo ng the toroidal co-ordinate and able to create a continuous rotation with v ariable speed has been envisaged. Neural networks (NNs) represent a promisi ng approach for rapid detection of the locked mode angular position in such a system, and in this paper the performances of different NNs trained to i dentify the locked mode position are compared and discussed. In particular, their robustness to noise is analyzed, and it is shown that NNs provide re liable results, sometimes better than those computed with fourier analysis. (C) 2001 Elsevier Science B.V. All rights reserved.