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.