A. Ikonomopoulos et Thjj. Vanderhagen, A NOVEL SIGNAL VALIDATION METHOD APPLIED TO A STOCHASTIC-PROCESS, Annals of nuclear energy, 24(13), 1997, pp. 1057-1067
A novel methodology is presented for the purposes of modelling the pro
cess dynamics of neutron flux during induced boiling of the coolant in
a nuclear reactor environment. The proposed approach is based on the
utilisation of radial basis functions from the point of view of functi
on approximation, regularisation, and noisy interpolation. Data-driven
multiple-input/multiple-output radial basis function networks are sub
jected to faulty input signals and their signal validation capabilitie
s are studied. Networks based on radial basis functions employ trainin
g procedures that are substantially faster than the methods used in tr
aining multi-layer perception networks. Auto-associative schemes of th
e proposed technique are shown capable of identifying faulty process s
ignal measurements and provide the operator with an estimate of the ac
tual process value. The data utilised for the purposes of this project
are obtained from an experimental facility constructed to simulate bo
iling phenomena and positioned next to tie core of the IRI research re
actor. (C) 1997 Published by Elsevier Science Ltd.