Some techniques for fault detection involve the comparison of measured
process signals with independent estimates. The prediction of process
variables can be achieved either by physical or empirical modeling of
a plant subsystem. An automated procedure for generating empirical pr
ocess models is developed here. Independent prediction of critical sig
nals is required for consistency checking of instrument outputs, for t
heir degradation monitoring and for isolating common-mode failures. Th
e steady-state empirical models are developed using data from differen
t steady-state conditions. Signal anomaly is identified by comparing t
he error between the model-based prediction and the actual measurement
with a fuzzy function (curve) utilizing the signal tolerance as a thr
eshold. In the event a signal is declared as failed, the predicted est
imate is used as input to a control/safety system or for display to an
operator. Application of the methodology to signal validation using o
perational data from a commercial PWR and the EBR-II is presented.