EMPIRICAL PROCESS MODELING TECHNIQUE FOR SIGNAL VALIDATION

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.