Discrete Event System Diagnosis Using Parameter Estimation Methods

Abstract

This paper presents a new diagnosis method for discrete event systems represented by general timed Petri nets. Parameter estimation is used to determine estimates for the holding times of the Petri net's places. The residuals between these estimated values and given nominal values serve as fault indicators and can be used for fault isolation. It is shown that a method developed earlier for timed event graphs is a special case of this new estimation algorithm.