ROBUST FAULT DETECTION AND ISOLATION BASED ON THE KULLBACK DIVERGENCE

摘要

In this paper, a fully stochastic setting is proposed to design indicators aimed at detecting and isolating faults in a dynamical system. Modelling uncertainties, as well as process and measurement noise are accounted for. Two distinct sets of fault indicators are determined, one for fault detection, the other one for fault isolation. Each indicator is obtained by solving an optimization problem aimed at maximizing a statistical distance (namely the Kullback divergence) between the distribution of the indicator under different faulty and fault free working modes. The solution of the problem relies on statistical experiment design for the stochastic characterization of the system.