On distributed discrete-time Kalman Filtering in large linear time-invariant systems

The paper is concerned with the problem of distributed Kalman Filtering for discrete-time linear large-scale systems with decentralized sensors. Using the standard approach to the centralized Kalman filtering, the problem of distributed filtering is introduced, given the incidence of additive recurrence to realize such problem. The obtained solutions support the residual signal generation using Kalman filter innovations in the model-based fault detection design. The results, offering structures for fault detection filter realization, are illustrated with a numerical example to note the effectiveness of the approach.