Finite-horizon estimation of randomly occurring faults for discrete time-varying systems

This paper deals with the finite-horizon estimation of randomly occurring faults for a class of linear discrete time-varying systems. All the system parameters are time-varying and the failures are assumed to occur in a random way, and two sets of Bernoulli distributed white sequences are introduced to govern the failures probability. By using the completing squares method and stochastic analysis techniques, necessary and sufficient conditions for the existence of the finite-horizon Hoo fault estimator are derived, and then the time-varying fault estimator parameters are obtained by solving coupled backward recursive Riccati difference equations (RDEs). A simulation example is utilized to illustrate the usefulness of the proposed fault estimation method.