Robust fault diagnosis of stochastic systems with unknown disturbances

This paper studies the robust fault diagnosis of stochastic systems with unknown disturbances based on a full order observer. This observer can give disturbance decoupling minimum variance state estimation for time-varying systems with both noise and unknown disturbances. The existence condition and the design procedure are presented in the paper. The output estimation error with disturbance decoupling and minimum variance properties is used as a residual signal to diagnose faults. The developed method is applied to an illustrative example and simulation results show that the approach taken is able to detect faults reliably in the presence of both modelling errors and noise.