Robust fault detection for a class of multirate linear systems

We develop a fault detection and isolation scheme for multirate systems with fast input sampling and slower output sampling rates. We design a separate observer for each set of simultaneous measurements operating at their sampling rate. We use an unknown input observer design to allow state estimation in the presence of disturbances and modeling errors. The observer estimates the system state and obtains a residual vector for fault detection. We provide necessary and sufficient conditions for the existence of the observer and the detection of the fault vector. An example is given to illustrate the new approach.