A unified approach to linear estimation for discrete-time systems. I. H/sub 2/ estimation

The paper addresses the H/sub 2/ estimation problem for linear discrete systems with current and delayed measurements. By re-organizing the measurements and introducing a re-organized innovation sequence, a unified solution to the H/sub 2/ filtering, prediction and fixed-lag smoothing is derived based on an innovation analysis method together with projection in Hilbert space. Our solution does not require system augmentation and the estimator is given in terms of a Riccati difference equation of the same order as that of the system state. The proposed results will find important applications in sensor and data fusion.