Based on the Kalman filter, a unified and general white noise estimation theory is presented for systems with correlated noises, and Mendel's input white noise estimators are extended and developed. It includes the unified optimal input white noise estimators and measurement white noise estimators, optimal fixed-point, fixed-lag and fixed interval white noise smoothers, steady-state white noise estimators, and white noise innovation filters and Wiener filters. Their applications to state estimation and deconvolution are given. They include new Wiener state filters, pole-assignment Kalman smoothers, and Wiener deconvolution filters. Many simulation examples show effectiveness of the proposed results. |