广义系统Wiener 滤波和Kalman 滤波新方法*

New Approaches to Wiener Filtering and Kalman Filtering For Descriptor Systems

中文关键词  广义系统  广义Wiener状态滤波器  广义Kalman滤波器  现代时间序列分析方法

英文关键词  desriptor systems  descriptor Wiener state estimators  descriptor Kalman filter  modem tine series analysis method

中文摘要

      应用时域上的现代时间序列分析方法，基于ARMA新息模型和白噪声估计理论，提出了广义系统的Wiener状态估值器和稳态Kalman估值器.它们可统一处理最优滤波、平滑和预报问题.它们避免了求解Diophantine方程和Riccati方程，因而构成了Wiener滤波和Kalman滤波新方法.两个仿真例子说明新方法的有效性.

英文摘要

      Using the modem time series analysis method in the time domain, based on the autoegressive moving averge (ARMR)innovation model and whire noise estimaton theory, Wiener state estimators and steady-state Kalman estimators are presented for descriptor systems. They can handle the optimal filtering, smoothing and prediction problems in unified frame-works. They avoid the solution of the Diophantine equations and Riccati equations,and constitute new approaches to Wiener fil-tering and Kalman filtering. Two simulation examples show the usefulness of the new approaches.