分离随机偏差两段解耦Wiener滤波器

应用现代时间序列分析方法,基于ARMA 新息模型和Wiener 状态滤波器,对带随机偏差系统首次提出了分离随机偏差两段解耦Wiener 滤波器,形成了一种新的偏差处理技术. 同传统的两段Kalman 滤波器相比,具有如下优点: 1) 可统一处理滤波、平滑和预报问题; 2) 避免了Riccati 方程的计算; 3) 具有最优性和渐近稳定性; 4)实现了完全解耦; 5) 便于实时应用. 两个仿真例子说明了其有效性.
关键词: 随机偏差; 输入偏差; 传感器偏差; 分离偏差滤波器; 两段解耦Wiener 滤波器
　　Abstract : Using the modern time series analysis method , based on the ARMA innovation model and Wiener state filters , the separate stochastic bias two- stage decoupled Wiener filters are presented for the first time for systems with stochastic bias ,
which formed a new technique for treatment of bias . Compared to the classical two- stage Kalman filters ,they have the following advantages : 1) they can handle the filtering ,smoothing ,and prediction problems in a unified framework ; 2) the computation of
the Riccati equations is avoided ; 3) they have the optimality and asymptotic stability ; 4) the complete decouple is implemented ; 5) they are suitable for real time applications . Two simulation examples show their effectiveness .
Key words : stochastic bias ; input bias ; sensor bias ; separate bias filters ; two- stage decoupled Wiener filters