Y可观典范型广义系统降阶Wiener状态估值器

Reduced-order Wiener state estimators for descriptor system with Y-observable canonical form

用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,提出了在Y可观典范型下广义系统的降阶Wiener状态估值器。它们可统一处理,滤波,平滑和预报问题且具有渐进稳定性。在计算上与非降阶的方法相比明显地减少了计算负担,同多项式方法相比避免了求解Diophantine方程。仿真例子说明了所提的理论和算法的有效性。

Using modern time series analysis method, based on the ARMA innovation model and white noise estimation theory. The reduced-order Wiener state estimators are presented for Descriptor system with Y-observable Canonical Form. They can handle the prediction, filtering, and smoothing problems in a unified framework and have a symptotic stability. Compared with non-reduced-order methods, the computational burden is obviously reduced, compared with the polynomial approach Diophantine equation is avoid. A simulation example shows its effectiveness.