快速次优固定区间白噪声平滑器

Fast Suboptimal Fixed-interval White Noise Smoother

应用现代时间序列分析方法,基于ARMA新息模型,用多项式矩阵的截尾方法提出了带相关噪声系统的统一的快速次优固定区间白噪声平滑器。它们可明显减小计算负担,且可用新息滤波器和Wiener滤波器表示。给出了截尾误差公式及截尾指数选择公式。一个Bemoulli-Gaussian白噪声的仿真例子说明其有效性。

Using the modern time series analysis method, based on the autoregressive moving average (ARMA) innovationmodel, the unified fast suboptimal fixed-interval white noise smoothers is presented by the truncation of polynomial matrices forsystems with correlated noises. They can obviously reduce the computational burden, and can be expresses as the innovationfilter and Wiener filter. The formulas of truncated error and truncated index are given. A simulation example for Bemoulli-Gaussian white noise shows its effectiveness.