一种新的自校正跟踪滤波器

A New Self- Tuning Tracking Filter

对于含未知模型参数和带未知噪声统计的一类雷达跟踪系统,本文用现代时间序列分析方法提出了一种新的自校正跟踪滤波器,其特点是基于 ARMA 新息模型的在线辨识,通过计算自校正输出预报器和自校正观测噪声滤波器,就可得到自校正跟踪滤波器。仿真例子说明了其有效性。

Using the modern time series analysis method, this paper presents a new self-tuning tracking filter for rader tracking system with unknown model parameter and unknown noise statistics. Its feature is that based on on-line identification of ARMA innovation model, a new self- tuning tracking is obtained by computing the self -tuning output predictor and observation noise filter. Simulation results show its effective-ness.