两传感器自校正信息融合Kalman滤波器

Two-sensor Self-tuning Information Fusion Kalman Filter

用现代时间序列分析方法,基于自回归滑动平均(ARMA)新息模型的在线辨识,对含有未知模型参数和噪声方差的两传感器线性离散随机系统,提出了自校正信息融合Kalman滤波器。它具有渐近最优性。一个仿真例子说明了其有效性。

Using the modem time series analysis method, based on the on-line identification of the autoregressive movingaverage(ARMA)innovation model,a self-tuning information fusion Kalman filter is presented for two-sensor linear discretestochastic systems of containing the unknown model parameters and noise variances, which has asymptotic optimality. A simu-lation example shows its effectiveness.