基于扩展贝叶斯滤波的鲁棒波束成形

Robust Beamforming Based on Extended Bayesian Filter

为提高信号源波达方向存在估计误差或不稳定时的波束成形器性能,提出了基于扩展贝叶斯滤波的鲁棒波束成形算法。将期望信号波达方向看成一组由若干离散样点组成的随机变量,对这些样点的后验概率进行估计并对后验概率低于门限值的样点进行重采样,在样点数有限的情况下获取期望信号附近样点的优化分布。通过对各样点最小方差无畸变响应(MVDR)权值的加权处理得到了优化的波束成形器权值。仿真结果表明,与典型的基于贝叶斯估计的鲁棒波束成形算法相比,文中算法能进一步提高波束成形器的鲁棒性。

To improve the performance of beamformer while there is error or uncertainty in source direction of arrival （ DOA）, robust beamforming based on extended Bayesian （E-Bayesian） filter is proposed. DOA of desired signal is regarded as a set of random variable composed by several samples. The posteriori probability of these samples is estimated and they are resampled when some posteriori probability is under the threshold value. Thus, the optimized distribution is obtained under limited number of samples. The optimized beamformer is the weighted sum of minimum variance distortionless response （MVDR） pointed at these samples. Computer simulations, compared with the typical adaptive beamforming algorithm based on Bayesian, show that the algorithm based on E - Bayesian filter improves the robustness of the beamformer more.