基于广义最小均方的自适应递归滤波算法

Adaptive Recursive Filter Algorithm Using Generalized Least Mean Square Algorithm

本文提出了一种广义最小均方(GLMS)算法,分析了GLMS算法的性能,并根据GLMS算法,导出一种自适应递归滤波(ARF)算法。在推导中,ARF算法避开了超稳定定理,从而考虑自适应系统的严格正实条件和Popov不等式是不必要的。计算机模拟表明ARF算法具有很高的收敛速度。

A generalized least mean square(GLMS) algorithm is proposed, and its performance is discussed.An adaptive recursive filter algorithm is obtained by GLMS.In derivation for the adaptive algorithm, hy-perstable theory is not used, it's not necessary for considering strictly positive real condition and Popov inequation in the adaptive system. The computer simulation shows that there is a high convergent speed in the adaptive algorithm.