一类基于LMK准则的自适应格形梯度算法  

A NEW FAMILY OF ADAPTIVE GRADIENT LATTICE ALGORITHM BASED ON LMK CRITERION

作　　者：叶华[1] 吴伯修[1] 

机构地区：[1]东南大学无线电工程系

出　　处：《自动化学报》1991年第4期418-425,共8页Acta Automatica Sinica

摘　　要：本文将最小平均四次方、最小平均六次方等误差准则延拓到格形结构,提出了一类LMK自适应格形梯度算法,文中分析了这类算法的收敛性能,推导出滤波器系数均值、方差的近似表示法和自适应格形滤波器的输出均方误差,计算机模拟结果表明了这类算法的合理性.This paper extends the idea of minimizing error in the mean fourth power and mean sixth power, etc. to the lattice structure, and develops a family of LMK adaptive gradient lattice algorithms. The convergence behavior of the LMK gradient lattice algorithm is analyzed by deriving the approximate expressions for the mean and covariance functions of the adaptive lattice filter coefficients and the output mean square error of the adaptive lattice filter. A computer simulation has been performed to confirm the theoretical analysis results presented in this paper.

关 键 词：LMK 自适应 滤波 格形梯度算法 

分 类 号：TN713[电子电信—电路与系统]