基于加权平均梯度的变步长LMS算法  

Variablestep-size LMS algorithm based on weighted average gradient

作　　者：高丽[1] 韩彦博[1] GAO Li;HAN Yan-bo(College of Electrical and Information Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China)

机构地区：[1]兰州交通大学电子与信息工程学院,甘肃兰州730070

出　　处：《吉林师范大学学报（自然科学版）》2018年第2期83-88,共6页Journal of Jilin Normal University:Natural Science Edition

基　　金：国家自然科学基金项目(61461024)

摘　　要：为了尽可能减少影响变步长LMS算法性能的因素,提出了基于加权平均梯度的变步长LMS算法.该算法的滤波器权系数在收敛的过程中自适应接近最优权矢量,算法利用平滑梯度矢量的欧式范数和瞬时误差控制步长更新,并从理论上分析了算法的稳态误差.与其他几种变步长LMS算法对比,该算法的收敛速度最快、稳态误差最小.In order to minimize the effect of influencing factors for variable step-size LMS,a gradient-based variable step size LMS algorithms is proposed.The filter weights could be close to the optimal weights in the convergence process by using L2-norm to control step-size.The steady-state maladjustment of the proposed algorithm is analyzed theoretically,results show that the maladjustment of the algorithm proposed in this paper is independent of filter order and input signal.Compared with other variable step-size LMS algorithms by simulation,results show that the rate of convergence is the fastest among these several algorithms,steady-state error is the smallest.

关 键 词：变步长 LMS算法 自适应均衡 

分 类 号：TN911.72[电子电信—通信与信息系统]