一种新的变步长LMS算法及分析  

A new variable step size LMS algorithm and its analysis

作　　者：彭宏[1] 陈泓宇 PENG Hong;CHEN Hongyu(College of Information. Engineerings Zhejiang University of Technology, Hangzhou 310023？ China)

机构地区：[1]浙江工业大学信息工程学院,浙江杭州310023

出　　处：《浙江工业大学学报》2018年第1期45-50,82,共7页Journal of Zhejiang University of Technology

基　　金：国家自然科学基金资助项目(61372087)

摘　　要：LMS算法存在收敛速度和稳态误差上的矛盾,当步长因子过大,则收敛速度快,但误差变化较大;当步长因子过小,则收敛速度很慢但是误差稳定.因此,渐渐发展出了多种变步长LMS算法.通过建立步长和误差的一种非线性函数关系,提出了一种新的变步长LMS算法,并且对算法参数进行分析.该算法计算简便,计算量低,且在算法收敛初期能够得到较大的步长,而稳态时期能够得到较小的步长,且在稳态收敛阶段有较为缓慢的步长变化,克服了传统算法在低误差范围内的步长调整的缺陷.仿真结果与理论结果相一致,证明了该算法比已有算法拥有更好的收敛性能.There is a contradiction between convergence speed and steady-state error in the LMS algorithm. When the step size factor is too large,the convergence speed is fast,but the error change is larger. Otherwise,the convergence speed is slow but the error is stable. Therefore,a variety of variable step size LMS algorithms are developed gradually. A new variable step size LMS algorithm is proposed by establishing a nonlinear function relationship between step size and error. The algorithm is simple with low computational complexity. In the early convergence,the algorithm can get a larger step early; in the steady period,the algorithm can get a small step,and the step change is slow in steady-state convergence stage. It overcomes the shortcomings in the step size adjustment of traditional algorithm in the low error range. The simulation results are in good agreement with the theoretical results,which show that the proposed algorithm has better convergence performance than the existing algorithms.

关 键 词：自适应滤波 变步长自适应滤波算法 收敛性能 LMS算法 

分 类 号：TN911[电子电信—通信与信息系统]