LMP凸组合算法的稳态性能分析  

Steady-state performance analysis of the LMP convex combination algorithm

作　　者：张佳微 林斌[1] 张卓 ZHANG Jia-wei;LIN Bin;ZHANG Zhuo(Information Science and Technology College,Dalian Maritime University,Dalian 116026,China)

机构地区：[1]大连海事大学信息科学技术学院,辽宁大连116026

出　　处：《大连海事大学学报》2021年第4期122-128,共7页Journal of Dalian Maritime University

摘　　要：为进一步解决最小p阶均方算法(least mean p-power,LMP)收敛速度和稳态误差之间的矛盾,提高自适应算法的性能,提出对算法采用不同p值和不同步长进行凸组合(combination of least mean p-power,CLMP)的方案.该方案在高斯环境下将独立的大步长LMP_(1)滤波器和小步长LMP_(2)滤波器(p_(1)>p_(2))并联,利用分离假设条件进行稳态误差表达式的理论推导.仿真实验证明,在高斯平稳环境下组合滤波器稳态性能较单一滤波器表现得更好,为自适应滤波算法研究提供了一种新思路.In order to further solve the contradiction between the convergence speed and the steady-state error of the least mean p-power algorithm(LMP)and improve the performance of the adaptive algorithm,a convex combination scheme with different p values and variable-step size was proposed(combination of least mean p-power,CLMP)to effectively solve this problem.In this scheme,independent large step filter LMP_(1)and small step filter LMP_(2)(p_(1)>p_(2))are connected in parallel in Gaussian environment,and the theoretical derivation of steady-state error expression was carried out by using separation assumption.Simulation results show that the steady-state performance of combined filter is better than that of single filter in Gaussian stationary environment,which provides a new idea for the research of adaptive filtering algorithm.

关 键 词：自适应滤波器 LMP算法 凸组合 性能分析 能量守恒 

分 类 号：TN91[电子电信—通信与信息系统]