quotation:		[Copy]
		[Copy]

This Paper:Browse 2849 Download 2267
基于零均值特性的改进G-SVSLMS算法
路翠华,谢鑫,周红梅
0 Fontlarge +\|Default\|Small
(海军航空工程学院 7系,山东烟台 264001)

摘要:

为解决改进的基于Sigmoid函数变步长最小均方（GSVSLMS）算法步长更新公式易受噪声干扰的问题，根据高斯白噪声的零均值特性，对GSVSLMS算法进行改进，提出基于零均值特性的改进GSVSLMS算法，使算法的抗噪声干扰能力明显增强。理论分析和仿真结果表明：若两算法选取相同参数α、β，则基于零均值特性的改进GSVSLMS算法相对于GSVSLMS算法具有小的稳态误差；在保证算法收敛的条件下，基于零均值特性的改进G SVSLMS算法相对于GSVSLMS算法具有较快的收敛速度。

关键词: 信号处理噪声抑制 G SVSLMS算法零均值特性稳态误差收敛速度

DOI：

基金项目:

Improved G-SVSLMS algorithm based on zero mean characteristics

LU Cui-hua,XIE Xin,ZHOU Hong-mei

()

Abstract:

The GSVSLMS algorithm′s stepformula can be disturbed easily by nois e jamming. According to the characteristics that the mean of white Gaussian nois e is zero, improved GSVSLMS algorithm based on zero mean characteristics is pu t forward in order to improved GSVSLMS algorithm′s ability of antinoise. If two algorithms choose the same parameters α，β, improved GSVSLMS al gorithm will have less steadystate error than GSVSLMS algorithm. Under the c ondition that the two algorithms are convergent, the convergence rate of improve d GSVSLMS algorithm is bigger than that of GSVSLMS algorithm . Improved GSVSLMS algorithm′s performance is testified through theoretica l analysis and simulation.

Key words: signal processing noise suppression G SVSLMS algorithm characteristic of zero mean steady state error convergence rate