Variable step size decorrelation Volterra LMS algorithm

doi:10.3778/j.issn.1002-8331.2010.28.044

Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (28): 157-159.DOI: 10.3778/j.issn.1002-8331.2010.28.044

• 数据库、信号与信息处理 • Previous Articles Next Articles

Variable step size decorrelation Volterra LMS algorithm

ZHANG Xiu-mei¹，ZHAO Zhi-jin^1，2，SHANG Jun-na^1，2

1.Telecommunication School，Hangzhou Dianzi University，Hangzhou 310018，China
2.State Key Lab of Information Control Technology in Communication System of No.36 Research Institute，China Electronic Technology Corporation，Jiaxing，Zhejiang 314001，China

Received:2009-02-25 Revised:2009-04-13 Online:2010-10-01 Published:2010-10-01
Contact: ZHANG Xiu-mei

变步长解相关Volterra LMS算法

张秀梅¹，赵知劲^1，2，尚俊娜^1，2

1.杭州电子科技大学通信工程学院，杭州 310018
2.中国电子集团第36研究所通信系统信息控制技术国家级重点实验室，浙江嘉兴 314001

通讯作者: 张秀梅

Abstract

Abstract: For Volterra filter is nonlinear，the impact of nonlinear operations on the input signal results in that the date correlation matrix consists of higher order statistics and eigen values spread，so its convergence speed is very slow.This paper proposes a kind of algorithm of second order Volterra LMS algorithm using varying step size and decorrelation.Decorrelation can accelerate the convergence speed，and varying step size can improve steady state.The combination of both sides is able to improve the original algorithm’s convergence performance obviously.The simulation results have shown that the convergence speed of the improved algorithm is faster than that of VLMS algorithm，and the steady state of the improved algorithm is better than that of VLMS algorithm.

Key words: Volterra filter, variable step size algorithm, decorrelation, system identification

摘要： Volterra滤波器的非线性使输入向量自相关矩阵包含了输入信号的高阶统计量，导致矩阵特征值扩展很大，因此LMS算法收敛速度一般很慢。从降低输入信号的相关性出发，提出了一种变步长解相关Volterra NLMS算法。解相关能显著加快LMS算法的收敛速度，变步长能够改善算法的稳态性能，两者的有机结合，能明显改善算法性能。仿真结果表明，在不同输入信号相关性情况下，该算法有更好的收敛速度和稳态性能。

关键词: Volterra滤波器, 变步长, 解相关, 系统辨识

CLC Number:

TP391

ZHANG Xiu-mei¹，ZHAO Zhi-jin^1，2，SHANG Jun-na^1，2. Variable step size decorrelation Volterra LMS algorithm[J]. Computer Engineering and Applications, 2010, 46(28): 157-159.

张秀梅¹，赵知劲^1，2，尚俊娜^1，2. 变步长解相关Volterra LMS算法[J]. 计算机工程与应用, 2010, 46(28): 157-159.

[1]	GENG Hong, REN Daoxian, DU Peng. Dynamic parameter identification model of aircraft engine based on NARX neural network [J]. Computer Engineering and Applications, 2017, 53(12): 241-248.
[2]	LI Hui1，2, CHEN Can1. Multivariable processes identification and its application in evaporation process [J]. Computer Engineering and Applications, 2016, 52(12): 221-226.
[3]	LI Feixiang1, ZHAO Zhijin1，2, ZHAO Zhidong1. Variable step-size VLMP algorithm using divided-order gradient weighted average [J]. Computer Engineering and Applications, 2014, 50(4): 207-210.
[4]	HAN Zhong1，2, ZHAO Shengdun2, ZHANG Guicheng2，3, RUAN Weiping3, LI Jianping3, SHEN Hongli3. Automatic structural modeling method based on process manufacturing system identifications [J]. Computer Engineering and Applications, 2014, 50(1): 227-231.
[5]	YAN Pingping1, ZHAO Zhijin1，2, SHANG Junna1，2, ZHAO Zhidong1. Variable memory length LMP algorithm of second-order Volterra filter [J]. Computer Engineering and Applications, 2013, 49(3): 121-125.
[6]	WANG Haitao1, DUAN Zhemin1, SI Wei2. New modeling method and application based on functional series [J]. Computer Engineering and Applications, 2012, 48(35): 11-14.
[7]	LI Souju1，CHEN Yuzhen2，WANG Jizhe3，QU Fuzheng2. Model parameter estimation scheme in shield tunneling operation based on neural network [J]. Computer Engineering and Applications, 2011, 47(29): 239-241.
[8]	ZHAO Baojiang. Identification of T-S fuzzy models based on ant colony clustering algorithm [J]. Computer Engineering and Applications, 2011, 47(21): 153-156.
[9]	ZHAO Yu，LI Feng. Step size control in affine projection algorithm [J]. Computer Engineering and Applications, 2011, 47(11): 112-113.
[10]	ZHONG Lusheng1，2，FAN Xiaoping1，YANG Hui2，Qu Zhihua1，QI Yepeng2，YAN Zheng2. Maximum-likelihood identification of state-space bilinear systems [J]. Computer Engineering and Applications, 2011, 47(10): 110-112.
[11]	ZOU Ning1，XU Songtao1，REN Guolei2. Application and performance analysis of improved SVSLMS algorithm in system identification [J]. Computer Engineering and Applications, 2011, 47(10): 229-232.
[12]	LU Shuang，ZHU Jian-hong，PENG Li. Improved ART2 neural network algorithm for fault diagnosis [J]. Computer Engineering and Applications, 2010, 46(9): 212-214.
[13]	LI Song¹，ZHANG Jie²，HE Guo-guang². Study on transfer functions model of urban traffic flow at intersection [J]. Computer Engineering and Applications, 2010, 46(4): 236-239.
[14]	ZHONG Lu-sheng^1，2，FAN Xiao-ping¹，YANG Hui²，QU Zhi-hua¹. System identification of stochastic state-space systems by gradient optimization search [J]. Computer Engineering and Applications, 2010, 46(33): 21-24.
[15]	SHEN Jia-ning,SUN Jun,XU Wen-bo. System identification based on QPSO algorithm [J]. Computer Engineering and Applications, 2009, 45(9): 67-70.

Variable step size decorrelation Volterra LMS algorithm

变步长解相关Volterra LMS算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics