Please wait a minute...
浙江大学学报(工学版)
J4  2012, Vol. 46 Issue (6): 1014-1020    DOI: 10.3785/j.issn.1008-973X.2012.06.009
无线电电子学、电信技术     
改进的变步长自适应滤波及Eckart加权抑噪算法
刘志坤, 刘忠, 付学志, 宁小玲
海军工程大学 电子工程学院,湖北 武汉 430033
Modified variable step-size adaptive filtering and
Eckart weighted denoising algorithm
LIU Zhi-kun, LIU Zhong, FU Xue-zhi, NING Xiao-ling
Electronics Engineering College, Naval University of Engineering, Wuhan 430033, China
 全文: PDF  HTML
摘要：

针对已有的变步长自适应滤波算法对噪声干扰敏感的问题,提出改进的变步长最小均方误差自适应算法,该算法对误差的自相关时间均值估计做遗忘加权补偿,并改步长因子固定范围约束为动态变化约束,一方面克服了单纯采用自相关时间均值估计调整步长所导致的步长因子快速衰减,获得了较快的收敛速度；另一方面相比基于Sigmoid函数的变步长算法,具有更平滑的步长变化和更低的稳态失调噪声.在改进算法中引入Eckart加权进一步抑制了自适应滤波器权系数伪峰,采用滑动窗遗忘加权降低了计算复杂度.将新算法及其Eckart加权应用于自适应时延估计仿真实验,结果表明：相比于已有的2种参数固定条件下的变步长自适应滤波算法,改进算法获得了更好的高斯噪声和突变噪声干扰下的时变时延跟踪性能.
Abstract:

The performance of the existing variable step-size least mean square （LMS） adaptive filtering algorithm is highly sensitive to the noise disturbance. In order to solve this problem, a modified variable step-size LMS-type algorithm was proposed. The modified algorithm compensates the time-averaged estimation of the autocorrelation of error with forgetting weight, and replaces the fixed step-size range restriction by dynamic change restriction. The modified algorithm overcomes the  fast attenuation of step-size and obtains faster convergence rate. In addition, comparing to another variable step-size algorithm based on Sigmoid function, the modified algorithm is provided with smoother step-size variation and lower steady-state offset noise. Moreover, Eckart weighted method is introduced into the algorithm to restrain fake peaks of adaptive filter’s coefficient vector, and the use of sliding forgettingweighted window reduces the  computational complexity. The results of the simulation on tracking time-varying delay indicated that, the modified algorithm and its Eckart weighted method achieved superior performance for cases of Gaussian noise and impulsive noise interference, comparing to the existing step-size LMS algorithm being of fixed parameters.
出版日期: 2012-07-24
:  TN 911.72  
基金资助:

国防预研基金资助项目.
通讯作者: 刘忠，男，教授.     E-mail: realzaza@sina.com
作者简介: 刘志坤（1984—），男，博士生，从事目标定位与跟踪研究.E-mail:bill1302lzk@sina.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

刘志坤, 刘忠, 付学志, 宁小玲. 改进的变步长自适应滤波及Eckart加权抑噪算法[J]. J4, 2012, 46(6): 1014-1020.

LIU Zhi-kun, LIU Zhong, FU Xue-zhi, NING Xiao-ling. Modified variable step-size adaptive filtering and
Eckart weighted denoising algorithm. J4, 2012, 46(6): 1014-1020.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2012.06.009    或    http://www.zjujournals.com/eng/CN/Y2012/V46/I6/1014

［1］ WIDROW B. Adaptive signal processing［M］. N J: PrenticeHall, Inc, 1985.
［2］ KWONG R H, JOHNSON E W. A variable step size LMS algorithm［J］.IEEE Trans on Signal Processing,1992,40(7): 1633-1642.
［3］ 覃景繁,欧阳景正.一种新的变步长自适应滤波算法［J］.数据采集与处理,1997,12(3): 171-174.
QIN Jingfan,OUYANG Jingzheng. A new variable step size adaptive filtering algorithm［J］. Journal of Data Acquisition& Processing, 1997, 12(3): 171-174.
［4］ 宋恒,林雪原,王红星,等.采用SRM准则的盲均衡器［J］.北京邮电大学学报,2008,31(4): 6-9.
SONG Heng,LIN Xueyuan,WANG Hongxing,et al. A blind equalizer based on SRM rule［J］. Journal of Beijing University of Posts and Telecommunications, 2008,31(4): 6-9.
［5］ 孙晖,朱善安.基于时延自相关预处理的 HilbertHuang变换解调［J］.浙江大学学报:工学版,2005,39(12): 1998-2001.
SUN Hui, ZHU Shanan. HilbertHuang transform demodulation based on delayed autocorrelation pretreatment［J］.Journal of Zhejiang University: Engineering Science, 2005,39(12): 1998-2001.
［6］ ABOULNASR T, MAYYAS K. A robust variable stepsize LMSType algorithm: analysis and simulation［J］.IEEE Trans on Signal Processing,1997,45(3): 631-639.
［7］ 高鹰,谢胜利.一种变步长LMS自适应滤波算法及分析［J］.电子学报,2001,29(8): 1094-1097.
GAO Ying, XIE Shengli. A variable step size LMS adaptive filtering algorithm and its analysis［J］.Acta Electronica Sinica,2001,29(8): 1094-1097.
［8］ 邓江波,侯新国,吴正国.基于箕舌线的变步长LMS自适应算法［J］.数据采集与处理,2004,19(3): 282-285.
DENG Jiangbo,HOU Xinguo,WU Zhengguo. Variable step adaptive filtering LMS algorithm based on tongue like curve［J］.Journal of Data Acquisition & Processing,2004,19(3): 282-285.
［9］ 张中华,张端金.一种新的变步长LMS自适应滤波算法及性能分析［J］.系统工程与电子技术,2009,31(9): 2238-2241.
ZHANG Zhonghua, ZHANG Duanjin. New variable step size LMS adaptive filtering algorithm and its performance analysis［J］.Systems Engineering and Electronics, 2009,31 (9): 2238-2241.
［10］ ZHANG Y G, CHAMBERS J A, WANG W W, et al. A new variable stepsize LMS algorithm with robustness to nonstationary noise［C］∥Proc Of International Conference on Acoustics, Speech and Signal Processing. Honolulu, Hawaii: \
[s.n.\], 2007: 1349-1352.
［11］ 孙恩昌,李于衡,张冬英,等.自适应变步长LMS滤波算法及分析［J］.系统仿真学报,2007,19(14): 3172-3175.
SUN Enchang, LI Yuheng, ZHANG Dongying, et al. Adaptive variablestep size LMS filtering algorithm and its analysis ［J］. Journal of System Simulation, 2007, 19(14): 3172-3175.
［12］ 张雯雯,司锡才,柴娟芳,等.一种新的变步长LMS自适应谱线增强算法［J］.系统工程与电子技术,2009,31(1): 33-35.
ZHANG Wenwen,SI Xicai,CHAI Juanfang,et al. New variable step size LMS adaptive spectralline enhancement algorithm［J］.Systems Engineering and Electronics,2009,31(1): 33-35.
［13］ 曾召华,刘贵忠,赵建平.LMS和归一化LMS算法收敛门限与步长的确定［J］.电子与信息学报,2003,11(25): 1469-1474.
ZENG Zhaohua, LIU Guizhong, ZHAO Jianping. Determining of convergent threshold and stepsize for LMS and normalized LMS algorithm［J］.Journal of Electronics and Information Technology,2003,11(25): 1469-1474.
［14］ 王宏禹,邱天爽.自适应噪声抵消与时间延迟估计［M］.大连:大连理工大学出版社,1999: 36-47.
[1] 金文光, 张正宇, 唐少华. 2FSK信号DSTFT解调算法中的同步新方法[J]. J4, 2011, 45(6): 1027-1031.
[2] 张少蔚, 徐东, 袁博, 赖晓平. 复数FIR滤波器椭圆误差约束最小二乘设计[J]. J4, 2010, 44(7): 1338-1342.