非高斯噪声环境中基于梯度范数的自适应滤波算法

冯子昂; 胡国平; 匡旭斌; 周豪

doi:10.15892/j.cnki.djzdxb.2017.03.024

2017 , Vol. 37 >Issue 3: 93 - 96

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2017.03.024

摘要

针对传统最小均方类算法在非高斯噪声中自适应滤波性能下降的问题,提出了一种基于梯度范数的变步长归一化最小平均p范数算法。算法将α稳定分布作为非高斯噪声分布模型,依靠梯度范数与均方权值偏差(MSD)的关系自适应调整步长,加快收敛速度的同时减小稳态误差,理论推导证明了算法的有效性。仿真结果表明,在非高斯噪声条件下,该算法具有更好的收敛性能和抗突变能力以及更小的稳定误差。

关键词： α稳定分布; 自适应滤波; 梯度范数; 归一化最小平均p范数算法

本文引用格式

冯子昂 , 胡国平 , 匡旭斌 , 周豪 . 非高斯噪声环境中基于梯度范数的自适应滤波算法[J]. 弹箭与制导学报, 2017 , 37(3) : 93 -96 . DOI: 10.15892/j.cnki.djzdxb.2017.03.024

Abstract

Conventional least mean square (LMS) algorithms meet declines of performance in non-Gaussian environment. A new variable step-size normalized least mean p-norm algorithm based on gradient-norm is proposed. The new algorithm assumes that the non-Gaussian noise satisfies alpha stable distribution, and the step size is adaptively adjusted by the relationship between mean square departure (MSD) and the gradient-norm. Through the relationship, the convergence rate is accelerated and the steady state error is decreased at the same time. The performance of the proposed algorithm is confirmed by theoretical derivation. Simulation results show that the proposed method has faster convergence rate, smaller steady state error and better performance of anti-saltation in non-Gaussian environment.

Key words： a-stable distribution; adaptive filtering; gradient norm; normalized least mean p-normalgorithm

[an error occurred while processing this directive]

参考文献

[1]	CHRYSOSTOMOS L Signal processing with Alpha-stable distributions and applications New York: John Wiley & Sons Inc., 1995.
[2]	TSIHRINTZIS GA, NIKIAS C L. Evaluation of fractional lower-order statistics-based detection algorithms on real radar sea-clutter data[J]. IEE Proceedings, Radar, Sonar and Navigation, 1997, 144(1):29-38.
[3]	郭莹. 稳定分布环境下的时延估计新方法研究[D]. 大连: 大连理工大学, 2009.
[4]	SHAO M, NIKIAS C L. Signal processing with fractional lower order moments: Stable processes and their application[J]. Proceedings of the IEEE, 1993, 81(7):986-1010.
[5]	ARIKAN O, BELGE M, CETIN A E,et al. Adaptive filtering approaches for non-gaussian stable processes[C]// IEEE International Conference on Acoustics, Speech, and Signal Processing. Detroit, MI, USA, 1995:1400-4403.
[6]	BELGE M, MILLER E L. A Sliding Window RLS-like Adaptive Algorithm for Filtering Alpha-stable Noise[J]. IEEE Signal Processing Letters, 2000, 7(4):86-89.
[7]	ANG W P, FARHANG-BOUROUJENY B. A New class of gradient adaptive step-size LMS algorithm[J]. IEEE Transactions on Signal Processing, 2001, 49(4):805-810.
[8]	高鹰, 谢胜利. 一种基于相关函数的LMS算法[J]. 数据采集与处理, 2004, 19(1):1-4.
[9]	SHIN H C, SAYED A H, SONG W J. Variable step-size NLMS and affine projection algorithms[J]. IEEE Signal Processing Letters, 2004, 11(2):132-435.
[10]	LU L, ZHAO HQ. Combination of two NLMP algorithm for non-linear system identification in Alpha-stable noise[C]// IEEE China Summit & Int Conf on Signal and Information Processing. Chengdu, 2015:1012-4016.
[11]	NAVIA-VAZQUEZ A, ARENAS-GARCIA J. Combination of recursive least P-norm algorithm for robust adaptive filtering in Alpha-stable noise[J]. IEEE Transactions on Signal Processing, 2012, 60(3):1478-4482.
[12]	LU L, ZHAO HQ. A Novel convex combination of LMS adaptive filter for system identification[C]// International Conference on Signal Processing (ICSP).[S. l.: s. n.], 2015:225-229.
[13]	张莉, 冯大政. 一种改进的自适应脉冲对消LMP算法[J]. 西安电子科技大学学报, 2003, 30(2):183-485.
[14]	康亚明, 曹保卫. Alpha稳定分布随机变量仿真及模型参数估计[J]. 电子设计工程, 2011, 19(11):19-22.
[15]	单志明. α稳定分布参数估计及自适应滤波算法研究[D]. 哈尔滨: 哈尔滨工程大学, 2012.
[16]	李宁, 张勇刚, 郝燕玲. 一种鲁棒性变步长 LMS 公式的稳态性能分析[J]. 系统仿真学报, 2008, 20(18):4978-4981.

Options

文章导航