基于奇异值的小波变换微弱信号消噪法  

Weak Signal De-noising Based on Singular Value Decomposition and Wavelet Transform

作　　者：周洪成[1,2] 李猛[2] 

机构地区：[1]金陵科技学院信息技术学院,江苏南京211169 [2]南京航空航天大学自动化学院,江苏南京210016

出　　处：《金陵科技学院学报》2012年第4期6-10,共5页Journal of Jinling Institute of Technology

基　　金：江苏省教育厅基金项目(11KJD510002);南京市科委基金项目(2011ZD011)

摘　　要：针对信噪比低、噪声非均匀分布的弱信号消噪效果不佳的问题,提出了基于有效奇异值分解和小波阈值消噪相结合的方法。通过构造相空间矩阵并对其进行奇异值分解(SVD),得到一系列正交子空间。因为信号和噪声对奇异值贡献不同,提出奇异值最小二乘误差判定法进行有效奇异值选择,利用子空间重构信号。仿真实验表明:本方法提取出的信号完整性更好,信噪比更高。In view of the deficiencies with low SNR（Signal to Noise Ratio）and non-uniform noise distribution, an algorithm based on Singular Value Decomposition （SVD） plus wavelet threshold de-noising is presented. The phase space matrix is constructed by SVD, thus a series of orthogonal subspaces are obtained. According to the different contribution of signal and noise for the singular value, a method of the least squares error is proposed for estimating the effective singular value. The signal is rebuilt in the subspaces by the wavelet threshold method. The results show that the extracted signals have better integrity and higher SNR.

关 键 词：微弱信号 奇异值分解 最小二乘误差 小波阈值消噪 

分 类 号：TN911.7[电子电信—通信与信息系统]