一种基于奇异值的小波包改进算法  

Improved Wavelet Packet Algorithm Based on Singular Values

作　　者：陈桂明[1] 杨斌[1] 何庆飞 

机构地区：[1]第二炮兵工程大学装备管理工程系,西安710025

出　　处：《噪声与振动控制》2013年第1期59-63,67,共6页Noise and Vibration Control

摘　　要：为提高小波包降噪精度,提出一种小波包和奇异值结合的改进算法。首先选取合适的小波基函数进行小波包分解,对小波包系数进行奇异值分解,然后重构信号,最后仿真验证该算法的有效性。结果表明该算法可以有效地滤去噪声信号,同时可以保留信号中的高频成分,降噪效果优于小波包降噪。In order to raise the accuracy of wavelet packet de-noising, an improved algorithm combining the wavelet packet with singular values was put forward. Firstly, the method based on appropriate wavelet base functions was used for decomposition of the N-layer wavelet. Secondly, the singular value processing was carried out for the N-layer wavelet packet. Then the signal was reconstructed and restored. Finally the Matlab simulation was conducted to prove the effectiveness of the algorithm. The results show that the algorithm can effectively filter out the noise signal and can keep the high-frequency components in the signal, and the effect of signal noise reduction of the algorithm is better than that of the conventional wavelet packet.

关 键 词：振动与波 小波包 多分辨率分析 奇异值 降噪 

分 类 号：TH17[机械工程—机械制造及自动化]