小波阈值降噪算法中最优分解层数的自适应确定及仿真

Adaptive selection and simulation of optimal decomposition level in threshold de-noising algorithm based on wavelet transform

小波阈值降噪算法是一种有效的从测试信号中去除噪声的方法。通过对有用信号和噪声信号在小波空间上传播特性的不同进行分析,提出了一种基于小波去相关白噪声检验的最优分解层数自适应确定算法。该算法可以根据含噪声信号的特点和信噪比,自适应的选择小波变换的最优分解层数以达到最优的降噪效果。最后,在MATLAB环境下进行了仿真实验,并进行了工程应用。仿真实验和工程应用结果表明,该方法可以有效的确定合理分解层数得到最优的信噪比。

Threshold de-noising based on wavelet transform is an efficient method to reduce noise from test signal. Through analyzing the propagation characteristic of signal and noise in wavelet domain, a new method to determine the optimal decomposition level based on wavelet de-correlation white noise verification is proposed. The algorithm can determine the optimal decomposition level adaptively according to the feature and SNR of the signal. Simulation results under MATLAB environment and engineering application prove that the method can determine the decomposition level effectively and reach best SNR.