基于自适应小波阈值收缩算法的冲击消噪

冲击信号属于非平稳随机信号,在分析冲击信号之前信号消噪非常重要.基于Donoho提出的小波阈值收缩算法,提出了一种新的自适应于原信号的折中收缩函数.不同于经典阈值消噪算法,新算法克服了硬阈值算法造成的信号不连续的缺点,也弱化了软阈值算法中原信号小波系数与消噪后小波系数的固定偏差.应用结果表明,自适应小波阈值算法对冲击信号消噪比常用的软阈值或硬阈值算法具有更好的直观效果.

Denoising of Shock Signal Based on Self-Adaptive Wavelet Thresholding Algorithm

Shock signal belongs to non-stationary random signal,and the signal denoising is an important task before analyzing it.Based on wavelet thresholding denoising algorithm presented by Donoho,a new compromising threshold function that is self-adaptive to the signal is proposed.Unlike classical thresholding denoising algorithms,the new algorithm overcomes the discontinuity of the hard-thresholding algorithm and reduces the fixed deviation between the estimated wavelet coefficients and the decomposed wavelet coefficients of the soft thresholding algorithm.The results show that the improved algorithm gives better signal than the two classic algorithms.