基于提升小波与粒子群相结合的混沌信号降噪

De-Noising for Chaotic Signal Using PSO and Lifting Wavelet Transform

提升小波变换用于混沌信号降噪具有良好的效果,阈值选取与混沌信号降噪后信号的畸变具有紧密联系。为了提高混沌信号中提升小波的自适应能力,降低降噪后信号的畸变率,提出了一种基于提升小波和粒子群相结合的混沌信号降噪方法。该方法在对提升小波变换后的细节部分进行阈值处理时,采用阈值自适应选择方法,并结合粒子群算法全局搜索最优阈值。通过对Colpitts模型进行仿真分析,与标准的软阈值降噪相比,能更好地对混沌信号降噪,并且降噪后信号失真度较小,具有很好的应用价值。

Lifting wavelet transform are efficient for chaotic signal noise reduction. Threshold estimation is closely related to chaotic signals de-noised by wavelet shrinkage methods. An adaptive wavelet threshold algorithm for de-noising of chaotic signals is put forward in order to improve the adaptive property of wavelet de-noising and to reduce distortion of de-noised signal. The wavelet de-nosing algorithm is based on an optimum and adaptive shrinkage scheme. A class of shrinkage functions with continuous derivatives and PSO is used for the adaptive shrinkage scheme. The de-noising result of simulative chaotic signals is presented. The chaotic signals de-noised by the adaptive wavelet threshold algorithm can remove the white noise effectively and have smaller distortion in waveform than the signals de-noised by using the standard soft shrinkage scheme. This method has good value in practical chaotic online monitoring.