摘要
针对MEMS水听器接收水下信号时混入的噪声,提出一种CEEMDAN和小波包的联合去噪算法.方法是利用CEEMDAN将含噪信号分解成一系列的IMF分量,IMF由高频到低频排列.由于高频噪声和低频干扰,所以要分别对高频和低频IMF进行处理.根据每层IMF的频谱分析,去掉前几层和后几层IMF分量形成一个带通滤波器,然后将剩余分量进行重构信号.最后,利用小波包对重构信号去噪得去噪信号.通过仿真实验和中北大学汾机实测实验验证了算法的有效性,并在去噪效果和性能指标上较单一CEEMDAN和小波包去噪有明显提升.
In this paper, the MEMS hydrophone signal is mixed with the noise of the un- derwater. A combined de noise algorithm of CEEMDAN and wavelet packet is proposed. The method is to use CEEMDAN to decompose the noisy signal into a series of IMF components, IMF is arranged by high frequency to low frequency. Due to high frequency noise and low frequency interference, it is to deal with the high frequency and low frequency IMF, respectively. According to the spectrum analysis of each layer of IMF, a band pass filter is formed by removing the IMF components from the first layers and the back layers, and then the remaining components are reconstructed. Finally, using wavelet packet to reconstruct the signal to get the denoising signal. The simulation experiments and Fenji experiments of North University of China verify the algorithm is effective, and the effect of denoising and performance indexes are better than the single CEEMDAN and wavelet packet denoising.
出处
《数学的实践与认识》
北大核心
2016年第13期139-147,共9页
Mathematics in Practice and Theory
基金
国家自然科学基金(61275120)
2016年山西省研究生教育创新项目
