基于奇异谱分析的经验模态分解去噪方法

发布时间：2018-01-09 21:46

本文关键词：基于奇异谱分析的经验模态分解去噪方法　出处：《计算机工程与科学》2017年05期 　论文类型：期刊论文

【摘要】：提出了一种基于奇异谱分析(SSA)的经验模态分解(EMD)去噪方法。该方法先对带噪信号进行EMD分解,得到若干个本征模态函数(IMF)。再通过SSA对每个IMF分量进行去噪处理:把第一个IMF分量作为高频噪声,并根据它计算出剩余IMF中所含的噪声能量,从而得到剩下的每个IMF中信号所占的能量比值。然后选择合适的窗口长度,对每个IMF进行SSA变换,根据IMF中信号所占的能量比值选择合适的奇异值分解(SVD)分量重构,得到去噪后的IMF。再将所有重构得到的IMF分量以及余项相加,得到最终去噪后的信号。经过实验,对比研究了该方法与小波软阈值、EMD软阈值和EMD滤波方法的去噪效果,结果表明该方法整体优于其它方法,是一种有效的信号去噪方法。
[Abstract]:An empirical mode decomposition (EMD) denoising method based on singular spectrum analysis (SSA) is proposed, which firstly decomposes the noisy signal by EMD. Some intrinsic mode functions are obtained and each IMF component is de-noised by SSA: the first IMF component is used as high frequency noise. According to it, the noise energy in the remaining IMF is calculated, and the energy ratio of the signal in each remaining IMF is obtained. Then, the appropriate window length is selected and each IMF is transformed by SSA. According to the energy ratio of the signal in the IMF, the appropriate singular value decomposition (SVD) component is selected, and the de-noised IMF component is obtained. Then all the reconstructed IMF components and the remainder are added together. Finally, the final de-noised signal is obtained. Through experiments, the denoising effect of this method is compared with that of wavelet soft threshold and EMD filtering. The results show that the proposed method is better than other methods on the whole. It is an effective signal denoising method.
【作者单位】：湖南大学电气与信息工程学院;
【基金】：中央国有资本经营预算项目(财企[2013]470号) 中央高校基本科研项目(2014-004) 国家自然科学基金(61172089) 湖南省科技计划项目(2014WK3001) 中国博士后科研基金(2014M562100) 湖南省科技计划重点项目(2015JC3053)
【分类号】：TN911.4
【正文快照】： 种对信号去噪的重要方法[1,2],但是对信号运用小1　引言波分析方法去噪时,要求事先给定小波基函数以及小波分解层数,而且选择不一样的小波基函数和分对信号进行去噪处理是数字信号处理中不可解层数会对小波去噪的效果有很大影响[3,4],这给避免的问题,小波分析具有良好的时频特

【相似文献】