Centroid-based sifting for empirical mode decomposition  

作　　者：Hong HONG Xin-long WANG Zhi-yong TAO Shuan-ping DU 

机构地区：[1]Key Laboratory of Modern Acoustics and Institute of Acoustics, Nanjing University, Nanjing 210093, China [2]State Key Laboratory of Ocean Acoustics, Hangzhou Applied Acoustics Research Institute, Hangzhou 310012, China

出　　处：《Journal of Zhejiang University-Science C(Computers and Electronics)》2011年第2期88-95,共8页浙江大学学报C辑（计算机与电子（英文版）

基　　金：Project supported by the National Natural Science Foundation of China (No. 10574070);the State Key Laboratory Foundation of China (No. 9140C240207060C24)

摘　　要：A novel sifting method based on the concept of the 'local centroids' of a signal is developed for empirical mode decomposition (EMD), with the aim of reducing the mode-mixing effect and decomposing those modes whose frequencies are within an octave. Instead of directly averaging the upper and lower envelopes, as suggested by the original EMD method, the proposed technique computes the local mean curve of a signal by interpolating a set of 'local centroids', which are integral averages over local segments between successive extrema of the signal. With the 'centroid'-based sifting, EMD is capable of separating intrinsic modes of oscillatory components with their frequency ratio ν even up to 0.8, thus greatly mitigating the effect of mode mixing and enhancing the frequency resolving power. Inspection is also made to show that the integral property of the 'centroid'-based sifting can make the decomposition more stable against noise interference.A novel sifting method based on the concept of the ＇local centroids＇ of a signal is developed for empirical mode decomposition （EMD）, with the aim of reducing the mode-mixing effect and decomposing those modes whose frequencies are within an octave. Instead of directly averaging the upper and lower envelopes, as suggested by the original EMD method, the proposed technique computes the local mean curve of a signal by interpolating a set of ＇local centroids＇, which are integral averages over local segments between successive extrema of the signal. With the ＇centroid＇-based sifting, EMD is capable of separating intrinsic modes of oscillatory components with their frequency ratio v even up to 0.8, thus greatly mitigating the effect of mode mixing and enhancing the frequency resolving power. Inspection is also made to show that the integral property of the ＇centroid＇-based sifting can make the decomposition more stable against noise interference.

关 键 词：SIFTING Empirical mode decomposition (EMD) Mode mixing effect Frequency resolution Local centroids Noise resistance 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]