几种改善EMD端点效应方法的比较研究

Study on methods for improving EMD end effect

经验模态分解(EMD)的一个关键问题是改善端点效应。目前工程上已经提出了多种处理方法。在此对端点镜像方法、多项式拟合法、极值延拓法、平行延拓法和边界局部特征尺度延拓法等5种方法进行对比研究,利用分解信号与原信号的相似系数、分解信号与原信号的平均相对误差以及算法的运行时间作为端点处理方法的评价指标。仿真结果表明,极值延拓法是处理准周期信号的相对较好的EMD端点效应处理方法。

One of the most important problems in empirical mode decomposition（EMD）applications is the improvement of the end effect. Several methods for improving the end effect are proposed. Five common methods（mirror image method,polyno-mial fitting method,extremum extending method,parallel extending method and boundary local characteristic scale extending method） are investigated in this paper. For evaluating the end effect,the similarity coefficient and average relative error of de-composed signal and original signal,and the operation time are taken as evaluation criterions of the end processing methods. Simulation results indicate that the extremum extending method is the better option for quasi periodic signal.