经验模态分解的边界效应处理技术

经验模态分解是近年来发展起来的分析非线性、非平稳信号的新方法，已经应用于许多工程领域，并体现出了独特的优势，然而在经验模态分解过程中。当样条函数拟合信号上、下包络时却存在着棘手的端点问题。在论述经验模态分解原理的基础上，针对筛过程存在的边界效应，提出了将外推极值点与镜像延拓相结合的边界效应处理方法，进一步完善了经验模态分解理论；在仿真实验中，将所提的经验模态分解与基于镜像延拓、基于AR模型延拓等经验模态分解进行了性能对比，实验结果表明所提出的方法能够有效地抑制经验模态分解过程中出现的边界效应，具有通用性好、适应性强等优点。

End Effects Processing Technique of Empirical Mode Decomposition

Empirical mode decomposition(EMD) is a newly developed method used to analyze nonlinear and non-stationary signal.The method has been applied in many engineering domains and has represented unique advantages.However,EMD is an involved end issue during fitting the upper and lower envelops of the signal by spline function.Discussing the EMD theory and the end effects in the sifting process,a processing approach of combining extrapolating extrema with mirror extension is proposed.The EMD theory is improved perfectly.Their capabilities of the presented EMD,the EMD with mirror extension and the EMD with AR model extension will be compared in the simulation experiments.The experimental results demonstrate that the presented method can restrain the end effects effectively and has good universality and great adaptability.