完全互补小波噪声辅助集总经验模态分解

A complete complementary wavelet ensemble empirical mode decomposition with adaptive noise

经验模态分解(EMD)是一种自适应非线性非平稳数据处理方法。噪声辅助的EMD方法能克服EMD方法在处理间歇信号时出现的"模态混叠"现象。在这些噪声辅助方法中,互补集总经验模态分解(CEEMD)和完全噪声辅助噪声集总经验模态分解(CEEMDAN)恢复了EMD分解的完整性。在现有分析方法上提出了完全互补小波噪声辅助集总经验模态分解(CCWEEMDAN)算法。该算法能用更小的集总数、更少的迭代次数和极小的计算消耗获得更好的光谱分离效果和数目较少的筛选模态。

Empirical mode decomposition (EMD) is a self-adaptive method and suitable to analysing the non-stationary and nonlinear signals. Noise-assisted versions have been proposed to alleviate the so-called “mode mixing” phenomenon, which may appear when an EMD algorithm is used to deal with a signal with intermittency. Among them, the complementary ensemble EMD (CEEMD) and complete ensemble EMD with adaptive noise (CEEMDAN) recover the completeness property of EMD. In this work a new algorithm named complete complementary wavelet ensemble empirical mode decomposition with adaptive noise(CCWEEMDAN) was presented based on those existing techniques, obtaining better spectral separation of the modes with fewer sifting iterations and less noise of components with small ensemble number and extremely low computational cost. © 2017, Editorial Office of Journal of Vibration and Shock. All right reserved.