基于局部积分均值的经验模态分解改进算法

端点效应和模态混叠现象是经验模态分解算法应用中存在的主要问题。在介绍标准经验模态分解算法的基础上,阐述了基于局部积分均值经验模态分解算法的基本原理,提出自适应的端点局部积分均值拟合线的拟合方法。改进算法通过距离相关度函数在待分解信号内部寻找与端点处信号变化趋势相关度最高的一段波形,并用此段波形的局部积分均值拟合线来重新刻画端点处的局部积分均值拟合线,将修正后的局部积分均值拟合线应用于EMD算法筛选过程中。仿真实验结果表明,改进算法有效抑制了模态混叠和端点效应现象,提高了分解的精度和可靠性。

Improved Algorithm for Empirical Mode Decomposition Based on Local Integral Mean

The end effect and mode mixing is the main problem in the application of the empirical mode decomposition（EMD） method.The principles of standard EMD algorithm and the method of empirical mode decomposition based on local integral mean are introduced,and the advanced method of empirical mode decomposition based on local integral mean is presented.The method finds the best correlative sequence in the inner data and adopts the optimum sequence to proofread the fixing line near the ends of the data,and use the proofread fixing line into the sifting process of the algorithm.The simulation results show the method is effective in restraining end effect and mode mixing.