经验模式分解算法的探讨和改进

Discussion and Improvement on Empirical Mode Decomposition Algorithm

对经验模式分解算法中的滤波停止条件和端点延拓问题进行了研究。在改进的EMD算法基础上,通过对本征模函数使用“新的滤波停止条件”,获得了更好的实验分解结果,同时,由于改进的EMD算法假定信号是无限长的,回避了B样条插值中节点延拓的固有问题,研究了有限长度信号的端点延拓问题,给出了端点延拓算法,从而弥补了已有方法的不足,使之更具实用性。实验表明,文中提出的算法是有效的。

The stopping criteria for sifting and boundary effect are studied for Empirical Mode Decomposition （EMD） algorithm. The decomposition is enhanced by combining with the alternative EMD approach and the new stopping criteria. The alternative EMD approach circumvents the problem of boundary continuation in B-Spline in- terpolation, where the signal is assumed to be infinitely long. A discussion for boundary continuation with finite length is presented and its algorithm is developed. This research compensates for the existing approach and can serve as an applicable method in practice. Experiments show that the proposed method is effective.