EMD Sifting Based on Bandwidth

Abstract

Empirical-mode decomposition (EMD) provides a powerful tool for adaptive multiscale analysis of nonstationary signals. Aiming at the intrinsic mode function (IMF) criteria in sifting process and the scale mixing problem in EMD, this paper proposes a bandwidth criterion for IMF. By analyzing the simulated signal, it is confirmed that the IMFs obtained with the bandwidth criterion approximate the real components better and reflect the intrinsic information of the analyzed signal. Furthermore, the criterion based on bandwidth can weaken the scale mixing problem.