A Single-channel BSS Method Based on ICEEMDAN and FastICA and Its Application in EMI Analysis

Abstract

In the field of electromagnetic compatibility, electromagnetic interference (EMI) has always been a difficult problem for researchers. In order to achieve accurate separation of single-channel EMI signal, this paper proposes a one-stop method based on ICEEMDAN and FastICA. Firstly, the ICEEMDAN algorithm is used to extract several intrinsic mode functions (IMFs) from a single-channel mixture. Secondly, the multi-dimensional signals are reconstructed according to the IMFs and the original aliasing signal and separated by the FastICA algorithm. Finally, the feasibility of the proposed method is proved by experiments. Compared with the existing methods, it has better separation effect, which provides a reference for solving EMI problems.