Stacked Autoencoder for Wavelet-Based the EMI Signal analysis

One way to analyze and improve the electromagnetic compatibility (EMC) of an electronic system is to sample multiple signals and then locating the electromagnetic interference (EMI) sources. First, each signal is decomposed into sub-signals using wavelet transform in which contains potential interes...

Full description

Saved in:
Bibliographic Details
Published in2021 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) pp. 126 - 129
Main Authors Li, Hongyi, Yang, Yuan, Peng, Zhen, Zhao, Di
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2021
Subjects
Clustering algorithms
Electric potential
Electromagnetic interference
EMI
Error analysis
Feature extraction
Fréchet distance
Stacked Autoencoder
Wavelet
Wavelet analysis
Wavelet transforms
Online AccessGet full text

Cover

More Information
Summary:One way to analyze and improve the electromagnetic compatibility (EMC) of an electronic system is to sample multiple signals and then locating the electromagnetic interference (EMI) sources. First, each signal is decomposed into sub-signals using wavelet transform in which contains potential interesting EMI components. Then, the cluster algorithm is used to identify EMI sources. However, due to the inconsistency imposed by different sampling time and space, sampling signals belong to the same source may take on diverse patterns, thus deteriorating the clustering accuracy. This paper proposed a feature extraction method based on Stacked Autoencoder (SAE) in order to yield a robust signal representation. An additional robust feature based on Fréchet distance is also proposed. Experimental results demonstrate that the proposed method could significantly promote the clustering performance compared to existing methods.
DOI:10.1109/AIEA53260.2021.00034