Abstract
Equivalent dipole moments are widely used for noise source reconstruction in radio frequency interference (RFI) study. The equivalent dipole sources are usually extracted from measured near-field pattern. This paper introduces a machine learning based method to extract the dipole moments. A convolutional neural network is trained to perform a multi-label classification to determine the type of dipole moments. The locations of the dipole moments are obtained from the global averaging pooling layer. Then the magnitude and phase of the dipoles can be calculated from least square (LSQ) optimization. The proposed method is tested on simulated near-field patterns. The comparison between reconstructed field pattern and original field pattern is given.
Recommended Citation
J. He et al., "Dipole Source Reconstruction by Convolutional Neural Networks," 2020 IEEE International Symposium on Electromagnetic Compatibility and Signal/Power Integrity, EMCSI 2020, pp. 231 - 235, article no. 9191529, Institute of Electrical and Electronics Engineers, Jul 2020.
The definitive version is available at https://doi.org/10.1109/EMCSI38923.2020.9191529
Department(s)
Electrical and Computer Engineering
Keywords and Phrases
convolutional neural network (CNN); dipole moment; machine learning; radio frequency interference (RFI)
International Standard Book Number (ISBN)
978-172817430-3
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
01 Jul 2020
Comments
National Science Foundation, Grant 1916535