Abstract
A deep learning-based method is developed to solve electromagnetic scattering problems, where the U-Net is combined with the conjugate gradient method (U-Net-CG). Numerical results show that the U-Net-CG outperforms the traditional CG in terms of computational speed under the comparable accuracy.
Original language | English |
---|---|
Title of host publication | 2021 International Applied Computational Electromagnetics Society Symposium, ACES-China 2021, Proceedings |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9781733509619 |
DOIs | |
Publication status | Published - 28 Jul 2021 |
Event | 4th International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2021 - Chengdu, China Duration: 28 Jul 2021 → 31 Jul 2021 |
Publication series
Name | 2021 International Applied Computational Electromagnetics Society Symposium, ACES-China 2021, Proceedings |
---|
Conference
Conference | 4th International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2021 |
---|---|
Country/Territory | China |
City | Chengdu |
Period | 28/07/21 → 31/07/21 |
Fingerprint
Dive into the research topics of 'U-Net Conjugate Gradient Solution of Electromagnetic Scattering from Dielectric Objects'. Together they form a unique fingerprint.Cite this
Xue, B. W., Wu, DI., Song, B. Y., Guo, R., Pan, X. M., Li, M. K., & Sheng, X. Q. (2021). U-Net Conjugate Gradient Solution of Electromagnetic Scattering from Dielectric Objects. In 2021 International Applied Computational Electromagnetics Society Symposium, ACES-China 2021, Proceedings (2021 International Applied Computational Electromagnetics Society Symposium, ACES-China 2021, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ACES-China52398.2021.9581406