Abstract
This paper discusses the training of deep neutral
networks (DNNs) for electromagnetic problems. The main concerns
include how to modify EM problems to take the advantage
of the deep learning techniques and how to tailor conventional
deep learning concepts with electromagnetic domain knowledge,
which has been overlooked by most existing DNN based EM
research. A 1 8 patch antenna array has been adopted as the
test vehicle for investigation, with the aim to use deep learning
for radiation pattern synthesis. It is analyzed via electromagnetic
simulation first to collect sufficient training data sets containing
different combinations of excitation signals and corresponding
radiation patterns. These data are then pre-processed and passed
to DNNs for training to imitate the mapping between excitation
signals and radiation patterns. With careful feature selection and
DNN architecture optimizations, two DNN models are obtained
eventually. One of them aims at forward radiation synthesis
in any certain excitation condition, and the other seeks out
backward excitation signals needed for a given radiation pattern,
and both achieved an accuracy over 80%. This paper may
provide enlightenment and reference in applying deep learning
to electromagnetic problems in terms of feature selection and
architecture modification.
networks (DNNs) for electromagnetic problems. The main concerns
include how to modify EM problems to take the advantage
of the deep learning techniques and how to tailor conventional
deep learning concepts with electromagnetic domain knowledge,
which has been overlooked by most existing DNN based EM
research. A 1 8 patch antenna array has been adopted as the
test vehicle for investigation, with the aim to use deep learning
for radiation pattern synthesis. It is analyzed via electromagnetic
simulation first to collect sufficient training data sets containing
different combinations of excitation signals and corresponding
radiation patterns. These data are then pre-processed and passed
to DNNs for training to imitate the mapping between excitation
signals and radiation patterns. With careful feature selection and
DNN architecture optimizations, two DNN models are obtained
eventually. One of them aims at forward radiation synthesis
in any certain excitation condition, and the other seeks out
backward excitation signals needed for a given radiation pattern,
and both achieved an accuracy over 80%. This paper may
provide enlightenment and reference in applying deep learning
to electromagnetic problems in terms of feature selection and
architecture modification.
Original language | English |
---|---|
Title of host publication | 2021 IEEE MTT-S International Wireless Symposium (IWS) |
Number of pages | 3 |
Publisher | IEEE |
Publication date | 2021 |
Article number | 9499638 |
ISBN (Print) | 978-1-6654-3528-4 |
ISBN (Electronic) | 978-1-6654-3527-7 |
DOIs | |
Publication status | Published - 2021 |
Event | 2021 IEEE MTT-S International Wireless Symposium (IWS) - Nanjing, China Duration: 23 May 2021 → 26 May 2021 |
Conference
Conference | 2021 IEEE MTT-S International Wireless Symposium (IWS) |
---|---|
Country/Territory | China |
City | Nanjing |
Period | 23/05/2021 → 26/05/2021 |
Keywords
- electromagnetic
- deep learning
- DNN
- excitation deduction
- radiation synthesis