Research output: Contribution to journalJournal articleResearchpeer-review


This paper tackles the generalized synthesis of antenna arrays using two-order deep learning. Existing deep learning assisted antenna synthesis approaches mainly rely on model training using electromagnetic (EM) simulation data, and hence feature limited generalization ability and the need for huge amount of EM simulations. The proposed two-order deep learning method uses the first-order model to learn the generic features of radiation patterns from the data set that can be efficiently calculated by applying conventional array factors, while the second-order model learns from EM simulations to capture the detailed pattern variations due to concrete coupling effects in case of certain array arrangement with different operating frequencies, radiation structures, and feeding schemes. Therefore the two-order DL model can predict the radiation patterns of a series of antenna arrays while reducing the needed amount of EM simulation data. An implementation was carried out on a series of patch antenna arrays to verify the feasibility and robustness of the proposed approach. The validation includes conditions when the array operating at arbitrary new frequencies, using modified radiation structures, and new feeding schemes. The results show that the proposed two-order model provides a prediction accuracy of about 84$\%$ for a series of 1 by 4 antenna arrays, clearly outperforming the existing regular one-order DL model which obtains an accuracy of around 65$\%$ with the same EM simulation data. The proposed method reveals a promising direction for applying deep learning in assisting the design and analysis of large scale and complex antenna systems for beyond 5G and 6G communications.
Original languageEnglish
JournalIEEE Transactions on Artificial Intelligence
Publication statusAccepted/In press - 2022


Dive into the research topics of 'Two_order_Deep_Learning_for_Generalized_Synthesis_of_Radiation_Patterns_for_Antenna_Arrays'. Together they form a unique fingerprint.

Cite this