HyperHyperNetworks for the Design of Antenna Arrays

TL;DR

This paper introduces a deep learning framework using HyperHyperNetworks for designing antenna arrays and single antennas, achieving better performance and novel designs that meet specific spatial and radiation pattern requirements.

Contribution

The paper proposes a novel deep learning approach with hypernetworks within hypernetworks for antenna design, improving over existing methods in pattern accuracy and design novelty.

Findings

Designs are compliant with specified requirements.

Achieves better radiation pattern similarity than baselines.

Produces novel antenna and array configurations.

Abstract

We present deep learning methods for the design of arrays and single instances of small antennas. Each design instance is conditioned on a target radiation pattern and is required to conform to specific spatial dimensions and to include, as part of its metallic structure, a set of predetermined locations. The solution, in the case of a single antenna, is based on a composite neural network that combines a simulation network, a hypernetwork, and a refinement network. In the design of the antenna array, we add an additional design level and employ a hypernetwork within a hypernetwork. The learning objective is based on measuring the similarity of the obtained radiation pattern to the desired one. Our experiments demonstrate that our approach is able to design novel antennas and antenna arrays that are compliant with the design requirements, considerably better than the baseline methods. We compare the solutions obtained by our method to existing designs and demonstrate a high level of overlap. When designing the antenna array of a cellular phone, the obtained solution displays improved properties over the existing one.