Improving Generative Inverse Design of Rectangular Patch Antennas with Test-Time Optimization

Beck LaBash, Shahriar Khushrushahi, Fabian Ruehle

Keywords: Antenna Design, Inverse Design, Test Time Optimization

TL;DR: We improve inverse design of rectangular patch antennas by combining generative modeling with test-time optimization for more accurate and practical antenna geometries.

Abstract:

We propose a two-stage deep learning framework for the inverse design of rectangular patch antennas. Our approach leverages generative modeling to learn a latent representation of antenna frequency response curves and conditions a subsequent generative model on these responses to produce feasible antenna geometries.
We further demonstrate that leveraging search and optimization techniques at test time improves the accuracy of the generated designs and enables consideration of auxiliary objectives such as manufacturability. Our approach generalizes naturally to different design criteria, and can be easily adapted to more complex geometric design spaces.

Submission Number: 10