Inverse Design of Freely Partitioned Metasurface Antennas via Simulation-Driven Active Learning and Deep Neural Network
- 15 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 25 (1) , 219-223
Abstract
This letter presents a novel inverse design method for metasurface antennas (MSAs). Specifically, we propose a data generation strategy by employing a Voronoi-based partitioning algorithm, and construct a mapping model from performance parameters to structural topology using a deep neural network (DNN) trained with a simulation-driven active learning (SDAL) approach. Compared with passive learning, our method achieves a lower loss level after 990 training epochs. The trained SDAL-assisted DNN achieves training and validating accuracies of 95.59% and 90.84%, respectively. Using the trained DNN model, a wideband MSA and a dual-band MSA were inversely designed. Both simulation and experimental results prove that the generated structural topologies can fully achieve the desired design specifications. Therefore, our proposed inverse design approach enhances the design flexibility of MSAs and significantly reduces the time cost of design process, making it well-suited for a variety of design scenarios.Keywords
Funding Information
- National Natural Science Foundation of China (U2441232)
- Postdoctoral Fellowship Program of CPSF (GZB20250153)
This publication has 24 references indexed in Scilit:
- Deep-Learning-Assisted Design of Polarization Conversion Metasurface With On-Demand Frequency Response and Ultra-Broadband Electromagnetic Scattering ReductionIEEE Journal on Multiscale and Multiphysics Computational Techniques, 2024
- A Novel Triband Circularly Polarized Metasurface Antenna Based on Characteristic Mode AnalysisIEEE Antennas and Wireless Propagation Letters, 2024
- Time-Domain Scattering Parameters-Based Neural Network Inverse Model for Antenna DesignsIEEE Antennas and Wireless Propagation Letters, 2024
- Bandwidth Enhancement of Metasurface Antennas by Shifting and Reshaping High-Order ModeIEEE Antennas and Wireless Propagation Letters, 2022
- A Compact Wideband Low-Profile Metasurface Antenna Loaded With Patch-Via-Wall StructureIEEE Antennas and Wireless Propagation Letters, 2022
- Inverse Design of Metasurface Polarization Convertor with Controllable Bandwidth2021
- Low-Profile Broadband Metasurface Antenna Under Multimode ResonanceIEEE Antennas and Wireless Propagation Letters, 2021
- An Efficient Artificial Neural Network Model for Inverse Design of MetasurfacesIEEE Antennas and Wireless Propagation Letters, 2021
- Handling Vanishing Gradient Problem Using Artificial DerivativeIEEE Access, 2021
- Machine‐Learning Designs of Anisotropic Digital Coding MetasurfacesAdvanced Theory and Simulations, 2018