Physics-Informed Generative Adversarial Network for Synthesis of Nonuniform Antenna Arrays with Mutual Coupling
Li Zhang, Yiping Liu, Jie Chen, Yanshuo Shen · 2026
Read Physics-Informed Generative Adversarial Network for Synthesis of Nonuniform Antenna Arrays with Mutual Coupling by Li Zhang, Yiping Liu, Jie Chen, Yanshuo Shen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13414038.txt.
Description
Li Zhang and co-authors teach a generative network the physics of antenna arrays in 2026 so it can design unevenly spaced arrays that account for elements interfering with each other. Nonuniform arrays focus beams with fewer elements, yet mutual coupling makes design a thorny search usually run by slow full-wave simulation. Their physics-informed GAN generates layouts and excitations, judges them against target patterns, and swaps the simulator for a fast learned stand-in for each element's behaviour.
Trials on a sixteen-element line and a three-hundred-element plane reached lower peak sidelobes than the comparison designs reported. A built sixteen-element prototype measured close to simulation, confirming the pipeline works off the page. The authors pitch the approach for next-generation wireless and radar hardware design.
Catalog record
| CREATOR | Li Zhang, Yiping Liu, Jie Chen, Yanshuo Shen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29004 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |