论文信息 - An Angularly Stable Triple-band Reflective Polarizing Surface Using a Generative Adversarial Network

An Angularly Stable Triple-band Reflective Polarizing Surface Using a Generative Adversarial Network

Linear-to-circular polarization converters with wide- and multi-band capabilities can simplify antenna systems where circular polarization is desired. Multi-band solutions are attractive in satellite communication systems, which commonly have the additional requirement that the sense of polarization is reversed between bands. However, the design of these structures using conventional methods is ad hoc and relies heavily on empirical methods. Here, we employ a data-driven approach integrated with a generative adversarial network to explore the space of polarizer unit cells thoroughly. A triple-band reflective surface with stable performance over incident angles up to and including 30° is proposed.

N. Fonseca | S. Hum | G. Goussetis | Parinaz Naseri

[1] N. Fonseca,et al. Angularly Stable Linear-to-Circular Polarizing Reflectors for Multiple Beam Antennas , 2021, IEEE Transactions on Antennas and Propagation.

[2] Ian Goodfellow,et al. Generative adversarial networks , 2020, Commun. ACM.

[3] Parinaz Naseri,et al. A Generative Machine Learning-Based Approach for Inverse Design of Multilayer Metasurfaces , 2020, IEEE Transactions on Antennas and Propagation.

[4] Kumar Vijay Mishra,et al. Multi-Discriminator Distributed Generative Model for Multi-Layer RF Metasurface Discovery , 2019, 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[5] Jonathan A. Fan,et al. Simulator-based training of generative neural networks for the inverse design of metasurfaces , 2019, Nanophotonics.

[6] Nelson J. G. Fonseca,et al. High-Performance Electrically Thin Dual-Band Polarizing Reflective Surface for Broadband Satellite Applications , 2016, IEEE Transactions on Antennas and Propagation.