Inverse design of ultra-wideband transparent frequency selective surface absorbers based on evolutionary deep learning

Conventional frequency selective surface (FSS) absorbers design is time-consuming, involving multiple electromagnetic (EM) simulations for parameter scanning. A novel reverse design method is proposed utilizing evolutionary deep learning (EDL) based on an improved bacterial foraging optimization (IBFO) algorithm and a deep belief network. It establishes the relationship between the geometric structure and EM response. The combination of IBFO and EDL facilitates an efficient optimization for structural parameters, mitigating the 'one-to-many' problem and accelerating the design process. An optically transparent FSS absorber with an ultra-bandwidth of 8-18 GHz is designed to verify the proposed method's capability. The simulation and experimental results demonstrate that the absorber displays exceptional characteristics such as polarization insensitivity and robustness under a 45 & DEG; oblique incidence angle, making it a suitable candidate for radar stealth and photovoltaic solar energy applications. The proposed method can be applied to the design and optimization of various absorbers and complex EM devices.