Physics-Informed Reinforcement Learning for Multi-Band Octagonal Fractal Frequency-Selective Surface Optimization

Diverse application scenarios demand frequency-selective surfaces (FSSs) with tailored center frequencies and bandwidths. However, their design traditionally relies on iterative full-wave simulations using tools such as the High-Frequency Structure Simulator (HFSS) and Computer Simulation Technology (CST), which are time-consuming and labor-intensive. To overcome these limitations, this work proposes an octagonal fractal frequency-selective surface (OF-FSS) composed of a square ring resonator and an octagonal fractal geometry, where the fractal configuration supports single-band and multi-band resonance. A physics-informed reinforcement learning (PIRL) algorithm is developed, enabling the RL agent to directly interact with CST and autonomously optimize key structural parameters. Using the proposed PIRL framework, the OF-FSS achieves both single-band and dual-band responses with desired frequency responses. Full-wave simulations validate that the integration of OF-FSS and PIRL provides an efficient and physically interpretable strategy for designing advanced multi-band FSSs.