Design of highly selective ultrawideband FSS based on deep learning for EMI shielding in 5G bands

Abstract In this paper, a frequency selective surface (FSS) for n41, n78, n257, n258, n260, and n261 bands electromagnetic interference (EMI) shielding is proposed using a deep learning method. The size of the FSS unit cell is 4.8 mm (0.071 λ 0 ), where λ 0 is the wavelength corresponding to the cutoff frequency of the −10 dB stopband where the n41 and n78 bands are located. This FSS exhibits three key characteristics. Firstly, it possesses ultrawideband capability, with a stopband frequency range of 23.922–40.023 GHz and a relative bandwidth reaching 50.4%. Secondly, it effectively shields against electromagnetic radiation in multiple 5 G bands, including n41, n78, n257, n258, n260, and n261. Thirdly, it demonstrates high selectivity, with a very narrow transition band of only 0.405 GHz between the passband and the stopband. To validate the designed FSS, a prototype of this structure was first fabricated for experimentation. The experimental results show that the measured S21 is highly consistent with the simulated S21. Secondly, the unit cell array of FSS is placed above the monopole antenna for co-simulation. It can be observed that after placing the FSS, the intensity of electromagnetic radiation propagating in space is significantly reduced by up to more than 90%. Therefore, the proposed FSS can be effectively applied for EMI shielding in 5 G bands.