Optimization of Double Ring Frequency Selective Surface for Sub 5G/X-Band Communications Using Supervised ML and DL Algorithms
SD. Sairam, D. Sriram Kumar, Sreenivasan Rathina Sabapathi, Saikiran Angali
Abstract
In this research article, a frequency selective surface (FSS) for double band stop response for sub 5G (6 GHz) communication, X-band (10 GHz) communication, and band pass response for 7.2 GHz for ultra-wideband applications with optimized dimensions will be predicted by machine learning (ML) and deep learning (DL) techniques. From the equivalent circuit model (ECM), the inductance and capacitance characteristics of various dimensions are calculated, and datasets are prepared. The shielding effectiveness, operating frequency, transmission loss <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(S_{21})$</tex-math></inline-formula> , and return loss <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(S_{11})$</tex-math></inline-formula> are taken as input data, and the structure dimension as output data for the ML and DL algorithms. Two ML and one DL algorithms are tried for getting a mean square error of 0.02–0.09 between the desired and observed results. The size of the FSS element is 0.6 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\lambda _{0}$</tex-math></inline-formula> × 0.6 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\lambda _{0}$</tex-math></inline-formula> for the shielding frequency. The thickness of the shielding structure is 1.6 mm, and the dielectric material used is RT Duroid 5880 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(\varepsilon _{r}=2.2)$</tex-math></inline-formula> . The extreme gradient boosting, adaptive boosting, and deep neural network algorithms are used for multiple input features and multiple output features from the datasets through advanced feature extraction and regression techniques. The results obtained from the static back propagation algorithm are endorsed using EM simulation and analyzed from the fabricated structure.