Efficient Frequency Selective Surface Analysis via End-to-End Model-Based Learning

TL;DR

Comparisons with direct models, including deep neural networks (DNN) and radial basis function networks (RBFN), demonstrate the superiority of the model-based approach in terms of computational efficiency, model size, and generalization capability.

Abstract

This paper introduces an innovative end-to-end model-based deep learning approach for efficient electromagnetic analysis of high-dimensional frequency selective surfaces (FSS). Unlike traditional data-driven methods that require large datasets, this approach combines physical insights from equivalent circuit models with deep learning techniques to significantly reduce model complexity and enhance prediction accuracy. Compared to previously introduced model-based learning approaches, the proposed method is trained end-to-end from the physical structure of the FSS (geometric parameters) to its electromagnetic response (S-parameters). Additionally, an improvement in phase prediction accuracy through a modified loss function is presented. Comparisons with direct models, including deep neural networks (DNN) and radial basis function networks (RBFN), demonstrate the superiority of the model-based approach in terms of computational efficiency, model size, and generalization capability.

Figures (6)

• Figure 1: Block diagram of the proposed model-based approach. The response of an FSS is predicted from its geometry via a circuital equivalent whose values are obtained through an MLP.
• Figure 2: Comparison of predictions before and after end-to-end training for a specific example.
• Figure 3: Training curve showing the reduction in test error across the two training phases.
• Figure 4: Comparison of phase predictions before and after the adjustment of the cost function.
• Figure 5: Comparison of Prediction Quality Among Different Models