A Surrogate Model for the Forward Design of Multi-layered Metasurface-based Radar Absorbing Structures

2025-05-14

AI Summary

Full-wave electromagnetic simulation of multilayer metasurface radar-absorbing structures (RAS) is computationally expensive and time-consuming, hindering rapid design optimization. Method: This work proposes a high-fidelity convolutional neural network (CNN) surrogate model tailored for broadband reflection response prediction. It establishes an end-to-end mapping from geometric parameters of multilayer unit cells directly to full-spectrum reflectance curves; employs a convolutional architecture to enhance spatial feature extraction; and incorporates Huber loss to improve robustness against outlier responses. Contribution/Results: After 1,000 training epochs, the model achieves 99.9% cosine similarity and 0.001 mean squared error versus ground-truth simulations. Experimental and numerical validation confirms prediction accuracy comparable to full-wave simulation, while inference time is reduced by over two orders of magnitude. The model balances high accuracy, strong generalizability, and physical interpretability, establishing a new paradigm for efficient forward design of metasurface RAS.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Metasurface-based radar absorbing structures (RAS) are highly preferred for applications like stealth technology, electromagnetic (EM) shielding, etc. due to their capability to achieve frequency selective absorption characteristics with minimal thickness and reduced weight penalty. However, the conventional approach for the EM design and optimization of these structures relies on forward simulations, using full wave simulation tools, to predict the electromagnetic (EM) response of candidate meta atoms. This process is computationally intensive, extremely time consuming and requires exploration of large design spaces. To overcome this challenge, we propose a surrogate model that significantly accelerates the prediction of EM responses of multi-layered metasurface-based RAS. A convolutional neural network (CNN) based architecture with Huber loss function has been employed to estimate the reflection characteristics of the RAS model. The proposed model achieved a cosine similarity of 99.9% and a mean square error of 0.001 within 1000 epochs of training. The efficiency of the model has been established via full wave simulations as well as experiment where it demonstrated significant reduction in computational time while maintaining high predictive accuracy.

Problem

• Accelerating EM response prediction for metasurface RAS
• Reducing computational time in RAS design optimization
• Improving efficiency of multi-layered metasurface simulations

Innovation

• Surrogate model accelerates EM response prediction
• CNN with Huber loss estimates reflection characteristics
• Achieves high accuracy with reduced computational time