Inverse Machine Learning Approach for Metasurface based Radar Absorbing Structure Design for Aerospace Applications 2024-26-0480

Metasurfaces, comprised of sub-wavelength structures, possess remarkable electromagnetic wave manipulation capabilities. Their application as radar absorbers has gained widespread recognition, particularly in modern stealth technology, where their role is to minimize the radar cross-section (RCS) of military assets. Conventional radar absorber design are tedious by their time-consuming, computationally intensive, iterative nature, and demand a high level of expertise. In contrast, the emergence of deep learning-based metasurface design for RCS reduction represents a rapidly evolving field. This approach offers automated and computationally efficient means to generate radar absorber designs. However, the practical implementation of radar-absorbing structures on complex aircraft bodies presents significant challenges. In this article, a straightforward inverse design methodology for a single-layer, broadband microwave absorber, primarily based on geometry and absorption characteristics is presented. The proposed design is based on an in-depth understanding of the behaviour of an optimized, practically implementable impedance sheet-based Meta-atom, and its electromagnetic variations relative to its overall dimensions and thickness. The impedance sheet design yields multiple electromagnetic resonances, facilitating wide bandwidth absorption. To achieve greater optimization and tunability, an inverse deep learning network based on this data is generated. It adapts the same Meta-atom design for RCS reduction across different frequency bands. This model can be employed to create radar-absorbing structures using a single Meta-atom design, tailored to various frequency bands.