Electromagnetic Illusion Device Based on Diffraction Neural Network

Abstract

In recent years, electromagnetic illusion technology has used metasurface technology to accurately manipulate radar wavefront, which enhances the controllability and adaptability of electromagnetic engineering. However, traditional metasurface-based electromagnetic illusion technology faces the problem of difficulty in achieving far-field measurement conditions, and phase acquisition in near-field measurement is difficult. Therefore, this paper proposes an electromagnetic camouflage device based on a diffraction neural network (DNN). The device can perform phase-free near-field testing to determine the radar cross-section (RCS) of the target. Using this device, we can use metasurface technology to reconstruct RCS. The mean square error (MSE) between the reconstructed RCS and the target RCS is below 0.02, which has great potential in military applications.