面向所需发射波束图的 MIMO 探测波形的生成式深度合成
信号处理
2024-12-31 v1
摘要
本文发展了一种生成式深度学习模型,用于合成具有所需属性的多输入多输出(MIMO)主动探测波形,包括恒定幅值和用户定义的波束图。该方法能够按需生成唯一的相位代码,有望减少共存主动探测系统之间的干扰,并促进低概率截获/低概率检测(LPI/LPD)雷达运行。本文扩展了我们之前关于约束正交 MIMO 相位代码合成的工作,引入对发射波束图的灵活控制。开发的机器学习方法采用条件 Wasserstein 生成对抗网络(GAN)结构。该方法的主要优势在于其按需发现新波形(训练后)的能力,以及相对于结构化优化方法在计算复杂度方面的低要求。
引用
@article{arxiv.2412.20883,
title = {Generative Deep Synthesis of MIMO Sensing Waveforms with Desired Transmit Beampattern},
author = {Vesa Saarinen and Robin Rajamäki and Visa Koivunen},
journal= {arXiv preprint arXiv:2412.20883},
year = {2024}
}
备注
\c{opyright} 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works