arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.11323cs.LGeess.SPphysics.app-phstat.ML
收藏

物理信息机器学习用于高效可重构智能表面设计

Physics-Informed Machine Learning for Efficient Reconfigurable Intelligent Surface Design

Guangzhou University(广州大学);Southeast University(东南大学);Hong Kong Polytechnic University(香港理工大学)

Zhen Zhang, Jun Hui Qiu, Jun Wei Zhang, Hui Dong Li, Dong Tang, Qiang Cheng, Wei Lin

AI总结:

针对传统RIS设计依赖耗时电磁仿真的问题,提出结合MLP与双端口网络的机器学习方法,快速预测反射系数,实验验证有效。

摘要:

可重构智能表面(RIS)是一种集成了大量反射元件的二维周期结构,能够以数字方式操纵电磁波,为无线通信和雷达探测应用提供了巨大潜力。然而,传统的RIS设计高度依赖于极其耗时的大规模全波电磁仿真。为应对这一挑战,我们提出了一种基于机器学习辅助的高效RIS设计方法。通过结合多层感知器神经网络(MLP)和双端口网络,开发了一个准确且快速的模型来预测RIS元件的反射系数,这能显著减少网络训练中繁琐的电磁仿真。基于所提出的方法,实际设计了一个RIS。为验证所提方法,该RIS也被制造并进行了测量。实验结果与仿真结果高度一致,验证了所提方法在RIS设计中的有效性。

英文摘要:

Reconfigurable intelligent surface (RIS) is a two-dimensional periodic structure integrated with a large number of reflective elements, which can manipulate electromagnetic waves in a digital way, offering great potentials for wireless communication and radar detection applications. However, conventional RIS designs highly rely on extensive full-wave EM simulations that are extremely time-consuming. To address this challenge, we propose a machine-learning-assisted approach for efficient RIS design. An accurate and fast model to predict the reflection coefficient of RIS element is developed by combining a multi-layer perceptron neural network (MLP) and a dual-port network, which can significantly reduce tedious EM simulations in the network training. A RIS has been practically designed based on the proposed method. To verify the proposed method, the RIS has also been fabricated and measured. The experimental results are in good agreement with the simulation results, which validates the efficacy of the proposed method in RIS design.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑