摘要：超表面因其对电磁波的卓越调控能力，在各个领域展现出重要价值。但由于其几何构型与电磁响应之间高度复杂的非线性映射关系，导致传统超表面设计方法依赖于海量的电磁仿真，严重制约了设计效率。为突破这一瓶颈，本文提出了基于一个深度神经网络的高性能相位预测模型的全自动化设计平台来快速设计聚焦型超表面。本文采用Python-CST软件的联合电磁仿真，结合一种创新的高效建模策略，在2至18GHz的超宽带内生成20000组均匀的几何数据-反射相位数据集，然后利用 KAN-CNN模块、注意力机制、残差连接等先进技术构建的相位预测网络，结合优化算法来实现由目标相位快速生成超表面结构参数。实验结果表明，该平台实现了92.7%的高精度宽带反射相位预测准确率，大幅提高了设计流程的效率，最终设计出在8 GHz频段下焦距为100 mm的高性能聚焦超表面阵列。

关键词：聚焦超表面；逆向设计；深度学习；KAN-CNN；

Abstract:Metasurfaces have demonstrated significant value across various fields due to its exceptional ability to manipulate electromagnetic waves. However, the highly complex nonlinear mapping relationship between their geometric configurations and electromagnetic responses has led traditional metasurface design methods to rely on massive electromagnetic simulations, severely constraining design efficiency. To achieve a breakthrough in this bottleneck, this paper proposes a fully automated design platform based on a high-performance phase prediction model using deep neural networks for the rapid design of focusing metasurfaces.This study adopts a co-simulation approach integrating Python and CST software, combined with an innovative high-efficiency modeling strategy to generate a uniform dataset of 20,000 sets of geometric data–reflection phase pairs across an ultra-wideband frequency range of 2 to 18 GHz. Advanced techniques—including a KAN-CNN module, attention mechanisms, and residual connections—are utilized to construct a phase prediction network. This network, combined with optimization algorithms, enables the rapid generation of metasurface structural parameters from target phase profiles.Experimental results demonstrate that the platform achieves a high prediction accuracy of 92.7% for broadband reflection phases, significantly enhancing the efficiency of the design workflow. The platform ultimately designs a high-performance focusing metasurface array with a focal length of 100 mm operating in the 8 GHz band.
Key words: Focusing Metasurface; Inverse Design; Deep Learning; KAN-CNN;
 

聚焦超表面；逆向设计；深度学习；KAN-CNN；