用生成模型+测试时优化，自动设计高性能矩形贴片天线
Improving Generative Inverse Design of Rectangular Patch Antennas with Test Time Optimization
- 先学天线频响特征，再生成符合要求的天线结构
- 测试时优化使设计更精准，还能兼顾可制造性
- 方法通用性强，适合复杂几何设计
我们提出一种两阶段深度学习框架，用于矩形贴片天线的逆向设计。该方法利用生成模型学习天线频率响应曲线的潜在表示，并以此条件化后续生成模型，产出可行的天线几何结构。进一步证明，在测试时引入搜索与优化技术能提升生成设计的准确性，并支持考虑可制造性等附加目标。该方法可自然推广至不同设计标准，且易于扩展到更复杂的几何设计空间。
原文摘要 · Abstract (English)
We propose a two-stage deep learning framework for the inverse design of rectangular patch antennas. Our approach leverages generative modeling to learn a latent representation of antenna frequency response curves and conditions a subsequent generative model on these responses to produce feasible antenna geometries. We further demonstrate that leveraging search and optimization techniques at test-time improves the accuracy of the generated designs and enables consideration of auxiliary objectives such as manufacturability. Our approach generalizes naturally to different design criteria, and can be easily adapted to more complex geometric design spaces.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。