模拟器精化扩散用于射频逆向设计
Simulator-Refined Diffusion for Radio-Frequency Inverse Design
- University of Virginia（弗吉尼亚大学）
- Arena Physica
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出模拟器精化扩散（SRD），结合可微代理与不可微模拟器，解决扩散模型在PCB逆向设计中难以满足电磁规格的问题，实验显示S参数匹配度显著提升。
AI中文摘要：
扩散模型在印刷电路板（PCB）逆向设计中展现出潜力，能够生成以目标S参数为条件的布局。尽管有此前景，将扩散模型应用于PCB布局生成仍具挑战性，因为其难以满足定量电磁规格。常见方法是基于梯度的引导，利用用于评估的目标函数的梯度来偏置扩散采样过程。然而，全波电磁模拟器准确但昂贵且通常不可微，而可微代理模型信息丰富但并非总是可靠。为解决这些局限，本文提出模拟器精化扩散（SRD），一种在扩散采样过程中将低保真可微代理模型与高保真不可微模拟器新颖结合的方法。与需要大量随机扰动的标准零阶优化不同，我们的方法利用代理模型的梯度来提出扰动方向，随后模拟器基于该方向进行搜索以识别有效的设计更新。不同设置下的实验结果表明，该方法持续优于当前最先进方法，生成的布局其模拟S参数与目标规格的匹配度在分布内目标上最高提升21.2%，在分布外目标上最高提升19.8%。
英文摘要：
Diffusion models have shown potential in inverse design of printed circuit boards (PCBs), enabling the generation of layouts conditioned on target S-parameters. Despite this promise, applying diffusion models to PCB layout generation remains challenging due to their difficulty in meeting the quantitative electromagnetic specifications. A common approach is gradient-based guidance, which biases the diffusion sampling process with the gradient of an objective used for evaluation. However, full-wave electromagnetic simulators are accurate but expensive and typically non-differentiable, whereas differentiable surrogates are informative but not always reliable. To address these limitations, this paper proposes Simulator-Refined Diffusion (SRD), a novel combination of a low-fidelity differentiable surrogate and a high-fidelity non-differentiable simulator within the diffusion sampling process. Unlike standard zeroth-order optimization, which requires a great number of random perturbations, our approach uses the surrogate's gradient to propose the perturbation direction while the simulator then searches based on this direction to identify an effective design update. Experimental results across different settings show that this method consistently outperforms current state-of-the-art methods, producing layouts whose simulated S-parameters match the target specifications up to 21.2% closer for in-distribution targets and up to 19.8% for out-of-distribution targets.
