arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.09578cs.LGcs.AIphysics.comp-ph
收藏

HeatGen:多物理场散热器设计优化的引导扩散框架

HeatGen: A Guided Diffusion Framework for Multiphysics Heat Sink Design Optimization

Department of Mechanical Engineering(机械工程系);University of British Columbia(不列颠哥伦比亚大学);Institute for Nano- and Microfluidics(纳微流体研究所);Technical University of Darmstadt(德累斯顿技术大学)

Hadi Keramati, Morteza Sadeghi, Rajeev K. Jaiman

AI总结:

本研究提出HeatGen引导扩散框架,利用DDPM和代理梯度生成散热器设计,在维持表面温度低于阈值的同时最小化压降,相比传统方法压降降低10%,推理高效且无需重新训练,为电子冷却生成模型奠定基础。

摘要:

本研究提出一种基于引导去噪扩散概率模型(DDPM)的生成式优化框架,该框架利用代理梯度生成散热器设计,在将表面温度维持在指定阈值以下的同时最小化压降。几何结构采用多个散热片的边界表示法,训练数据通过多保真度方法生成。利用该数据集及代表边界表示几何结构的向量,我们训练去噪扩散概率模型生成与数据中观察到的特征一致的散热器。我们训练两个不同的残差神经网络来预测每个几何结构的压降和表面温度,并使用这些代理模型相对于设计变量的梯度引导几何生成过程,使其满足低压降和表面温度约束。与CMA-ES等传统优化方法相比,这种推理时引导使生成过程得到的散热器设计不仅能防止过热,还能实现更低的压降。与传统黑箱优化方法相比,只要有足够的训练数据,我们的方法具有可扩展性。与传统拓扑优化方法不同,模型训练完成并保存散热器世界模型后,在新约束(如温度)下的推理计算成本低,无需重新训练。引导扩散模型生成的样本压降比传统黑箱优化方法获得的限值低10%。这项工作为构建电子冷却的基础生成模型迈出了一步。

英文摘要:

This study presents a generative optimization framework based on a guided denoising diffusion probabilistic model (DDPM) that leverages surrogate gradients to generate heat sink designs minimizing pressure drop while maintaining surface temperatures below a specified threshold. Geometries are represented using boundary representations of multiple fins, and a multi-fidelity approach is employed to generate training data. Using this dataset, along with vectors representing the boundary representation geometries, we train a denoising diffusion probabilistic model to generate heat sinks with characteristics consistent with those observed in the data. We train two different residual neural networks to predict the pressure drop and surface temperature for each geometry. We use the gradients of these surrogate models with respect to the design variables to guide the geometry generation process toward satisfying the low-pressure and surface temperature constraints. This inference-time guidance directs the generative process toward heat sink designs that not only prevent overheating but also achieve lower pressure drops compared to traditional optimization methods such as CMA-ES. In contrast to traditional black-box optimization approaches, our method is scalable, provided sufficient training data is available. Unlike traditional topology optimization methods, once the model is trained and the heat sink world model is saved, inference under new constraints (e.g., temperature) is computationally inexpensive and does not require retraining. Samples generated using the guided diffusion model achieve pressure drops up to 10 percent lower than the limits obtained by traditional black-box optimization methods. This work represents a step toward building a foundational generative model for electronics cooling.

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。

↑