发表机构
University of Michigan-Dearborn（密歇根大学迪尔伯恩分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出物理引导的液冷通道生成式设计框架，以条件扩散模型生成2.7 kW多芯片封装的液冷通道布局，筛选后最优设计G1016较传统方案性能显著提升，经OpenFOAM验证效果良好。
AI 中文摘要
高功率多芯片封装因在有限封装区域内产生更多热量，需要日益高效的冷却方案。本研究提出一种物理引导的液冷通道拓扑优化生成式设计框架，适用于含2个高功率GPU和1个CPU的2.7 kW多芯片封装。条件扩散模型以GPU最高温度、GPU温度分布、压降为性能目标生成对称通道布局；生成的设计需经过连通性和死端分支筛选，再经校准的降阶热工 hydraulic 模型评估。在5000个生成布局中，2220个具备连续进出流路径，229个满足最终拓扑筛选标准。多目标分析确定G1016为热性能最优可行设计，其预测GPU最高温度为70.30℃、GPU温度分布为24.90℃、压降为89.72 kPa；与传统参考拓扑相比，该设计分别降低GPU最高温度33.6%、温度分布52.5%、压降72.8%。在OpenFOAM中开展的独立三维共轭传热模拟预测，其GPU最高温度为66.70℃、压降为92.1 kPa，对应降阶模型（ROM）在温升和压降上的差异分别约为8.6%和2.6%。结果表明，物理引导的生成式设计可高效发现非常规冷却通道架构，同时将昂贵的全阶CFD计算限制在最终验证环节。
英文摘要
High-power multi-chip packages require increasingly effective cooling as intensive heat is generated within a limited package area. This work presents a physics-guided generative design framework for liquid-cooling channel topology optimization in a 2.7 kW multi-chip package containing two high-power graphics processing units (GPUs) and one central processing unit (CPU). A conditional diffusion model generates symmetric channel layouts using maximum GPU temperature, GPU temperature spread, and pressure drop as performance targets. Generated designs undergo connectivity and dead-end-branch screening and are evaluated using a calibrated reduced-order thermal-fluids model. Based on 5,000 generated layouts, the multi-objective analysis identified the optimal design for thermal properties, with estimated maximum GPU temperature of 70.30 degree Celsius, GPU temperature spread of 24.90 degree Celsius, and pressure drop of 89.72 kPa. Compared to a conventional reference topology, the optimal design reduced the maximum GPU temperature, temperature spread, and pressure drop by 33.6%, 52.5%, and 72.8%, respectively. High-fidelity three-dimensional conjugate heat-transfer simulation in OpenFOAM estimated a maximum GPU temperature of 66.70 degree Celsius and a pressure drop of 92.1 kPa, showing only differences of 8.6% in temperature rise and 2.6% in pressure drop. The results demonstrate that physics-guided generative design based on the reduced-order model can efficiently discover unconventional cooling channel architectures while reducing reliance on repeating computationally expensive simulation.
Comments29 pages, 5 figures
