arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.05976physics.comp-phcs.LG
收藏

声子玻尔兹曼输运方程的物理增强深度代理模型

Physics Enhanced Deep Surrogates for the Phonon Boltzmann Transport Equation

School of Computational Science and Engineering, Georgia Institute of Technology(计算科学与工程学院,佐治亚理工学院);Institute for Soldier Nanotechnologies, Massachusetts Institute of Technology(士兵纳米技术研究所,麻省理工学院)

Antonio Varagnolo, Giuseppe Romano, Raphaël Pestourie

AI总结:

提出物理增强深度代理模型(PEDS),结合可微傅里叶求解器与神经网络生成器,通过不确定性驱动主动学习,在弹道和扩散区域实现高精度、高数据效率的声子输运模拟,仅需300次高保真BTE模拟即可达到约5%的误差。

摘要:

设计具有可控纳米尺度热流的材料对于微电子、热电和能量转换技术的进步至关重要。在这些尺度上,声子输运遵循玻尔兹曼输运方程(BTE),该方程捕捉了非扩散(弹道)效应,但在逆设计循环中反复求解成本过高。现有的代理方法在速度和准确性之间权衡:快速宏观求解器可能高估热导率数百个百分点,而最近的数据驱动算子学习器通常需要数千次高保真模拟。因此,需要一种快速、数据高效的代理模型,在弹道和扩散区域均保持可靠。我们提出了一种物理增强深度代理模型(PEDS),它将可微傅里叶求解器与神经网络生成器相结合,并与不确定性驱动的主动学习耦合。傅里叶求解器作为物理归纳偏置,而网络学习几何依赖的修正和混合系数,该系数在宏观和纳米尺度行为之间插值。与纯数据驱动基线相比,PEDS将训练数据需求降低了高达70%,仅需300次高保真BTE模拟即可实现约5%的分数误差,并能够高效设计覆盖12-85 W m$^{-1}$ K$^{-1}$的多孔几何结构,平均设计误差为4%。学习到的混合参数恢复了弹道-扩散转变,并提高了分布外鲁棒性。这些结果表明,嵌入简单、可微的低保真物理可以显著提高代理模型的数据效率和可解释性,使重复的PDE约束优化在纳米尺度热材料设计中变得实用。

英文摘要:

Designing materials with controlled heat flow at the nano-scale is central to advances in microelectronics, thermoelectrics, and energy-conversion technologies. At these scales, phonon transport follows the Boltzmann Transport Equation (BTE), which captures non-diffusive (ballistic) effects but is too costly to solve repeatedly in inverse-design loops. Existing surrogate approaches trade speed for accuracy: fast macroscopic solvers can overestimate conductivities by hundreds of percent, while recent data-driven operator learners often require thousands of high-fidelity simulations. This creates a need for a fast, data-efficient surrogate that remains reliable across ballistic and diffusive regimes. We introduce a Physics-Enhanced Deep Surrogate (PEDS) that combines a differentiable Fourier solver with a neural generator and couples it with uncertainty-driven active learning. The Fourier solver acts as a physical inductive bias, while the network learns geometry-dependent corrections and a mixing coefficient that interpolates between macroscopic and nano-scale behavior. PEDS reduces training-data requirements by up to 70% compared with purely data-driven baselines, achieves roughly 5% fractional error with only 300 high-fidelity BTE simulations, and enables efficient design of porous geometries spanning 12-85 W m$^{-1}$ K$^{-1}$ with average design errors of 4%. The learned mixing parameter recovers the ballistic-diffusive transition and improves out of distribution robustness. These results show that embedding simple, differentiable low-fidelity physics can dramatically increase surrogate data-efficiency and interpretability, making repeated PDE-constrained optimization practical for nano-scale thermal-materials design.

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。

↑