用几何感知模型学习瞬态对流换热，实现物理仿真快速生成。
Learning Transient Convective Heat Transfer with Geometry Aware World Models
- 基于视频生成架构改进，加入全局参数与局部几何掩码双重条件控制。
- 在二维对流换热问题上成功复现复杂时空动态，训练数据拟合度高。
- 适合需要快速物理仿真且关注几何变化的工程场景，但外推精度有限。
偏微分方程（PDE）模拟是工程与物理的基础，但通常计算成本过高，难以用于实时应用。尽管生成式AI为代理建模提供了新路径，但标准视频生成架构缺乏物理仿真所需的精确控制与数据兼容性。本文提出一种基于长视频生成模型（LongVideoGAN）的几何感知世界模型架构，专为学习瞬态物理设计。引入两个关键组件：(1) 结合全局物理参数与局部几何掩码的双重条件机制；(2) 支持任意通道维度的结构适配，突破传统RGB限制。在包含浮力驱动流与固体导热耦合的二维瞬态计算流体动力学（CFD）问题上进行评估。结果表明，该条件模型能准确再现训练数据的复杂时空动态与空间相关性。进一步测试其在未见几何构型下的泛化能力，验证了其在可控仿真生成中的潜力，但也揭示了对分布外样本的空间精度仍存在局限。
原文摘要 · Abstract (English)
Partial differential equation (PDE) simulations are fundamental to engineering and physics but are often computationally prohibitive for real-time applications. While generative AI offers a promising avenue for surrogate modeling, standard video generation architectures lack the specific control and data compatibility required for physical simulations. This paper introduces a geometry aware world model architecture, derived from a video generation architecture (LongVideoGAN), designed to learn transient physics. We introduce two key architecture elements: (1) a twofold conditioning mechanism incorporating global physical parameters and local geometric masks, and (2) an architectural adaptation to support arbitrary channel dimensions, moving beyond standard RGB constraints. We evaluate this approach on a 2D transient computational fluid dynamics (CFD) problem involving convective heat transfer from buoyancy-driven flow coupled to a heat flow in a solid structure. We demonstrate that the conditioned model successfully reproduces complex temporal dynamics and spatial correlations of the training data. Furthermore, we assess the model's generalization capabilities on unseen geometric configurations, highlighting both its potential for controlled simulation synthesis and current limitations in spatial precision for out-of-distribution samples.
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。