稳态神经CFD代理模型的跨域预训练
Cross-Domain Pretraining for Steady-State Neural CFD Surrogates
浏览论文内容
中文总结 AI 辅助
本文研究跨域预训练提升稳态CFD神经代理模型的泛化能力，发现其可显著降低误差并减少所需样本，且简单汇集数据集即有效。
中文摘要 AI 辅助
计算流体力学（CFD）的神经代理模型有望通过加速模拟来极大促进工程创新。然而，神经代理模型的主要局限在于对训练集之外的几何形状和应用缺乏泛化能力，考虑到工程场景的多样性，这一问题尤为显著。目前，解决该问题的方法是为特定应用生成新数据集，但这需要运行昂贵的数值求解器。在本工作中，我们朝解决此问题迈出了一步，研究了在不同几何形状、边界条件和保真度上训练的神经代理模型。我们发现，相对于从零开始训练和从特定领域专家模型迁移，跨域预训练在保留数据集上的零样本和少样本性能均有提升。特别是，微调一个预训练的跨域模型，在相同样本量下可实现2-3倍更低的误差，并且达到相同误差所需的样本量减少8倍，相比于从零开始训练。这一优势与架构无关，并随模型规模和预训练数据集多样性增加而提升。此外，我们研究了跨域预训练在CFD代理模型中如何及为何有效，发现简单地汇集稳态数据集既充分又有效。鉴于生成CFD数据的高成本，利用现有数据集进行跨域预训练，随着未来代理模型扩展至新问题和使用场景，很可能成为一种有价值的策略。
英文摘要
Neural surrogates for computational fluid dynamics (CFD) have the potential to greatly enhance engineering innovation through accelerating simulation. However, the primary limitation for neural surrogates is the lack of generalization to geometries and applications beyond the training set, which is significant given the diversity of engineering scenarios. Currently, this is addressed by generating a new dataset for a specific application; however, this requires running costly numerical solvers. In this work, we take a step toward addressing this by studying neural surrogates trained across different geometries, boundary conditions, and fidelities. We find that cross-domain pretraining improves zero- and few-shot performance on held-out datasets relative to both training from scratch and transferring from domain-specific experts. In particular, finetuning a pretrained, cross-domain model can achieve 2-3x lower errors at the same sample size and use 8x fewer samples to achieve the same error, compared to training from scratch. This benefit is architecture agnostic and improves with model size and pretraining dataset diversity. Furthermore, we study how and why cross-domain pretraining works in CFD surrogates, and find that simply pooling steady-state datasets is both sufficient and effective. Given the high cost of generating CFD data, leveraging existing datasets through cross-domain pretraining will likely be a valuable strategy as future surrogates expand to tackle new problems and use cases.
发表机构
- Carnegie Mellon University（卡内基梅隆大学）
- New York University（纽约大学）
- Princeton University（普林斯顿大学）
- Polymathic AI
- Flatiron Institute, Center for Computational Astrophysics（Flatiron研究所，计算天体物理中心）
- Flatiron Institute, Center for Computational Mathematics（Flatiron研究所，计算数学中心）
- Flatiron Institute, Scientific Computing Core（Flatiron研究所，科学计算核心）
机构由 AI 辅助整理，请以论文原文为准。
