AI 中文总结
本文提出从二维几何学习流场表示并迁移至三维飞机，比较LVAE与POD，证明线性POD迁移更准，且迁移学习在数据稀缺时显著提升重建精度。
AI 中文摘要
分析空气动力学表面上的流场对于设计下一代飞机至关重要。原始计算表示是高维的，并且对于复杂的三维物体来说成本高昂，而传统的低维表示仅适用于它们所源自的系统。我们提出了一种方法，从简单的二维几何形状学习流体流动表示，并将其迁移到复杂的真实世界三维飞机上。将提出的最小体积自编码器（LVAE）与本征正交分解（POD）进行比较，我们表明两者都能产生二维流场的紧凑的28-41维表示，其中非线性的LVAE在匹配维度下产生更准确的域内重建。这些模型零样本迁移到三维系统，并且与直觉相反，线性POD比LVAE迁移得更准确。应用于挤压翼时，POD重建的升力和阻力保持在真实值的0.1%和0.7%以内，而迁移到复杂的翼身融合飞机时，在没有任何三维训练数据的情况下，升力和阻力保持精度在0.3%和0.7%以内。我们进一步表明，预训练模型遗漏的三维流动模式可以被分离出来，通过双编码器-解码器迁移学习策略训练一个解耦的三维潜在空间，在以前无法访问的数据稀缺区域中准确执行。仅使用五个翼身融合训练案例，均方重建误差相对于二维预训练模型下降了5倍，相对于从头训练的模型下降了70倍。这些结果表明，从现成的二维数据集进行迁移学习能够解锁复杂三维飞机表面流动的紧凑、可解释的表示，从而在传统方法需要数百到数千次模拟的数据匮乏的早期设计阶段提供设计见解。
英文摘要
Analyzing flow fields on aerodynamic surfaces is critical to designing next-generation aircraft. Raw computational representations are high-dimensional and costly for complex three-dimensional bodies, while conventional low-dimensional representations apply only to the systems from which they derive. We introduce an approach that learns fluid flow representations from simple two-dimensional geometries and transfers them to complex real-world three-dimensional aircraft. Comparing the proposed Least Volume autoencoder (LVAE) to proper orthogonal decomposition (POD), we show both yield compact 28-41 dimensional representations of two-dimensional flow fields, with the nonlinear LVAE producing more accurate in-domain reconstructions at matched dimensionality. These models transfer zero-shot to three-dimensional systems, and counterintuitively the linear POD transfers more accurately than LVAE. Applied to extruded wings, POD-reconstructed lift and drag remain within 0.1% and 0.7% of true values, while transfer to complex blended wing body aircraft preserves lift and drag to within 0.3% and 0.7% without any three-dimensional training data. We further show that three-dimensional flow patterns missed by the pretrained model can be isolated to train a disentangled 3D latent space via a dual encoder-decoder transfer learning strategy, performing accurately in previously inaccessible data-scarce regimes. Using only five blended wing training cases, mean squared reconstruction error drops by 5x relative to the 2D pretrained models and 70x relative to models trained from scratch. These results establish that transfer learning from readily available two-dimensional datasets unlocks compact, interpretable representations of complex three-dimensional aircraft surface flows, enabling design insights in data-starved early phases where conventional approaches require hundreds to thousands of simulations.
Comments30 pages (main document and supplementary) and 12 figures. Submitted to Machine Learning: Engineering
