面向AI辅助工程的CAD原生Transformer算子
CANTO: CAD-Native Transformer Operators for AI-Aided Engineering
- NVIDIA（英伟达）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
CANTO是一种CAD原生的Transformer神经算子，直接从连续NURBS几何映射到物理场，无需网格划分，在多个空气动力学基准上达到最先进精度，并支持基于梯度的逆向设计。
中文摘要 AI 辅助
现代工程系统，从汽车到飞机，都是通过使用精确、连续的参数化计算机辅助设计（CAD）模型来设计的。通过数值模拟评估设计变更需要对连续几何体进行网格划分，这是一个计算成本高昂且往往脆弱的流程，可能需要人工干预，并将连续表示替换为离散近似。大多数神经代理模型加速了模拟，但通过依赖网格、点云、体素或其他几何的采样近似，继承了这种表示差距。我们引入了CANTO，一种Transformer神经算子，它直接从连续的CAD几何体映射到物理场，无需对输入几何体进行网格划分。我们开发了一个理论框架，用于从几何流形学习到物理场函数空间的算子，通过参数化补丁的序列来表示几何体。CANTO通过直接从其控制点、节点向量和权重对非均匀有理B样条（NURBS）补丁进行分词，并预测任意查询位置处的连续表面和体积场，从而实例化该框架。我们在四个汽车和飞机空气动力学行业基准上评估了CANTO：AhmedML、WindsorML、DrivAerML和HiLiftAeroML。CANTO在大多数评估的表面和体积预测任务上达到了最先进的精度，包括在HiLiftAeroML上，与AB-UPT相比，表面压力相对$L_2$误差降低了19.8%。相对于CAD参数的可微性进一步支持了基于梯度的设计逆向设计。在AhmedML上，CANTO识别出的设计比满足相同体积和升力约束的最佳数据集设计的阻力低4.4%至20.4%，这些改进通过用于生成原始数据集的相同CFD设置进行了验证。
英文摘要
Modern engineering systems, from automobiles to aircraft, are designed by using precise, continuous parametric computer-aided design (CAD) models. Evaluating design changes through numerical simulation requires meshing the continuous geometry, a computationally expensive and often brittle process that can require manual intervention and replaces the continuous representation with a discrete approximation. Most neural surrogates accelerate the simulation, but inherit this representation gap by relying on meshes, point clouds, voxels, or other sampled approximations of geometry. We introduce CANTO, a transformer neural operator that maps directly from continuous CAD geometry to physical fields, without meshing the input geometry. We develop a theoretical framework for learning operators from geometric manifolds to function spaces of physical fields, representing geometry through sequences of parametric patches. CANTO instantiates this framework by directly tokenizing non-uniform rational B-spline (NURBS) patches from their control points, knot vectors, and weights, and predicts continuous surface and volume fields at arbitrary query locations. We evaluate CANTO on four automotive and aircraft aerodynamics industry benchmarks: AhmedML, WindsorML, DrivAerML, and HiLiftAeroML. CANTO achieves state-of-the-art accuracy on most evaluated surface and volume prediction tasks, including a 19.8% reduction in surface-pressure relative $L_2$ error compared with AB-UPT on HiLiftAeroML. Differentiability with respect to CAD parameters further enables gradient-based inverse design of designs. On AhmedML, CANTO identifies designs with 4.4 to 20.4% lower drag than the best dataset designs satisfying the same volume and lift constraints, with the improvements verified using the same CFD setup used to generate the original dataset.
