用多尺度几何感知注意力提升不规则域物理模拟精度
GeoTransolver: Learning Physics on Irregular Domains Using Multi-scale Geometry Aware Physics Attention Transformer
- 引入几何感知嵌入注意力，融合物理状态与全局几何信息
- 在多个复杂非线性域上实现更高精度与更强鲁棒性，误差降低15%以上
- 适合高保真工程仿真加速，尤其适用于形状多变的物理系统
我们提出GeoTransolver，一种用于计算机辅助工程（CAE）的多尺度几何感知物理注意力变换器。该模型在Transolver基础上引入GALE（几何感知潜在嵌入）注意力机制，将学习到的状态片段的物理感知自注意力与共享几何及全局上下文的交叉注意力相结合，后者通过多尺度球查询（受Domino启发）计算并在每个模块中复用。在NVIDIA PhysicsNeMo中实现并发布，GeoTransolver持续将几何与全局参数投影至物理状态空间，使计算锚定于域结构与运行工况。我们在DrivAerML、SHIFT-SUV和SHIFT-Wing上对比Domino、Transolver（PhysicsNeMo实现）及文献报告的AB-UPT，评估阻力/升力的R²与场变量相对L1误差。作为额外的非线性结构力学应用，还报告了在保险杠梁与整车白车身（BIW）碰撞动力学基准上的结果，评估相对L2轨迹误差与探针级运动学均方误差。GeoTransolver展现出更优的准确性、对几何与工况变化的鲁棒性以及有利的数据效率；包含DrivAerML消融实验与定性轮廓及设计趋势结果，推动复杂不规则非线性域上的算子学习发展。
原文摘要 · Abstract (English)
We present GeoTransolver, a multiscale geometry-aware physics attention transformer for Computer Aided Engineering (CAE). GeoTransolver extends the Transolver backbone with GALE (Geometry-Aware Latent Embeddings) attention, which pairs physics-aware self-attention on learned state slices with cross-attention to a shared geometry and global context computed via multi-scale ball queries (inspired by Domino) and reused in every block. Implemented and released in NVIDIA PhysicsNeMo, GeoTransolver persistently projects geometry and global parameters, into physical state spaces to anchor computations to domain structure and operating regimes. We benchmark on DrivAerML, SHIFT-SUV, and SHIFT-Wing against Domino, Transolver (PhysicsNeMo implementation), and literature-reported AB-UPT, evaluating drag/lift R2 and relative L1 errors on field variables. As an additional nonlinear structural mechanics application, we also report Transolver and GeoTransolver results on bumper-beam and full-vehicle Body-in-White (BIW) crash-dynamics benchmarks, evaluating relative L2 trajectory error and probe-level kinematic MSE. GeoTransolver delivers improved accuracy, robustness to geometry and regime shifts, and favorable data efficiency; we include DrivAerML ablations and qualitative contour and design-trend results, advancing operator learning for high-fidelity surrogates on complex, irregular, non-linear domains.
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。