GeoReplay 方法提升车辆空气动力学神经代理模型的跨类别迁移能力
Measuring and Improving Transfer of Neural Surrogates for Vehicle Aerodynamics
造车或做仿真工具的团队会关心:这篇论文测了 5 个预训练代理模型跨车型迁移,发现微调多数情况反而不划算,提出的 GeoReplay 在 80 个设置里 77 个降低了源域误差,比直接微调更稳。
arXiv 论文针对车辆外空气动力学神经代理模型无法零样本泛化到新车辆类别的问题,开展了大规模基准测试:在 DrivAerML 上预训练的五个代理模型被迁移到四个独立目标数据集,这些数据集在几何、CFD 求解器、湍流模型和流动条件上均与源域不同。
研究发现,微调预训练代理模型仅在不到一半的对比中优于从零训练,且会降低模型在源数据集上的精度。作者提出 GeoReplay,一种几何与梯度对齐的源域回放方法:训练时让源仿真在几何上接近目标,并只在源梯度与目标梯度一致时才应用其更新。论文还给出风险 bound,将几何覆盖与仿真物理差异分离,并证明每个足够小的 GeoReplay 步都会降低目标训练目标。
实验结果显示,GeoReplay 在 80 个设置中的 77 个降低了微调带来的源域误差,同时保持与普通微调相当的目标域精度。
Measuring and Improving Transfer of Neural Surrogates for Vehicle Aerodynamics
Neural surrogates for external vehicle aerodynamics are fast alternatives to physics-based computational fluid dynamics (CFD) simulations. Their foundational limitation is a lack of zero-shot generalization across vehicle classes, which results in an expensive, custom training campaign for each new vehicle design. Similar to pretrained models in other fields, a pretrained surrogate should adapt to a new vehicle class using only a few simulations and stay accurate on its pretraining domain. No prior study has systematically tested this transfer behavior. We conduct a large-scale, controlled benchmarking study on five DrivAerML-pretrained surrogates across four independent target datasets. These datasets differ from the source in geometry, CFD solver, turbulence model, and flow conditions. We find that fine-tuning these surrogates outperforms training from scratch in fewer than half of the comparisons and lowers the accuracy of the surrogate on its source dataset. We introduce GeoReplay, a geometry- and gradient-aligned source replay that keeps source simulations resembling the target in training and applies their updates only when they agree with the target gradient. A risk bound separates geometric coverage from differences in the simulated physics, and we prove that every sufficiently small GeoReplay step decreases the target training objective. GeoReplay lowers the source error of fine-tuning in 77 of 80 settings and matches its target accuracy.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include GeoReplay, DrivAerML, CFD, transfer learning.
Source attribution: curated from arXiv cs.LG (@Favour Nerrise, Julian Busch, Gurpreet Singh Hora, Martin Sipka, Danielle C. Maddix, Georgia Olympia Brikis).