VATO：面向非定常分离翼型流动的涡量力感知Transformer算子

中文摘要 AI 辅助

非定常分离流动的精确预测极具挑战性，因为气动力载荷取决于非线性分离和涡脱动力学。虽然高保真计算流体动力学（CFD）可解析这些机制，但其成本限制了在设计和控制中的重复使用。然而，标准场级代理训练无法区分对气动力载荷贡献最大的流动区域。我们提出VATO（涡量力感知Transformer算子，Vortex-Force-Aware Transformer Operator），通过两种互补机制将涡量力图（VFM）方法与几何感知神经算子耦合。VATO-S仅增加训练阶段的局部VFM力贡献场监督，模型大小和推理成本无增长；VATO-A则利用VFM贡献场和灵敏度场，为残差交叉注意力优先选择与力相关的源位置。在9种几何构型的54条轨迹上，针对双缘板翼型的非定常CFD数据对上述方法进行评估。在1-20ms的超前时间内，VATO-S将速度、压力和涡量误差分别降低10.4%、1.0%和15.6%，VATO-A则实现15.8%、7.5%和31.2%的降低。VATO-S的VFM衍生阻力误差最低，VATO-A的压力衍生升力和阻力误差最低。在超前时间超出训练范围50%的情况下，VATO-A仍保持26.9%的涡量误差降低，且在全部四个力读数上均实现更大改进，尽管速度和压力的增益有所减少。这些结果表明，力感知算子学习可提升非定常分离流动中的流场预测和气动力函数精度。

英文摘要

Accurate prediction of unsteady separated flows is challenging because the aerodynamic loads depend on nonlinear separation and vortex-shedding dynamics. Although high-fidelity CFD resolves these mechanisms, its cost limits repeated use in design and control. Standard field-level surrogate training, however, does not distinguish the flow regions that contribute most strongly to the aerodynamic loads. We introduce VATO (Vortex-Force-Aware Transformer Operator), which couples the Vortex Force Map (VFM) method to a geometry-aware neural operator through two complementary mechanisms. VATO-S adds training-only supervision of the local VFM force-contribution field, with no increase in model size or inference cost. VATO-A uses VFM contribution and sensitivity fields to prioritise force-relevant source locations for residual cross attention. The methods are evaluated on unsteady CFD data for double-edged-plate aerofoils over 54 trajectories from nine geometries. Over lead times of 1-20~ms, VATO-S reduces velocity, pressure, and vorticity errors by 10.4\%, 1.0\%, and 15.6\%, respectively, while VATO-A achieves reductions of 15.8\%, 7.5\%, and 31.2\%. VATO-S gives the lowest VFM-derived drag error, whereas VATO-A gives the lowest pressure-derived lift and drag errors. Over lead times extending 50\% beyond the training range, VATO-A retains a 26.9\% reduction in vorticity error and larger improvements in all four force readouts, despite reduced gains in velocity and pressure. These results show that force-aware operator learning can improve both flow-field prediction and aerodynamic functional accuracy in unsteady separated flows.

发表机构

• King’s College London（伦敦国王学院）

机构由 AI 辅助整理，请以论文原文为准。