用于可靠神经算子汽车空气动力学代理的多粒度共形预测
Multi-Granularity Conformal Prediction for Reliable Neural-Operator Automotive Aerodynamic Surrogates
浏览论文内容
中文总结 AI 辅助
研究针对汽车空气动力学代理建模，开发多粒度共形预测框架，以解决神经算子确定性预测问题。利用GeoTransolver等，对阻力系数等进行预测，通过共形校准等方法获得可靠区间，提升可靠性指标，助于后续CFD验证。
中文摘要 AI 辅助
高保真计算流体动力学（CFD）为车辆设计提供详细的空气动力学数据，但其成本限制了设计迭代。神经算子代理降低了成本，但其确定性预测无法表明几何形状或表面区域何时可靠。本研究为DrivAerML数据集上的可靠性感知汽车空气动力学代理建模开发了一个共形预测框架。GeoTransolver是主要骨干，而Transolver评估跨神经算子架构的迁移。对于阻力系数预测，共形化分位数回归构建校准的案例级区间。对于表面压力和壁面剪应力（WSS），点预测与残差尺度估计和残差归一化共形校准相结合以获得空间自适应区间。在拆分和交叉验证辅助的折叠外协议下比较了全局绝对、点自适应归一化和逐案例归一化校准。所有实验目标是90%的名义覆盖率。共形校准纠正了原始阻力系数分位数区间的覆盖率不足，而折叠外分数聚合将蒙特卡罗覆盖率标准差从10.41降低到3.10个百分点。对于表面场，点自适应归一化校准产生最窄的近名义区间，在折叠外协议下压力平均宽度减少22.68%，WSS减少25.35% - 27.09%。逐案例归一化校准更保守但提高了车辆级可靠性。平滑正则化将残差尺度局部变化分数降低74.29%并降低区间宽度而无覆盖率损失。该框架将确定性神经算子输出转换为校准的可靠性指标，以便在后续CFD验证中对不确定的车辆几何形状和表面区域进行优先级排序。
英文摘要
High-fidelity computational fluid dynamics (CFD) provides detailed aerodynamic data for vehicle design, but its cost limits design iteration. Neural-operator surrogates reduce this cost, yet their deterministic predictions do not indicate when a geometry or surface region is reliable. This study develops a conformal-prediction framework for reliability-aware automotive aerodynamic surrogate modeling on the DrivAerML dataset. GeoTransolver is the main backbone, while Transolver assesses transfer across neural-operator architectures. For drag coefficient prediction, conformalized quantile regression constructs calibrated case-level intervals. For surface pressure and wall shear stress (WSS), point prediction is combined with residual-scale estimation and residual-normalized conformal calibration to obtain spatially adaptive intervals. Global absolute, point-adaptive normalized, and case-wise normalized calibration are compared under split and cross-validation-assisted out-of-fold protocols. All experiments target 90% nominal coverage. Conformal calibration corrects the under-coverage of raw drag-coefficient quantile intervals, while out-of-fold score aggregation reduces the Monte Carlo coverage standard deviation from 10.41 to 3.10 percentage points. For surface fields, point-adaptive normalized calibration yields the narrowest near-nominal intervals, reducing mean width by 22.68% for pressure and 25.35%--27.09% for WSS under the out-of-fold protocol. Case-wise normalized calibration is more conservative but improves vehicle-level reliability. Smoothness regularization reduces the residual-scale local-variation score by 74.29% and lowers interval widths without material coverage loss. The framework converts deterministic neural-operator outputs into calibrated reliability indicators for prioritizing uncertain vehicle geometries and surface regions in follow-up CFD verification.
