基于叠加原理的Transformer神经算子提升端壁气膜冷却预测泛化能力
原标题：Enhancing generalization in endwall film cooling prediction: Incorporating the superposition principle into transformer-based neural operators
AI 摘要
研究提出一种物理增强的神经算子框架 SDNO，用于预测涡轮端壁气膜冷却温度场。该方法受气膜冷却叠加原理启发，将预测分为两阶段：Calculate Net 用 Transformer 神经算子预测各子区域温度场，Super Net 将其组合为完整布局的叠加温度场，并用符号距离函数编码气孔位置。模型仅在 1-5 个气孔样本上训练，却能泛化预测 10-20 个未见气孔布局的冷却效果，且精度优于全监督基线。
正文节选
Enhancing generalization in endwall film cooling prediction: Incorporating the superposition principle into transformer-based neural operators Note: Author manuscript. This article appeared in Physics of Fluids 36, 126110 (2024) and may be found at https://doi.org/10.1063/5.0239483. Abstract In this study, a physics-enhanced neural operator framework is proposed to enhance the generalization prediction ability of the cooling layout of a turbine endwall with variable number of film holes. Specifi