四川大学学报（自然科学版）2025，Vol.62Issue(2)：359-368,10.DOI:10.19907/j.0490-6756.240008
基于流场反演和图神经网络的翼型分离流动预测方法
An airfoil separation flow prediction method based on field inversion and graph neural network
摘要
Abstract
The traditional Reynolds-Averaged Navier-Stokes(RANS)model uses the Boussinesq approxi-mation and assumes a linear relationship between the turbulent Reynolds stress and the average velocity gradi-ent tensor.While this assumption applies to simple shear flows,its extension to intricate separated flow sce-narios poses challenges.To address the limitation of the multilayer perceptron network commonly utilized in the Field Inversion and Machine Learning(FIML)framework for representing turbulence spatial correlation,this paper proposes a graph neural network to modify the production term of the Spalart-Allmaras one-equation turbulence model.Furthermore,a weighted function is devised utilizing the characteristics of flow field separation to augment the message passing mechanism of the graph neural network.The experimental re-sults for separated flow over the S809 airfoil at high angles of attack and high Reynolds numbers indicate that,compared with the existing multilayer perceptron networks,the utilization of graph neural network results in lift coefficient predictions that closely align with experimental values at various angles of attack and grid con-figurations.Moreover,the incorporation of a novel message passing mechanism in the graph neural network enhances its predictive accuracy.关键词
湍流建模/流场反演/图神经网络/计算流体力学/数值模拟Key words
Turbulence modeling/Field inversion/Graph neural network/Computational fluid dynamics/Numerical simulation分类
信息技术与安全科学引用本文复制引用
邹远洋,董义道,张来平,邓小刚..基于流场反演和图神经网络的翼型分离流动预测方法[J].四川大学学报（自然科学版）,2025,62(2):359-368,10.基金项目
国家重大专项(GJXM92579) （GJXM92579）
国防科技大学科研计划项目(ZK21-08) （ZK21-08）
