基于物理信息神经网络的气膜冷却湍流模型反演学习  

PINN-based Inversion Learning of Turbulence Model for Film Cooling

作　　者：张振[1] 苏欣荣 袁新[1] ZHANG Zhen;SU Xinrong;YUAN Xin(Department of Energy and Power Engineering,Tsinghua University,Beijing 100084,China)

机构地区：[1]清华大学能源与动力工程系,北京100084

出　　处：《动力工程学报》2024年第9期1459-1465,共7页Journal of Chinese Society of Power Engineering

基　　金：国家自然科学基金资助项目(52306043、52276031);国家科技重大专项资助项目(J2019-III-0007-0050)。

摘　　要：由于气膜冷却问题中湍流的复杂特性,传统雷诺平均(RANS)方法会低估湍流的热扩散强度,导致冷却效果计算不准确。对此提出了一套基于物理信息神经网络(PINN)的湍流建模框架,基于RANS流场和大涡模拟(LES)温度场,建立了数据驱动的湍流普朗特数神经网络模型,在RANS求解器中嵌入该模型,可以动态调整湍流的热扩散强度,获得了与LES高度一致的温度场。结果表明:PINN是构建数据驱动湍流模型的良好方法,对于湍流普朗特数的建模可以有效提升RANS方法对温度预测的准确性。Due to the complexity of turbulent flow problems for film cooling,the traditional Reynolds average Navier-Stokes(RANS)method tends to underestimate the intensity of turbulent thermal diffusion,leading to inaccurate prediction of cooling effectiveness.A framework based on physics-informed neural network(PINN)was therefore proposed,and a data-driven neural network model of turbulent Prandtl number was built based on RANS flow data and large eddy simulation(LES)temperature data.After implementing this model into a RANS solver,the intensity of turbulent thermal diffusion could be adjusted dynamically and a temperature distribution highly consistent with LES results was obtained.Results show that PINN is an effective method to build a data-driven turbulence model and modeling of turbulent Prandtl number can effectively improve the accuracy of RANS temperature prediction.

关 键 词：气膜冷却 物理信息神经网络 湍流普朗特数 机器学习 湍流模型 

分 类 号：TK05[动力工程及工程热物理]