翼型模型几何误差对气动性能影响的自动微分分析方法  

An automatic differentiation method for uncertainty analysis due to airfoil configuration variation

作　　者：徐林程[1] 王刚[1] 武洁[1] 叶正寅[1] 

机构地区：[1]西北工业大学、翼型叶栅空气动力学国防科技重点实验室,陕西西安710072

出　　处：《空气动力学学报》2014年第4期551-556,共6页Acta Aerodynamica Sinica

基　　金：国家自然科学基金(11272264)

摘　　要：基于自动微分原理和NS方程有限体积方法建立了一套翼型敏感性导数计算方法和程序,可以一次性获得翼型不同气动力系数、压力分布对模型几何外形误差的敏感性导数和不确定度。计算结果表明,在跨声速范围内,即使翼型的外形误差只有63μm(弦长1m),也可以给翼型压力分布带来0.312(以来流动压为参考)量级的不确定度,而激波处的流动最为敏感。这种自动微分方法对于分析数值模拟结果的分散性、风洞试验结果的分散性或不确定性具有很好的指导意义。Focused on the quantification of the uncertainties of areodynamics performance of airfoils with respect to geometry error,with a set of CFD program based on finite volume algorithm solving the Reynolds-Averaged Navier-Stokes equations with S-A turbulent model,adopting automatic differentiation method to reform the program simultaniously,all kinds of sensitive derivatives,uncertainties of all kinds of aerody-namic coefficients and pressure coefficients distribution resulting from geometry error could be obtained in one course of computation.As the computational results show,even if the geometry error is only 63 microns （while the length of chord is 1 meter）,the pressure distribution of the walls could be influenced obviously with uncertainty quantity reaching 0.312 （taking dynamic pressure of the flow as reference）for an airfois in transonic flow,moreover,pressure attached to the place where shock wave stationed bears peak uncertainty. the results of method of automatic differentiation account for the dispersity of results of numeric simulations and wind tunnel experiments well.

关 键 词：几何误差 不确定性 敏感性分析 自动微分 跨声速 翼型 

分 类 号：V211.3[航空宇航科学与技术—航空宇航推进理论与工程]