基于神经网络的翼型优化设计方法研究

Aerodynamic Optimization Design of Airfoil Based on Neural Networks

针对气动外形优化设计中,气动特性计算可信度要求与巨大计算量之间的矛盾,采用一种基于神经网络构建适用于气动外形优化设计的气动特性计算模型的计算方法。同时,以神经网络近似模型来代替原有的流场数值计算气动分析程序,结合基于遗传算法建立的气动外形优化搜索方法,建立了一种新的翼型优化设计方法。实际翼型优化设计算例表明该方法有效减少了计算量,提高了工作效率,可以获得具有高可信度的设计结果。

During the process of aerodynamic optimization design, aerodynamic analysis usually requires a large number of evaluations for high fidelity. In this paper, to reduce the computational expense, a method that builds an aerodynamic analysis model based on neural networks is applied to aerodynamic shape optimization design. In addition, a new optimization design method is proposed here, which combines a genetic algorithm with a neural network model instead of primary CFD aerodynamic analysis. Practical airfoil optimization design results show that this method can achieve high- fidelity design results effectively as well as reduce the expensive computational cost to improve optimization efficiency.