摘要
在准三维设计基础上,采用多目标优化设计方法,给出一个多级涡轮气动优化设计流程,优化联合采用人工神经网络和遗传算法,流场计算采用全三维粘性流N-S方程求解。此优化设计流程有三个特点:针对每列叶栅的气动特性进行局部优化;各列叶栅反复多次优化;粗细网格交替使用。并采用此设计流程对一三级涡轮进行优化设计,效率提高1%,说明此方法可以有效的用于多级涡轮气动优化设计。
Based on the result of quasi-3D design, applying multi - objective aerodynamic optimization design method, an aerodynamic optimization design process of multistage axial turbine is presented. Genetic algorithm and artificial neural network are jointly adopted during optimization. Three-dimensional viscosity Navier-Stokes equation solver was applied. The optimization process has three features： local optimization based on aerodynamic performance of every cascade; several optimizations being performed to every cascade; and alternative use of coarse grid and fine grid. Such process is applied to optimize a three-stage axial turbine. The results show that the total efficiency increases 1%. This indicates that such method may be efficiently applied to the aerodynamic design optimization of multistage axial turbine.
出处
《推进技术》
EI
CAS
CSCD
北大核心
2007年第2期176-180,共5页
Journal of Propulsion Technology
关键词
涡轮
设计流程
多目标优化^+
遗传算法^+
人工神经网络^+
Turbine
Design process
Multi-objective optimization^＋
Genetic algorithm ^＋
Artificial neural network^＋
