摘要
本文联合应用S2流面正问题计算和多级局部优化设计对某三级涡轮进行多级气动优化设计。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,计算网格采用H-O-H型网格,即入口段、出口段采用H型网格,叶片区域采用O型网格。通过优化,总效率提高1.1%,总体性能提高,达到设计要求。
A three-stage axial turbine was redesigned by jointly applying S2 flow surface direct problem calculation methods and multistage local optimization methods in this article. Genetic algorithm and artificial neural network were jointly adopted during optimization. Flow computation applied three-dimensional viscosity Navier-Stokes equation solver. Computation grid adopted H-O-H-topology grid, i.e. inlet segment and outlet segment adopt H-topology grid and stator zone and rotor zone adopt O-topology grid. Through optimization design, the total efficiency has increased 1.1%, thus indicating that the total performance is improved and the design object is achieved.
出处
《燃气涡轮试验与研究》
2007年第1期27-31,共5页
Gas Turbine Experiment and Research
关键词
涡轮
优化设计
S2流面正问题计算
遗传算法
人工神经网络
turbine
optimization design
S2 flow surface direct problem calculation
genetic algorithm
artificial neural network