摘要
已知的环控系统再循环风扇为小流量、高转速、小尺寸的轴流风机。通过改变机匣间距和叶片数得到不同的风机模型,利用ANSYS软件中的CFX模块,模拟了这些风机模型的性能曲线和全压效率曲线。风机的全压效率随机匣间距和叶片数是非线性变化的,仅由拟合函数方式产生的结果误差较大,不能满足设计要求。针对上述问题,采用BP神经网络和遗传算法,通过寻优计算得到风机全压效率最高时风机的叶片数和机匣间距。
The known recirculation fan in environmental control system is the axial flow fan with low flow,high speed and small size.By changing the shroud tip and leaf number,different fan models are got,and the performance curve and total pressure efficiency of the models are obtained by using the software of CFX in ANSYS.The fan total pressure efficiency changes nonlinear with shroud tip and leaf number,which cannot meet the design requirements.By using neural network and genetic algorithm,the best fan shroud tip and leaf number are found when the total pressure efficiency is highest.
出处
《风机技术》
2014年第5期38-43,共6页
Chinese Journal of Turbomachinery
关键词
轴流风机
机匣间距
叶片数
神经网络
遗传算法
axial flow fan
shroud tip
leaf number
BP neural network
genetic algorithm