摘要
结冰会改变船用燃气轮机进气部件的气动特性,影响压气机工作效率。本文对船用燃气轮机进口导叶及导流罩进行二维结冰计算,以BP神经网络为基础,对船用燃气轮机进口导流罩的结冰临界温度进行预测。结果表明:结冰参数会影响部件表面冰形和结冰种类,从而影响部件的气动特性;特定条件下,当环境温度高于冰点时,进气部件表面也会发生结冰现象;明冰不仅会影响进气部件的气动特性,还存在冰层脱落的危险;结合BP神经网络可以形成一套具有适用范围的船用燃气轮机进口导流罩结冰临界温度预测代码。
The aerodynamic characteristics of the intake components of marine gas turbine would be changed by icing,which will affect working efficiency of the compressor.In this paper,two-dimensional icing of inlet guide vane and center deflector of marine gas turbine is calculated,and then the icing critical temperature of the center deflector of marine gas turbine is predicted based on the BP neural network.The results show that the icing parameters will influence the icing shape and icing species on the surface of component,and thereby influence the aerodynamic characteristics of the component.Under certain conditions,when the ambient temperature is higher than the freezing temperature,icing will also occur on the surface of intake components.Glaze ice will not only affect the aerodynamic characteristics of intake components,but also cause the risk of ice falling off.Combined with BP neural network,a set of applicable prediction codes for critical icing temperature of the center deflector of marine gas turbine can be formed.
作者
任永鹏
万雷
王萌
王忠义
曲永磊
REN Yongpeng;WAN Lei;WANG Meng;WANG Zhongyi;QU Yonglei(College of Power and Energy Engineering,Harbin Engineering University,Harbin 150001,China)
出处
《哈尔滨工程大学学报》
EI
CAS
CSCD
北大核心
2023年第2期235-243,共9页
Journal of Harbin Engineering University
基金
国家科技重大专项(J2019-Ⅲ-0017)。
关键词
船用燃气轮机
二维结冰
叶型
导流罩
数值模拟
欧拉法
FENSAP-ICE
临界温度
BP神经网络
marine gas turbine
two-dimensional icing
blade profile
center deflector
numerical simulation
Euler method
FENSAP-ICE
critical temperature
BP neural network