基于人工神经网络的某汽轮机高中压缸瞬态温度场分析

Artificial Neural Network-based Study of Transient Temperature Fieldsof a Steam Turbine High Pressure Cylinder

以某联合循环汽轮机高中压缸为对象,采用人工神经网络结合汽缸运行监控数据,反演求解了冷启动过程汽缸内壁对流换热系数。并以反演的热边界条件为基础,采用有限元软件ANSYS开展了高中压汽缸的瞬态温度场模拟,获得了冷启动过程汽缸温度场变化特征。通过汽缸壁测点温度模拟值与实测值进行比较,两者相对误差在8%以内,表明了基于人工神经网络反演求解汽缸内壁对流换热系数的可靠性。在汽缸温度场模拟基础上,还初步研究了冷启动过程高中压汽缸的等效热应力场。

In this paper,the transient heat transfer coefficient in the inner wall of the high pressure cylinder of a combined cycle turbine during cold start process was obtained by using the artificial neural network combined with the operation monitoring data.Based on the determined thermal boundary conditions,the simulation of the temperature field of the high pressure cylinder was carried out using FEM,and the characteristics of both the axial and radial temperature variations of the cylinder during the cold start process were investigated.It was shown that the relative error between the simulated temperature and the measured temperature is less than 8%in the inner wall of the cylinder,proving thereby that the inversion of the transient heat transfer coefficient based on the artificial neural network was reliable.On the basis of the calculated temperature field of the cylinder,the thermal stress field of the high pressure cylinder during the cold start process was also studied.