论文部分内容阅读
利用遗传神经网络(GNN)方法分析窄矩形通道内流动不稳定起始点(OFI),并检测其热流密度随各个系统参数的变化。检测结果显示,GNN的预测结果与实验值符合良好,误差在±10%范围内。进一步通过GNN模型预测各个系统参数对OFI的影响。结果显示:OFI点的热流密度随着系统压力、入口过冷度、质量流速的增加而增大;系统压力对OFI点热流密度的影响小于质量流速的影响,小于入口过冷度的影响。
OFN was analyzed by genetic neural network (GNN) method and the change of heat flux density with each system parameter was analyzed. The test results show that the predicted GNN results are in good agreement with the experimental data and the error is within ± 10%. The GNN model is further used to predict the impact of various system parameters on OFI. The results show that the heat flux density at OFI increases with the increase of system pressure, inlet undercooling and mass flow rate. The effect of system pressure on the heat flux density at OFI is less than that of mass flow rate and less than the effect of inlet undercooling.