人工神经网络在预测流动沸腾曲线中的应用

Prediction of Flow Boiling Curves Based on Artificial Neural Network

选用20世纪60年代以来的实验数据,应用人工神经网络分析入口欠热度、质量流速、压力等主要参数对沸腾曲线的影响。在整个传热区内,热流密度随入口欠热度的增加而增大;在过渡沸腾和膜态沸腾区,热流密度随质量流速的增加而增加;压力起重要的作用,除膜态沸腾区外,增加压力能强化传热。除泡核沸腾外,稳态和瞬态的流动沸腾曲线的差异很小。

The effects of the main system parameters on lyzed by using an artificial neural network（ANN） based flow boiling curves were anaon the database selected from the 1960s. The input parameters of the ANN are system pressure, mass flow rate, inlet subcooling, wall superheat and steady/transition boiling, and the output parameter is heat flux. The results obtained by the ANN show that the heat flux increases with increasing inlet sub cooling for all heat transfer modes. Mass flow rate has no significant effects on nucleate boiling curves. The transition boiling and film boiling heat fluxes will increase with an increase of mass flow rate. The pressure plays a predominant role and improves heat transfer in whole boiling regions except film boiling. There are slight differences between the steady and the transient boiling curves in all boiling regions except the nucleate one.