高热流条件下过冷沸腾CHF试验及神经网络预测研究

Experimental Study on Critical Heat Flux for Subcooled Water Flow Boiling Under High Heat Fluxes and Predictions Based on Neural Network

本文试验研究了10~15 MW/m^(2)高热流条件下过冷水流动沸腾的临界热流密度(CHF),并聚焦其预测方法。分析了热力学干度、质量流速和压力等参数对过冷沸腾CHF的影响。结果表明,随着热力学干度的增加,CHF近似线性降低。CHF随着质量流速增加而增加,但当靠近饱和点时,增加趋势逐渐减弱。在本文试验数据的基础上,搜集了文献中公开的实验数据,构建了高热流过冷沸腾CHF数据集(共709组),采用经验关联式和神经网络模型两种方法进行了预测,并定量评估了7个经验关联式和3个神经网络模型(BP,GA-BP和MEA-BP)的预测性能。结果显示,神经网络算法的预测性能相较于传统关联式有显著提升,其中,MEA-BP神经网络的预测效果最优,其平均绝对误差为15.61%,均方根误差为21.56%。

The critical heat flux(CHF)for subcooled water flow boiling is experimental studied under high heat fluxes conditions(10~15 MW/m^(2)),and the prediction methods are focused on.The effects of thermodynamic vapor quality,mass flux and pressure on CHF of subcooled boiling are analyzed.It is found that an increase in thermodynamic quality decreases the CHF linearly.The CHF increases with the rise of mass flux;however,when thermodynamic quality approaches the saturation point,the trend gradually decreases.The subcooled boiling CHF data in open literatures are collected to form a dataset of subcooled boiling of high heat flux with the paper data,including 709 data sets.And the empirical correlations and neural network models are adopted to make prediction research,and the prediction performance of seven empirical correlations and three neural networks model(BP neural network,GA-BP neural network,MEA-BP neural network)were quantitively evaluated.The results indicate that the prediction performance of machine learning has improved significantly compared to traditional correlation,and the MEA-BP neural network has the best prediction performance,the Mean Absolute Error is 15.61%and the Root Mean Square Error is 21.56%。