基于遗传BP神经网络的超临界水自然循环稳态流量研究

Study on Supercritical Water Steady-state Mass Flow under Natural Circulation Based on Genetic Neural Network

利用遗传BP神经网络建立超临界水自然循环稳态流量预测模型,采用平均影响值(MIV)的概念进行参数敏感度分析。研究结果表明,遗传BP网络可以很好的预测超临界水自然循环稳态流量值,误差落在了±10%范围内。在所选的参数范围内,入口温度增大,稳态流量减小,提高试验段高度或减小加热段长度、出入口阻力系数可以使自然循环流量增加,其重要度排序为入口温度、试验段高度、入口阻力系数、出口阻力系数、加热段长度,且入口阻力系数、出口阻力系数、加热段长度影响基本对等。

The genetic neural network is established to predict supercritical water steady- state mass flow under natural circulation and the method of mean impact value is used to analyze the sensitivity of parameters. The results show that the predictive values of GNN agree well with the actual values. The errors fall in the limits of ± 10%. Within the parameter range, the steady-state mass flow decreases rapidly with inlet temperature increase. The steady-state mass flow increases with test section height increase or heating zone length, inlet and outlet resistance coefficient decrease. The magnitude sequence of above factors is confirmed as inlet temperature, test section height, inlet resistance coefficient, outlet resistance coefficient and heating zone length. The influence is basic equivalence among inlet resistance coefficient, outlet resistance coefficient and heating zone length.