用神经网络法预测鼓泡塔内的气含率

Prediction of Gas Holdup in Bubble Columns Using Artificial Neural Network

在 2 0 0 0多组公开发表的鼓泡塔实验数据组成的数据库基础上 ,提出了一个预测鼓泡塔内气含率的关联式 ,介绍了一种新的神经网络回归方法。将该方法与受力分析结合起来得到 4个对鼓泡塔内气含率影响较大的无因次准数 。

On the basis of a large data bank consisting of more than 2000 experimental results published for bubble columns, a state of the art correlation for the prediction of gas holdup was proposed. A new method of neural network regression was introduced,and it was applied by combined with force analysis to identify four most expressive dimensionless groups. Assessment of the correlation was demonstrated.