基于BP神经网络的帷幕注浆量预测模型研究

Research on Curtain Grouting Quantity Predition Model Based on the BP Neural Network

在帷幕注浆工程中,注浆量预测具有重要的实际应用价值。利用Matlab神经网络功能,通过编写预测注浆量的程序,建立了预测帷幕注浆量的BP神经网络模型,得出了注浆量与影响因子的非线性关系。结合工程实例,分别对注浆段和注浆孔进行了注浆量预测,并将注浆量预测值与实测值进行了比较分析。结果表明,在帷幕注浆工程中,BP神经网络模型对注浆量的预测误差较低,预测效果良好。

It has important practical application value to predict the grouting quantity during curtain grouting project. In this paper, the neural network function of MATLAB software is used to compile a program and to establish BP neural network prediction model of curtain grouting quantity, then the relationship between grouting quantity and influence factors is obtained. The grouting quantity of both grouting interval and the whole hole are also predicted, respectively. The results are analyzed and compared with the engineering example. It is shown that the prediction of curtain grouting quantity reaches the expected purpose by using the BP neural network.