基于BP神经网络的盐胀量的预测方法

为了研究盐胀量与含水量、含盐量、干密度以及上覆荷载之间的关系,自主设计了硫酸盐渍土的定量增湿盐胀试验,并在试验结果的基础上采用BP神经网络对盐胀量进行了预测。经验证发现:采用BP神经网络对不同含水量、含盐量、干密度和上覆荷载等级条件下盐胀量的预测值和试验实测值有较高的拟合度。证明了运用BP神经网络对盐胀量进行预测这一方法是可行的,从而为盐胀量的预测提供了一个新的研究思路和方法。

The prediction of salt expansion based on BP neural network

In order to study the relationship between the salt expansion amount and moisture content ,salt content ,dry density ,the overlying load, we design the sulfate saline soil salt expansion test quantitative humidifying independently and make use of the BP neural network to forecast the amount of salt expansion on the basis of the experimental results .We found that the prediction value that the adaption of BP neural network to different moisture content, salt content, dry density and overlying load level condition is near to the actual value. We prove that it is feasible to use the BP neural network to predict the amount of salt expansion, which offers a new idea to predict salt expansion.