摘要
提出了改进的BP神经网络模型 ,把它应用到软基高速公路的沉降预测中 ,提出了两种构造神经网络训练样本基本思路 ,并分别进行了计算和对比 ,指出了各自的优、缺点。结果表明改进的BP网络模型比较稳健、收敛快 ,而且根据时间与对应的沉降量形成的样本训练的网络预测出的沉降误差小、精度高。
The improvment of BP neural network model is brought forward and adopted to predict the settlement of expressway on soft ground.Two methods of forming the training samples are introduced,and their virtues and shortcomings are pointed out by calculations and analyses.It shows that the improved BP neural network model is steady and fast convergence.Furthe more,the network model trained by the samples from time versus according settlement has least error and more accurate.
出处
《低温建筑技术》
2004年第1期36-38,共3页
Low Temperature Architecture Technology
关键词
改进的BP网络模型
高速公路
沉降
预测
improved BP neural network
expressway
post-construction settlement
prediction
