摘要
针对路基沉降预测中信息的灰色性和数据的非线性性,提出用灰色神经网络预测路基沉降的新方法。以京沪高铁某段路基断面为例进行了预测研究,并与用GM(1,1)模型预测的结果进行了对比。研究结果表明:灰色神经网络预测比GM(1,1)模型预测误差小。
Aiming at the greyness of information and nonlinearity of data in forecasting for subgrade settlement,a new method to forecast subgrade settlement is proposed with grey-artificial neural network （ G-ANN）. Take the section of Bei- jing-Shanghai High Speed Railway as an example ,the forecasting subgrade settlement is obtained with G-ANN and compared it with GM （ 1,1 ） model. The results show that the errors of grey-artificial neural network forecasting model is smaller than that of GM （ 1,1 ） forecasting model.
出处
《建筑技术开发》
2011年第8期11-13,24,共4页
Building Technology Development
关键词
路基沉降
灰色神经网络
预测模型
GM(1
1)预测模型
BP神经网络预测模型
subgrade settlement
grey-artificial neural network
forecasting model
GM （ 1,1 ） forecasting model
BP neural net-work forecasting model
