人工神经网络在预测高速公路路基沉降中的应用  

Application of Artificial Neural Networks to Forecast of Subgrade Settlement of Expressways

作　　者：王琛艳[1] 郑治[2] 

机构地区：[1]重庆交通学院,重庆市400074 [2]重庆交通科研设计院,重庆市400067

出　　处：《公路交通技术》2004年第3期7-10,共4页Technology of Highway and Transport

基　　金：交通部西部交通建设科技项目 :高填方路堤沉降变形规律研究及压实技术研究

摘　　要：人工神经网络具有较强的自组织、自适应、容错性以及很强的学习、联想能力 ,本文将其应用到高速公路路基沉降预测中。重点介绍了ELMAN模型方法 ,本方法利用实测资料直接建模 ,避免了传统方法计算过程中的各种局限性 ,通过对高速公路路基实测沉降资料的计算分析 ,证明本模型预测精度高 ,简便易行 ,具有广泛的工程实用价值。Artificial neural network (ANN) has the advantages of self-organizing,adaptive identifying,self-studying and being tolerant towards errors. ANN is used in forecast of subgrade settlement of expressways in this paper. An ELMAN model is introduced here,which is directly established by using the measured data to avoid the limits of calculating in the traditional ways. Calculations and analyses of the measured data of subgrade settlement of expressways are carried out. The results show that the model can give a precise forecast and it is simple and easy for use and can be extensively applied in engineering.

关 键 词：人工神经网络 高速公路 路基沉降 沉降预测 BP网络学习算法 

分 类 号：U416.1[交通运输工程—道路与铁道工程]