基于BP人工神经网络的高速公路造价估算研究  

Research on Expressway Cost Estimation based on BP Artificial Neural Network

作　　者：张羽 ZHANG Yu(Shanxi Province Communications Planning Surveying and Designing Institute Co.Ltd.,Taiyuan 030032,China)

机构地区：[1]山西省交通规划勘察设计院有限公司,太原市030032

出　　处：《公路》2025年第1期336-339,共4页Highway

摘　　要：为了提高高速公路造价估算水平,先筛选出了影响高速公路造价的特征因素,从输入层、隐含层、输出层等方面建立了BP神经网络的框架结构,并阐述了其传递函数、权值、阈值确定方法。搜集了某地区多条高速公路项目的原始数据,并利用MATLAB软件开展归一化处理和网络训练。同时,对不同高速公路的造价预测误差进行分析,研究成果可用于指导高速公路前期造价估算。In order to improve the level of expressway cost estimation,in this paper,the characteristic factors that affect the expressway cost are firstly screened out,the framework structure of BP neural network is established from the input layer,hidden layer and output layer,and the determination methods of its transfer function,weight and threshold are expounded.The original data of several expressway projects in a certain area are collected,and MATLAB software is used to carry out normalization processing and network training.At the same time,the cost prediction error of different expressways is analyzed.The research results can be used to guide the cost estimation of expressways in early phase.

关 键 词：公路工程造价 造价估算 特征因素 BP神经网络 误差分析 

分 类 号：U415.13[交通运输工程—道路与铁道工程] U495