基于神经网络的公路工程造价预测模型  

Based on the model of BP neural network to predict the project cost of highway

作　　者：王飞[1] 郑张丽 郭静静[1] 尹建英 

机构地区：[1]河北工程大学经济管理学院,河北邯郸056038 [2]邯郸市城市建设投资公司,河北邯郸056002

出　　处：《河北工程大学学报（自然科学版）》2014年第4期102-104,共3页Journal of Hebei University of Engineering:Natural Science Edition

摘　　要：文章对高速公路的工程特征进行全面的分析和筛选,确定了7个对公路工程造价影响较大的工程特征,使其作为神经网络预测模型的输入向量,随之构建了基于BP神经网络的高速公路工程造价预测模型,最后结合MATLAB神经网络工具箱对程序进行设计,并选取已完工程为实例。通过对模型的训练、修正以及实例验证,证明BP神经网络可以有效提高预测的精确度,具有较强的实用价值。Based on the principle of BP neural network in and on the analysis of the characteristics of highway engineering, this paper identified seven engineering characteristics as the input vector of the neural network, build the highway engineering cost prediction model is based on BP neural network, combined with MATLAB neural network toolbox to design, and has the engineering as an example. By training, correction, and to verify the model, it is proven that BP neural network can effectively improve the accuracy of the prediction, has very good practical value.

关 键 词：公路工程 BP神经网络 造价预测 

分 类 号：TU984.2[建筑科学—城市规划与设计]