基于BP神经网络数据挖掘方法的政府投资项目投资估算方法

政府项目投资失控问题业已引起社会广泛关注,而造价估算不准是其中主要原因之一。许多不确定因素影响着项目造价,并且这些影响因素与造价之间呈高度非线性关系,传统统计方法难以对新建项目造价进行准确估算。本文利用BP神经网络在已完工程资料中“提取”“规则”,实现了对项目造价的准确估算。本文对BP网络基本理论作了简介,并用举例说明BP网络预测工程造价的准确性。从例子可以看到,预测值与实际值的相对误差很小,足以满足造价估算的要求。

Estimating Primary Cost Based on Neural Network in Government-Invested Engineering Projects

Uncontrolled government investment attracts more and more public attention. The inaccuracy of cost estimation is one of main reasons that make investment of government out of control. Cost estimation is affected by many uncertain factors, and the relationship between them is nonlinear and traditional model is hard to solve it. Artificial neural network based on BP algorithm provides a practical solution for that problem and it is applied to determine cost estimation through "distilling" rules from the materials of completed projects. The basic theory of BP network is introduced and its application is illustrated with an example in this paper. From the example, we can see that the relative errors are small enough for accuracy demand of cost estimation after simulation, and test result show the model based on BP neural network is accurate and successful.