基于CS理论和BP神经网络理论的工程造价估算研究

Study on engineering cost estimation based on cost-significant theory and BP neural network theory

在借鉴国内外相关理论和方法的基础上,利用显著性成本理论和神经网络理论相结合对工程项目的投资进行估算.运用显著性成本理论,通过寻找显著性项目,简化工程造价估算的操作难度,从而解决操作烦琐的问题;并依据BP神经网络在大量已完工程资料中提取类似CSIs和显著性因子csf,从非线性角度实现了对项目投资的准确预测,并进行算例分析,从算例可以看到,预测值与实际值的相对误差很小,满足投资预测要求.

Based on the reference to Chinese and foreign correlative theories and methods,this paper advances the model of cost estimation based on cost-significant theory and neural network theory.The cost-significant theory is put forward to solve the tedious operation issues by finding out significant items to simplify the operation difficulty of engineering cost estimates;then the back-propagation neural network model is made up according to the BP algorithm to＂distill＂CSIs and csf（cost significant factor）from the data and information of completed projects,which provides a practical solution for those problems according to the nonlinear theory.The basic theories of BPNN and CS are introduced and their applications are illustrated with an example.For example,we can see that the relative errors are so small that they can meet the accuracy demand of cost estimations after simulation.The result shows that the model based on cost-significant theory and neural network theory is accurate and successful.