基于BP神经网络的民用建筑工程造价估算方法研究

Research on Civil Construction Project Cost Estimation Method Based on BP Neural Network

分析影响民用建筑工程造价的主要因素并提取相应的工程特征指标;采用系统聚类的方法,选择待估算工程的有效样本类,确定最佳样本数量。将上述提取的工程特征值作为输入值,以工程造价作为输出值,建立建筑工程造价的BP神经网络估算模型。最后通过实例验证,预测精度符合决策阶段的要求,证明该模型确实可行。

This paper analyzes the main factors that influence the civil construction project cost,extracts the corresponding engineering characteristic indexes. Then,applies the system clustering method to divide the samples into categories and select those which contain the project to be estimate,determines the optimal number of samples. The paper builds the civil construction project cost estimation model based on BP neural network by taking the value of extracted characteristics as input and value of the project cost as output respectively. Finally,uses an instance to verify that the model meets the requirements of the decision-making stage.