摘要
基于某地区输电线路的历史工程造价数据,应用相关分析和聚类分析以及支持向量机理论等数据挖掘技术对电力输电工程的建设造价估算进行研究,提出了一种新的输电线路造价估算的预测模型。首先借助SPSS15.0软件采用相关分析对指标属性进行优化精简,构建了输电线路造价估算的技术指标体系,然后通过聚类分析对输电线路历史工程造价数据进行数据清洗及预处理,最后采用了基于支持向量机的回归模型来构建输电工程造价估算的预测模型。通过应用MATLAB7.0软件对实际输电线路工程设计概算数据的仿真分析,证明了该模型的有效性和可行性。
Based on the historical cost data of power transmission projects in a certain zone, data mining technology, such as relative analysis, clustering analysis and support vector machine theory,is used for new cost estimation methods of power transmission projects. Firstly, with the software SPSS 15. 0 and the relative analysis, the index attributes is simplified and optimized. Then,the historical cost data is cleaned and pre-processed by the clustering analysis. At last, the regression model based on the support vector machine theory is used to establish the prediction model, for cost estimation power transmission projects. Simulation analysis of real power transmission projects with Matlab 7.0 shows that the proposed model is valid and feasible.
出处
《工业工程与管理》
北大核心
2009年第3期90-95,104,共7页
Industrial Engineering and Management
基金
国家电力公司科技项目资助(04207520070603)
关键词
数据挖掘
聚类分析
支持向量机
输电工程
造价估算
date mining
clustering analysis
support vector machine
power transmission projects
cost estimation
