基于BP和SVM变量筛选的LC技术特征对项目绩效比较研究

Research on GA-BP with SVM for Towards Coupling of Lean Construction Technology and Project Performance

摘要:

为探究精益建设技术与项目绩效之间的内在作用机理,构建了基于BP和SVM变量筛选的6S、可视化管理、最后计划者等7种精益建设技术与知识能力、财务、业主等5个项目绩效分项指标和综合指标的耦合模型。仿真结果表明：在精益建设技术特征与项目绩效分项指标的耦合模型仿真分析中,基于GA-BP的预测模型比标准BP神经网络模型精度要高；在精益建设技术特征与项目绩效综合指标的耦合模型仿真分析中,基于SVM的预测模型比GA-BP的预测模型精度要高。另外,利用BP和SVM结合MIV算法进一步探究了不同精益建设技术对项目绩效各指标和综合指标的影响程度。研究结果为项目利益相关者提高项目管理绩效提供决策支持。

Abstract:

as the internal mechanism between inquiry lean construction technology and project performance, constructs the screening of BP and SVM variables 6S, visual management, the last planner and other 7 kinds of lean construction technology and knowledge ability, financial, owners, based on the coupling model of 5 project performance index and comprehensive index. The simulation results show that: in the analysis of coupled model simulation technology characteristics of lean construction and project performance sub index, prediction model of GA-BP is higher than standard BP neural network model based on the analysis of precision; coupled model simulation comprehensive indicators of performance technology characteristics of lean construction and project, the predictive model of SVM is higher than the precision of forecasting model GA-BP based on. In addition, using the BP and SVM combined with MIV algorithm to further explore the influence of different lean construction techniques of each index and comprehensive index of project performance. Research results provide decision support for the project stakeholders to improve the performance of project management.