高铁工程全生命成本智能预测模型与实证研究  

Intelligent Prediction Model and Empirical Study on Life-circle Cost for High-speed Railway Project

作　　者：喇海霞 段晓晨[1] 牛衍亮[1] La Haixia;Duan Xiaochen;Niu Yanliang(School of Economics and Management,Shijiazhuang Tiedao University,Shijiazhuang 050000,China)

机构地区：[1]石家庄铁道大学管理学院,河北石家庄050000

出　　处：《科技管理研究》2023年第7期213-220,共8页Science and Technology Management Research

基　　金：国家自然科学基金项目“国际高铁联营体竞合机理与策略研究”(72071133);河北省自然科学基金项目“高铁投资与运营收入三维非线性智能估算方法研究”(G2019210226)。

摘　　要：为提高高铁工程成本估算的准确性,简化高铁工程成本估算程序,提出基于显著性成本理论的高铁工程全生命成本智能预测模型。首先,结合已完同类工程量清单,运用显著性成本理论,确定同类工程显著性成本项目与显著性因子;其次,运用余弦相似度法,结合已完工程与拟建工程的工程特征数据,完成相似工程的筛选;再次,结合相似工程数量的多少,分别选用基于PSO-RBF、PSO-LSSVM、FCM聚类、FIS的模糊推理预测模型进行高铁工程全生命成本预测;最后,通过实例验证该模型的准确性与可行性。研究结果表明,该模型的运用确保了估算的精度,并提高了高铁工程成本估算效率。In order to improve the accuracy of the cost estimation of high-speed railway engineering and simplify the cost estimation procedure of high-speed railway engineering,proposes an intelligent prediction model of the whole life cost of high-speed railway engineering based on the significance cost theory.Firstly,determine the CSIs and csf of similar projects by using the significance cost theory combined with the completed list of similar projects.Secondly,select similar projects combined with the characteristics of completed projects and planned projects by Cosine Similarity.Then,forecast the whole life cost of high-speed railway projects by selecting different estimation models based on PSO-RBF,PSO-LSSVM,FCM clustering and FIS,combined with the number of similar projects.Finally,verify the accuracy and feasibility of the model by an example.The results show that the prediction model ensures the accuracy of estimation and improves the efficiency of cost estimation of high-speed railway engineering.

关 键 词：显著性成本理论 高铁工程 RBF神经网络 最小二乘向量机 模糊推理 

分 类 号：F52[经济管理—产业经济] O242[理学—计算数学] TB11[理学—数学] O_(2)9[理学—应用数学]