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

摘要:

为了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，本文提出了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；然后，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。

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

Abstract:

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, this paper 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, intelligent 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 the prediction model ensures the accuracy of estimation and improves the efficiency of cost estimation of high-speed railway engineering.

Key words:cost significant ; high-speed railway; RBF;LSSVM;FIS