RS-IPSO-BPNN模型在建筑工程估价中的应用  

Application of RS-IPSO-BP Neural Network model for construction engineering cost evaluation

作　　者：莫连光[1,2] 洪源[2] 

机构地区：[1]湖南城市学院城市管理学院,湖南益阳413000 [2]湖南大学经贸学院,长沙410079

出　　处：《计算机工程与应用》2013年第21期19-23,共5页Computer Engineering and Applications

基　　金：国家自然科学基金青年基金项目(No.71103060);湖南省科技厅科技项目(No.2012GK3068);湖南省社科基金项目(No.11JD10)

摘　　要：针对一般建筑工程估价问题的复杂性,融合粗糙集理论、粒子群算法和神经网络算法的优势,提出了一种新的建筑工程估价模型——基于粗糙集理论、改进粒子群算法和神经网络算法集成的建筑工程估价模型。利用粗糙集理论对影响建筑工程造价的因素进行约简,优化BP神经网络的输入变量;利用一种带收缩因子的改进粒子群算法优化BP神经网络初始权重和阈值。该方法有效地增强了BP算法对非线性问题的处理能力,同时提高了BP算法的收敛速度和搜索全局最优值的能力。选取湖南某市工程案例进行实证分析。研究结果表明,新的算法模型能够以工程特征为依托,科学客观地评估建筑工程造价,具有较高的实际应用价值。Aiming at coping with the complexity of construction engineering cost evaluation, the advantages of rough set theory, particle swarm algorithm and BP neural network are integrated to put forward a new model of construction engineering cost eval- uation, namely, the model of construction engineering cost evaluation of optimized particle swarm and BP neural network on the basis of rough set theory. Rough set theory is used to reduce the factors affecting construction engineering cost and optimize input variables of BP neural network. The improved particle swarm algorithm with constriction factors is adopted to optimize the initial weights and thresholds. Through this method, BP neural network can be used in a better way to solve nonlinear problems and to improve the rate of convergence and the ability to search global optimum. An engineering project in a city of Hunan is selected to make empirical analysis. It shows that based on the features of engineering, this new model enjoys a high practical value as it can be applied to making scientific evaluation of costs of construction engineering.

关 键 词：估价 粗糙集 粒子群算法 神经网络 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]