[1]卢 梅,韩小康,孔祥坤,等.基于BP神经网络和TOC的工程造价预控研究[J].西安建筑科技大学学报:自然科学版,2011,43(01):106-112.[doi:DOI:10.15986/j.1006-7930.2011.01.026]
 ,,et al.Research of construction cost forecasting and control basedon BP neural network and theory of constraint[J].J.Xi’an Univ. of Arch. & Tech.:Natural Science Edition,2011,43(01):106-112.[doi:DOI:10.15986/j.1006-7930.2011.01.026]
点击复制

基于BP神经网络和TOC的工程造价预控研究()
分享到:

西安建筑科技大学学报:自然科学版[ISSN:1006-7930/CN:61-1295/TU]

卷:
43
期数:
2011年01期
页码:
106-112
栏目:
出版日期:
2011-02-28

文章信息/Info

Title:
Research of construction cost forecasting and control based
on BP neural network and theory of constraint
文章编号:
1006-7930(2011)01-0106-07
作者:
卢 梅1韩小康1孔祥坤2蔡静3
(1.西安建筑科技大学管理学院,陕西 西安 710055,2. 武警陕西消防总队,陕西 西安 710016,3. 日照市规划设计研究院,山东 日照276826)
Author(s):
LU Mei1HAN Xiao-kang1KONG Xiang-kun2CAI Jing3
(1.School of Management,Xi′an University of Architecture and Technology,Xi′an 710055,China;
2.Shaanxi Fire Unit of Armed Police,Xi′an 710016,China;3.Rizhao Guihua Sheji Yanjiuyuan,Rizhao 276826,China)
关键词:
工程造价BP神经网络TOC
Keywords:
construction cost BP neural network theory of constraint
分类号:
TU723.3
DOI:
DOI:10.15986/j.1006-7930.2011.01.026
文献标志码:
A
摘要:
为了有效控制工程造价,使建设投资确定,本文运用BP神经网络对工程造价进行预测,以预测结果对工程量清单计价模式进行优化,再以优化的工程量清单计价模式为计价依据,通过TOC理论对工程造价进行控制。以六条高速公路为样本数据,其中一条为检测数据,运用BP神经网络仿真,建立仿真模型。通过十三次迭代,模型顺利拟合,并且代人样本检测数据的输出结果与实际吻合。再以检测数据的输出结果为依据对这条高速公路进行TOC理论优化,最终相比优化前工程决算总额减少了2072.6万元,降低了1%。
Abstract:
To control construction cost effectively so that the investment of construction company is to ensure can be engured,
this paper applies BP neural network to forecast the construction cost,and uses the outcome of the forecast to optimize
 the bill of quantities(BOQ)again.It then takes advantage of the theory of constraint to control the construction
cost based upon the optimized the BOQ at last.With a sample of data from six highways,including a testing data,using
BP neural network simulation,simulation model is built.Through 13iterations,the model fit well,and the outputs of test
data proved to be consistent with the actual.Then by using TOC to optimize based on the output,the optimized final account
 of the project represents a reduction of 20.726million yuan,lower by 1%as compared with the previous final account.

参考文献/References:

references
[1] 深圳市中哲投资顾问有限公司.2010-2015年中国建筑业投资分析及前景预测报告[R].深圳:中投顾问产业研究
中心,2009.
Shenzhen Zhongzhe Investment Advisory Co.,Ltd.Investment analysis and forecast report on Chinas construction
industry 2010-2015[R].Shenzhen:Investment Adviser Industry Research Center,2009.
[2] 朱 凯,王正林.精通MATLAB神经网络[M].北京:电子工业出版社,2010:193-198.
ZHU Kai,WANG Zheng-lin.Proficient in MATLAB Neural Network[M].Beijing:Publishing House of Electronics
Industry,2010:193-198.
[3] GOLDRATT EM.It’s Not Luck[M].Great Barrington:The North River Press,1997.
[4] GOLDRATT EM.Critical Chain[M].Great Barrington:The North River Press,1997.
[5] 艾利·高德拉特.关键链[M].北京:电子工业出版社,2006.
GOLDRATT E M.Critical Chain[M].Beijing:Publishing House of Electronics Industry,2006.
[6] 韩小康,卢 梅.基于关键链的工程造价控制研究[J].建筑经济,2009(12):103-105.
HAN Xiao-kang,LU Mei.Research of construction cost control based upon critical chain method[J].Construction
Economy,2009(12):103-105.
[7] 全国造价工程师执业资格考试培训教材编审委员会.工程造价计价与控制[M].北京:中国计划出版社,2009:205.
Training Materials Qualification Examination Editorial Board of National Construction Cost Engineer.Pricing and
Control of Construction Cost[M]:Beijing:China Planning Press,2009:205.
[8] 朱大奇,史 慧.人工神经网络原理及应用[M].北京:科技出版社,2006:43.
ZHU Da-qi,SI Hui.Principle and Application of Artificial Neural Networks[M].Beijing:Science and Technology
Press,2006:43.

相似文献/References:

[1]崔凤坤,杜岳涛,徐 岳,等.基于混合算法的大跨度钢管混凝土拱桥正常使用可靠度评估[J].西安建筑科技大学学报:自然科学版,2016,48(06):874.[doi:10.15986/j.1006-7930.2016.06.016]
 CUI Fengkun,DU Yuetao,XU Yue,et al.Reliability evaluation for long-span CFST arch bridges at serviceability limit states based on hybrid algorithm[J].J.Xi’an Univ. of Arch. & Tech.:Natural Science Edition,2016,48(01):874.[doi:10.15986/j.1006-7930.2016.06.016]
[2]韦海民,苏桐.地下综合管廊PPP项目模式选择研究[J].西安建筑科技大学学报:自然科学版,2018,50(01):126.[doi:10.15986/j.1006-7930.2018.01.020]
 WEI HaiminSU Tong.Research on mode selection of utility tunnel PPP project[J].J.Xi’an Univ. of Arch. & Tech.:Natural Science Edition,2018,50(01):126.[doi:10.15986/j.1006-7930.2018.01.020]
[3]段瑞芳,冉 衠,王旭东,等.考虑施工不确定性的斜拉桥张拉方案优化[J].西安建筑科技大学学报:自然科学版,2019,51(01):59.[doi:10.15986/j.1006-7930.2019.01.010]
 DUAN Ruifang,RAN Zhun,WANG Xudong,et al.Study of the backfill effect on tunnel lining segments property[J].J.Xi’an Univ. of Arch. & Tech.:Natural Science Edition,2019,51(01):59.[doi:10.15986/j.1006-7930.2019.01.010]
[4]卢梅,杨佳兴,张喜临.基于BP神经网络及熵权灰靶法的分包商选择研究[J].西安建筑科技大学学报:自然科学版,2019,51(03):447.[doi:10.15986/j.1006-7930.2019.03.021]
 LU Mei,YANG Jiaxing,ZHANG Xilin.Research on subcontractor selection based on BP neural network and entropy grey target method[J].J.Xi’an Univ. of Arch. & Tech.:Natural Science Edition,2019,51(01):447.[doi:10.15986/j.1006-7930.2019.03.021]

备注/Memo

备注/Memo:
收稿日期: 修改稿日期:基金项目:陕西省“13115”科技创新工程重大科技项目(2009ZDKG-66);陕西省重点学科建设专项资金资助项目(1971—),女,新疆乌鲁木齐人,博士,,副教授,主要从事工程项目管理、结构工程;BP神经网络又称为误差反向传播(Back Propagation)神经网络,它是一种多层的前向型神经网络。在BP网络中,信号是前向传播的,而误差是反向传播的。BP网络通常具有一个或多个sigmoid隐层和线性输出层,能够对具有有限个不连续点的函数进行逼进。所谓的反向传播是指误差的调整过程是从最后的输出层依次向之前各层逐渐进行的。标准的BP网络采用梯度下降算法,网络权值沿着性能函数的梯度反向调整[2]。BP神经网络的结构见图1所示,P、A是网络的输入、输出向量,每一个神经元用一个节点表示,网络由输入层、隐层和输入层节点组成,隐层可以是一层,也可以是多层(图1是单隐层),前层至后层节点通过权联接。图1 BP神经网络
更新日期/Last Update: 2015-11-01