改进BP算法在公路工程主材价格预测中的应用研究
|
摘要
分析了传统BP算法的不足,利用相关分析法筛选出公路工程主材价格的主要影响因素;在确定BP神经网络结构及选取训练函数的基础上,建立了基于改进BP神经网络算法的公路工程主材价格预测模型,并结合合肥市石屑价格预测的实例,利用建立的预测模型,采用BP传统算法及附加动量法、自适应学习速率法、两者相结合法等3种改进算法分别预测了合肥市2个季度的石屑价格,并将预测结果进行对比,分析了不同BP算法预测结果之间的差异。结果表明,使用改进的BP神经网络算法进行公路工程主材价格预测,可以将预测误差控制在6%以内,并减少95%左右的训练步数。同时采用自适应学习速率和附加动量改进BP网络的方法相对最有效。
The prices of main materials for highway engineering are complicated variables which are affected by many factors.Application of improved BP algorithms in price prediction of highway engineering main materials was discussed.The specific methods are as follows: First,the shortcomings of traditional BP algorithm were pointed out and then its improved algorithms were put forward. Then,the main influencing factors of highway engineering main materials were screened out with correlation analysis method.On the basis of determining the structure of BP neural network and selecting training functions,a price forecasting model based on improved BP algorithms of highway engineering main materials was established.Finally,combining with the case of forecasting the prices of stone chips in Hefei,traditional and three improved BP algorithms were used and the forecasting results were analyzed.The results indicate that forecasting by applying improved BP neural network is feasible and effective.The forecasting errors can be reduced to less than 6% and training steps can be reduced by 95% percent using self-adaptive study speed algorithm and additional momentum algorithm simultaneity.
The prices of main materials for highway engineering are complicated variables which are affected by many factors.Application of improved BP algorithms in price prediction of highway engineering main materials was discussed.The specific methods are as follows: First,the shortcomings of traditional BP algorithm were pointed out and then its improved algorithms were put forward. Then,the main influencing factors of highway engineering main materials were screened out with correlation analysis method.On the basis of determining the structure of BP neural network and selecting training functions,a price forecasting model based on improved BP algorithms of highway engineering main materials was established.Finally,combining with the case of forecasting the prices of stone chips in Hefei,traditional and three improved BP algorithms were used and the forecasting results were analyzed.The results indicate that forecasting by applying improved BP neural network is feasible and effective.The forecasting errors can be reduced to less than 6% and training steps can be reduced by 95% percent using self-adaptive study speed algorithm and additional momentum algorithm simultaneity.
引文
[1]张海龙,黄鹏,田伟雄,等.基于人工神经网络和遗传算法的大跨连续梁桥参数相关分析[J].公路交通科技,2007,24(7):86-90.ZHANG Hai-long,HUANG Peng,TIAN Wei-xiong,et al.Analysis of Parameters for Long-span Continuous Bridges Basedon Neural Network and Genetic Algorithms[J].Journal ofHighway and Transportation Research and Development,2007,24(7):86-90.
[2]王云鹏,李世武,郭栋,等.基于BP神经网络的城市道路轻型车排放率模型[J].交通与计算机,2007,25(5):1-7.WANG Yun-peng,LI Shi-wu,GUO Dong,et al.VehicleEmission Rate Model of Urban Road Based on BP Neural Net-work[J].Computer and Communications,2007,25(5):1-7.
[3]温岩,乔兵,李忠伟.基于MATLAB工具箱的神经网络在地震预报中的应用[J].东北地震研究,2001,17(3):36-41.WEN Yan,QIAO Bing,LI Zhong-wei.Application of NervalNetwork Based on MATLAB Toolbox to Earthquake Prediction[J].Seismological Research of Northeast China,2001,17(3):36-41.
[4]马成前,任桂山.基于神经网络的城市公路隧道交通智能监控[J].计算机与现代化,2007,23(9):83-85.MA Cheng-qian,REN Gui-shan.Intelligent Control System forUrban Road Tunnel Based on Neural Network Model[J].Computer and Modernization,2007,23(9):83-85.
[5]马宁,马光,李长明.BP网络局部极小值的修正算法[J].北华航天工业学院学报,2007,17(5):24-27.MA Ning,MA Guang,LI Chang-ming.Implementation of Modifi-cation Algorithm for BP Network Local Minima[J].Journal ofNorth China Institute of Aerospace Engineering,2007,17(5):24-27.
[6]贺晓琴,陈峻,卞华.BP神经网络在航道网总运量预测中的应用[J].水运管理,2006,28(8):16-21.HE Xiao-qin,CHEN Jun,BIAN Hua.Application of BP Neu-ral Network in forecasting Waterway Net Freight[J].Shipp-ing Management,2006,28(8):16-21.
[7]任其亮,李顺勇.基于BP神经网络的建设项目交通影响度的敏感性分析方法研究[J].公路交通科技,2006,23(9):98-103.REN Qi-liang,LI Shun-yong.Research on Sensitivity AnalysisMethod for Traffic Impact of Construction Projects on TransportNetwork Based on BP Neural Network[J].Journal of High-way and Transportation Research and Development,2006,23(9):98-103.
[8]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005.ZHOU Kai-li,KANG Yao-hong.The Model of Neural Networkand Its MATLAB Simulation Program Design[J].Beijing:Tsinghua Publishing House,2005.
[9]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2005.Fecit Technology Development Center.The Theory of NeuralNetwork and Its MATLAB7 Implementing[M].Beijing:Chi-na Electronic Industry Publishing House,2005.
[10]苏变萍,金维兴.改进BP神经网络及其在西北建筑业预测中的应用[J].建筑经济,2006,27(12):26-29.SU Bian-ping,YU Wei-xing.Improvement of BP Neural Net-work and Application in Predicting Northwest Construction In-dustry[J].Construction Economy,2006,27(12):26-29.
[11]李海峰,王炜.基于神经网络的交通方式选择模型[J].公路交通科技,2007,24(7):132-136.LI Hai-feng,WANG Wei.The Option Model of Traffic ModeBased on Neural Network[J].Journal of Highway and Trans-portation Research and Development,2007,24(7):132-136.
[12]于英,王麒麟,田晋跃.高速公路养护成本预测模型[J].交通运输工程学报,2007,7(3):76-85.YU Ying,WANG Qi-lin,TIAN Jin-yu.Forecast Model of Ex-pressway Maintenance Cost[J].Journal of Traffic and Trans-portation Engineering,2007,7(3):76-85.
[2]王云鹏,李世武,郭栋,等.基于BP神经网络的城市道路轻型车排放率模型[J].交通与计算机,2007,25(5):1-7.WANG Yun-peng,LI Shi-wu,GUO Dong,et al.VehicleEmission Rate Model of Urban Road Based on BP Neural Net-work[J].Computer and Communications,2007,25(5):1-7.
[3]温岩,乔兵,李忠伟.基于MATLAB工具箱的神经网络在地震预报中的应用[J].东北地震研究,2001,17(3):36-41.WEN Yan,QIAO Bing,LI Zhong-wei.Application of NervalNetwork Based on MATLAB Toolbox to Earthquake Prediction[J].Seismological Research of Northeast China,2001,17(3):36-41.
[4]马成前,任桂山.基于神经网络的城市公路隧道交通智能监控[J].计算机与现代化,2007,23(9):83-85.MA Cheng-qian,REN Gui-shan.Intelligent Control System forUrban Road Tunnel Based on Neural Network Model[J].Computer and Modernization,2007,23(9):83-85.
[5]马宁,马光,李长明.BP网络局部极小值的修正算法[J].北华航天工业学院学报,2007,17(5):24-27.MA Ning,MA Guang,LI Chang-ming.Implementation of Modifi-cation Algorithm for BP Network Local Minima[J].Journal ofNorth China Institute of Aerospace Engineering,2007,17(5):24-27.
[6]贺晓琴,陈峻,卞华.BP神经网络在航道网总运量预测中的应用[J].水运管理,2006,28(8):16-21.HE Xiao-qin,CHEN Jun,BIAN Hua.Application of BP Neu-ral Network in forecasting Waterway Net Freight[J].Shipp-ing Management,2006,28(8):16-21.
[7]任其亮,李顺勇.基于BP神经网络的建设项目交通影响度的敏感性分析方法研究[J].公路交通科技,2006,23(9):98-103.REN Qi-liang,LI Shun-yong.Research on Sensitivity AnalysisMethod for Traffic Impact of Construction Projects on TransportNetwork Based on BP Neural Network[J].Journal of High-way and Transportation Research and Development,2006,23(9):98-103.
[8]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005.ZHOU Kai-li,KANG Yao-hong.The Model of Neural Networkand Its MATLAB Simulation Program Design[J].Beijing:Tsinghua Publishing House,2005.
[9]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2005.Fecit Technology Development Center.The Theory of NeuralNetwork and Its MATLAB7 Implementing[M].Beijing:Chi-na Electronic Industry Publishing House,2005.
[10]苏变萍,金维兴.改进BP神经网络及其在西北建筑业预测中的应用[J].建筑经济,2006,27(12):26-29.SU Bian-ping,YU Wei-xing.Improvement of BP Neural Net-work and Application in Predicting Northwest Construction In-dustry[J].Construction Economy,2006,27(12):26-29.
[11]李海峰,王炜.基于神经网络的交通方式选择模型[J].公路交通科技,2007,24(7):132-136.LI Hai-feng,WANG Wei.The Option Model of Traffic ModeBased on Neural Network[J].Journal of Highway and Trans-portation Research and Development,2007,24(7):132-136.
[12]于英,王麒麟,田晋跃.高速公路养护成本预测模型[J].交通运输工程学报,2007,7(3):76-85.YU Ying,WANG Qi-lin,TIAN Jin-yu.Forecast Model of Ex-pressway Maintenance Cost[J].Journal of Traffic and Trans-portation Engineering,2007,7(3):76-85.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心