考虑PCA-RBF的变压器标底预测模型研究
|
摘要
针对变压器制造企业投标报价缺乏科学理论指导,准确性低的问题,以准确预估下一批招标的标底价为目标,提出了结合主成分分析(PCA)与人工神经网络(ANN)的变压器标底预测模型-PCA-RBF标底预测模型。模型采用PCA对高维原始变量进行降维处理,提取主成分(PC)作为径向基函数神经网络(RBF)的输入。PCA算法降低了原始变量的维数,去除了各变量间的相关性,在简化ANN结构的同时,提高了预测模型的精度。仿真结果表明,PCA-RBF变压器标底预测模型具有较高的预测精度。
Aiming at the problem of transformer manufacturing enterprises bidding is lacking of scientific theoretical guidance and low accuracy,for accurately predicting the next batch of tender`s pre-tender estimate price,combining principal component analysis(PCA)and artificial neural network(ANN)of the transformer pre-tender estimateforecast model is proposedPCA-RBF pre-tender estimateforecast model. The model uses PCA to preprocess the original multidimensional input variables,and selects the principal component(PC)as the input of the radial basis function neural network(RBF).The PCA algorithm reduces the dimension of the original variables,removes the correlation among the variables,and improves the accuracy of the prediction model while simplifying the ANN structure. The simulation results show that PCA-RBF pre-tender estimateforecast model has higher prediction accuracy.
Aiming at the problem of transformer manufacturing enterprises bidding is lacking of scientific theoretical guidance and low accuracy,for accurately predicting the next batch of tender`s pre-tender estimate price,combining principal component analysis(PCA)and artificial neural network(ANN)of the transformer pre-tender estimateforecast model is proposedPCA-RBF pre-tender estimateforecast model. The model uses PCA to preprocess the original multidimensional input variables,and selects the principal component(PC)as the input of the radial basis function neural network(RBF).The PCA algorithm reduces the dimension of the original variables,removes the correlation among the variables,and improves the accuracy of the prediction model while simplifying the ANN structure. The simulation results show that PCA-RBF pre-tender estimateforecast model has higher prediction accuracy.
引文
[1]张美英,何杰.时间序列预测模型研究综述[J].数学的实践与认识,2011,41(18):189-195.(Zhang Mei-ying,He Jie.Summary on time series forecasting model[J].Mathematics in Practice and Theory,2011,41(18):189-195.)
[2]王祯显.模糊数学在土建工程中招标投标的应用[J].土木工程学报,1986(2):88-92.(Wang Zhen-xian.Application of fuzzy mathematical to bidding and tendering in civil and building construction[J].China Civil Engineering Journal,1986(2):88-92.)
[3]谢媛芳,申伟.灰色预测理论在工程标底中的应用[J].西安科技学院报,2004,24(3):297-300.(Xie Yuan-fang,Shen Wei.The application of gray prediction in engineering bidding price[J].Journal of Xi’an University of Science and Technology,2004,24(3):297-300.)
[4]黄敏,吴立,樊友川.基于博弈论在交通工程投标报价分析中的研究[J].公路工程,2016,41(1):183-187.(Huang Min,Wu Li,Fan You-chuan.Analysis of game theory in the traffic engineering bid quotation[J].Highway Engineering,2016,41(1):183-187.)
[5]国亮.改进多元线性回归模型在某油田产量预测中的应用[J].西安电子科技大学学报,2009,19(3):71-75.(Guo Liang.Application of improved multivariate linear regression to output prediction of an oilfield[J].Journal of Xidian University,2009,19(3):71-75.)
[6]熊志斌.ARIMA融合神经网络的人民币汇率预测模型研究[J].数量经济技术经济研究,2011(6):64-76.(Xion Zhi-bing.Research on RMB exchange rate forecasting model based on combining ARIMA with neural networks[J].The Journal of Quantitative&Technical Economics,2011(6):64-76.)
[7]卢强,陈来军,梅生伟.博弈论在电力系统中典型应用及若干展望[J].中国电机工程学报,2014,34(29):5009-5017.(Lu Qiang,Chen Lai-jun,Mei Sheng-wei.Typical applications and prospects of game theory in power system[J].Proceedings of the CSEE,2014,34(29):5009-5017.)
[8]尹光志,李铭辉,李文璞.基于改进BP神经网络的煤体瓦斯渗透率预测模型[J].煤炭学报,2013,38(7):1179-1184.(Yin Guang-zhi,Li Ming-hui,Li Wen-pu.Model of coal gas permeability prediction based on improved BP neural network[J].Journal of China Coal Society,2013,38(7):1179-1184.)
[9]张晓瑞,方创琳,王振波.基于RBF神经网络的城市建成区面积预测研究-兼与BP神经网络和线性回归对比分析[J].长江流域资源与环境,2013,22(6):691-697.(Zhang Xiao-rui,Fang Chuang-lin,Wang Zhen-bo.Prediction of urban built-up area based on rbf neural network-comparative analysis with bp neural network and regression[J].Resources and Environment in the Yangtze Basin,2013,22(6):691-697.)
[10]邓捷,陆百川,刘权富.基于RBF神经网络的交通生成预测模型[J].武汉理工大学学报,2014(1):43-47.(Deng Jie,Lu Bai-chuan,Liu Quan-fu.Forecasting model of trip generation based on RBF neural network[J].Journal of Wuhan University of Technology,2014(1):43-47.)
[2]王祯显.模糊数学在土建工程中招标投标的应用[J].土木工程学报,1986(2):88-92.(Wang Zhen-xian.Application of fuzzy mathematical to bidding and tendering in civil and building construction[J].China Civil Engineering Journal,1986(2):88-92.)
[3]谢媛芳,申伟.灰色预测理论在工程标底中的应用[J].西安科技学院报,2004,24(3):297-300.(Xie Yuan-fang,Shen Wei.The application of gray prediction in engineering bidding price[J].Journal of Xi’an University of Science and Technology,2004,24(3):297-300.)
[4]黄敏,吴立,樊友川.基于博弈论在交通工程投标报价分析中的研究[J].公路工程,2016,41(1):183-187.(Huang Min,Wu Li,Fan You-chuan.Analysis of game theory in the traffic engineering bid quotation[J].Highway Engineering,2016,41(1):183-187.)
[5]国亮.改进多元线性回归模型在某油田产量预测中的应用[J].西安电子科技大学学报,2009,19(3):71-75.(Guo Liang.Application of improved multivariate linear regression to output prediction of an oilfield[J].Journal of Xidian University,2009,19(3):71-75.)
[6]熊志斌.ARIMA融合神经网络的人民币汇率预测模型研究[J].数量经济技术经济研究,2011(6):64-76.(Xion Zhi-bing.Research on RMB exchange rate forecasting model based on combining ARIMA with neural networks[J].The Journal of Quantitative&Technical Economics,2011(6):64-76.)
[7]卢强,陈来军,梅生伟.博弈论在电力系统中典型应用及若干展望[J].中国电机工程学报,2014,34(29):5009-5017.(Lu Qiang,Chen Lai-jun,Mei Sheng-wei.Typical applications and prospects of game theory in power system[J].Proceedings of the CSEE,2014,34(29):5009-5017.)
[8]尹光志,李铭辉,李文璞.基于改进BP神经网络的煤体瓦斯渗透率预测模型[J].煤炭学报,2013,38(7):1179-1184.(Yin Guang-zhi,Li Ming-hui,Li Wen-pu.Model of coal gas permeability prediction based on improved BP neural network[J].Journal of China Coal Society,2013,38(7):1179-1184.)
[9]张晓瑞,方创琳,王振波.基于RBF神经网络的城市建成区面积预测研究-兼与BP神经网络和线性回归对比分析[J].长江流域资源与环境,2013,22(6):691-697.(Zhang Xiao-rui,Fang Chuang-lin,Wang Zhen-bo.Prediction of urban built-up area based on rbf neural network-comparative analysis with bp neural network and regression[J].Resources and Environment in the Yangtze Basin,2013,22(6):691-697.)
[10]邓捷,陆百川,刘权富.基于RBF神经网络的交通生成预测模型[J].武汉理工大学学报,2014(1):43-47.(Deng Jie,Lu Bai-chuan,Liu Quan-fu.Forecasting model of trip generation based on RBF neural network[J].Journal of Wuhan University of Technology,2014(1):43-47.)