期刊文献+

基于SPSS与BP网络的锌产量预测模型 被引量:1

SPSS and BP Artificial Neural Network and Its Application in Zinc Output forecast
下载PDF
导出
摘要 金属锌对人们的生活具有非常重要的意义,为了使锌产量最大化,有必要对密闭鼓风炉铅锌熔炼操作参数进行优化,提出了基于SPSS与BP网络的密闭鼓风炉熔炼锌产量的预测模型;先对DCS系统上获得的在线数据建立初步的参变量与锌产量之间的因果关系,再利用SPSS统计分析软件中的主成分分析法对各参变量进行分析,最后将得到的与锌产量最相关的少数几个因素用BP网络建立预测模型,仿真结果表明,该方法减少了网络的训练时间,改善了学习效率,具有较高的预测精度,是可行的、有效的。 The metal zinc has very important significance to people's life , In order to maximize zinc output, It is necessary to optimize the parameters of the Imperial Smelting Furnace smelting zinc output , suggesting a zinc output forecasting model of Imperial Smelting Furnace based on SPSS and the BP network. At the first, set up a relationship between datas getting from DCS system and Zinc output, Second, make use of Principal Component Analysis in SPSS statistic analysis software to follow the analysis being in progress to every variable parameter and so get some variable parameters with Zinc output, At the last , set up a a zinc output forecasting model with that variable parameters based on BP network, that method has decreased by network training time , has improved the efficiency studying, has higher forecast accuracy , is feasible, effective.
出处 《计算机测量与控制》 CSCD 2008年第8期1116-1118,共3页 Computer Measurement &Control
基金 国家自然科学基金项目(60574030)
关键词 SPSS 主成分分析 BP网络 密闭鼓风炉 锌产量预测 SPSS principal component analysis BP network imperial smelting furnace zinc output forecasting model
  • 相关文献

参考文献4

二级参考文献15

  • 1丁云飞,许维东,潘峰.密闭鼓风炉的混合故障诊断方法[J].计算机工程与设计,2004,25(11):1923-1926. 被引量:4
  • 2卢学强,梁雪慧,卢学军.神经网络方法及其在非线性时间序列预测中的应用[J].系统工程理论与实践,1997,17(6):97-99. 被引量:56
  • 3焦李成.神经网络系统导论[M].西安:西安电子科技大学出版社,1992..
  • 4Lera G,Pinzolas M. Neighborhood based Levenberg-Marquardt algorithm for neural network training [J]. IEEE Transactions on Neural Networks.2002,13(5): 1200-1203.
  • 5Srinivasan B,Prasad U R,Rao N J. Back propagation through adjoints for the identification of nonlinear dynamic systems using recurrent neural models [J]. IEEE Transactions on Neural Networks,1994,5 (2):213-228.
  • 6Huang Yunbing,Preprints of the 14th IFAC World Congress,1999年,545页
  • 7Dunia R,AIChE J,1998年,44卷,8期,1813页
  • 8孙文爽,多元统计分析,1994年
  • 9闻新 周露.MATLAB神经网络应用设计[M].北京:科学出版社,2001..
  • 10Christopher J.C. Burges.A Tutorial on Support Vector Machines for Pattern Recognition[J].Data Mining and Knowledge Discovery.1998(2)

共引文献133

同被引文献12

  • 1郑小霞,钱锋.基于PCA和最小二乘支持向量机的软测量建模[J].系统仿真学报,2006,18(3):739-741. 被引量:33
  • 2Wang M H,Wang L K.Mathematical modeling of electrical energy consumption and heating requirements by municipal wamewater treatment plants[J].Journal of Environmental Scierlces,1979,24:23-26.
  • 3Olason G,Andrews J F.Dissolved oxygen control in theactivated sludge process[J].War.Sci.Tech.,1981,13(10):341-347.
  • 4Charpentier J,Florentz M,David G.Oxidation-reduction potential(ORP)regulation:a way to optimize pollution removal and energy savings in the low load activated sludge process[J].War.Sci.Tech.,1987,19:645-655.
  • 5Charpentier J,Godarth,Martin G,et al.Oxidation-reduction potential(ORP)resqdation as a way to optimize aeration and C,N and P removal:experimental basis and various fullscale examples[J].Wat.Sci.Tech.,1989,21:1209-1223.
  • 6Fetter J,Rodrigo M A,Seco A,et al.Energy saving in the aeration process by fuzzy bsic control[J].War.Sci.Technol.,1998,38(3):209-217.
  • 7Bongards M,Ebel A,Hilmer T.Predictivc control of wastewater works by neural networks[C]//Soft.Comp.Ind.Appl.Proc.Biannual World Autom.Cong.Sevilla,Spain:[s.n.],2004:397-102.
  • 8Yin P Y,Chen L H.A new non itemtive approach for clustering[J].Pattern Recognition Letters,1994,15(2):125-133.
  • 9丁晓贵,刘桂江.基于PIDNN的污水处理系统参数辨识研究[J].计算机技术与发展,2008,18(5):200-202. 被引量:1
  • 10贾群.PCA-BP算法模块化设计的编程实现[J].计算机技术与发展,2008,18(12):98-101. 被引量:3

引证文献1

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部