| 127 | 6 | 119 |
| 下载次数 | 被引频次 | 阅读次数 |
采用偏最小二乘法(PLS)和主成分分析法(PCA)对光谱数据进行主成分提取,并利用遗传算法(GA)对波长进行选择,剔除不相关的变量,达到压缩数据的目的;采用反向传播人工神经网络(BP-ANN)方法,对多组分体系进行定性定量分析.建立了一个PLS-BP-ANN、PCA-BP-ANN、GA-BP-ANN和BP-ANN四种模型的化学计量学多组分分析平台,对谱带混叠严重的5种大气有机毒物——苯、甲苯、甲醇、氯仿和丙酮进行了定性定量测定,比较了4种模型的误差,结果表明,PLS-BP-ANN模型得到的结果最好.
Abstract：The principal component of spectrum data is extracted through the methods of partial least squares(PLS) and principal component analysis(PCA),and the wavelength is selected based on genetic algorithm(GA) by removing uncorrelated variables for the sake of data compressing.The qualitative and quantitative analysis of multi-component system is performed through BP-ANN method.The chemo metrics multi-component analysis platform composed of PLS-BP-ANN,PCA-BP-ANN,GA-BP-ANN and BP-ANN models performs the qualitative and quantitative analysis of five air toxics(benzene,toluene,methanol,chloroform and acetone) whose absorption bands overlap seriously.The prediction errors of the four models are compared,which shows that the PLS-BP-ANN model works best.
[1]Bjarnestad S,Dahlman O.Chemical compositions of hard-wood and softwood pulps employing photoacoustic fouriertransform infrared spectroscopy in combination with partialleast-squares analysis[J].Anal Chem,2002,74(22):5851-5858.
[2]李世欣,温建,邵孝侯,等.偏最小二乘法与人工神经网络耦合的小流域产沙模型[J].河海大学学报:自然科学版,2010,38(2):149-153.
[3]Pereira R C C,Skrobot V L,Castro E V R,et al.Determi-nation of gasoline adulteration by principal componentsanalysis-linear discriminant analysis applied to FTIR spec-tra[J].Energy&Fuels,2006,20(3):1097-1102.
[4]欧文娟,孟耀勇,张小燕,等.紫外可见吸收光谱结合主成分-反向传播人工神经网络鉴别真假蜂蜜[J].分析化学,2011,39(7):1104-1108.
[5]Tarca L A,Grandjean B P A,Larachi F.Integrated geneticalgorithm-artificial neural network strategy for modelingimportant multiphase-flow characteristics[J].Ind Eng ChemRes,2002,41(10):2543-2551.
[6]Zinn P.Adaptive multicomponent analysis by genetic algo-rithms[J].J Chem Inf Model,2005,45(4):880-887.
[7]Amin N A S.Hybrid artificial neural network-genetic algo-rithm technique for modeling and optimization of plasma re-actor istadi[J].Ind Eng Chem Res,2006,45(20):6655-6664.
[8]王改良,武妍.用入侵的自适应遗传算法训练人工神经网络[J].红外与毫米波学报,2010,29(2):136-139.
[9]Li Y,Wang J D,Chen Z R,et al.Artificial neural networkfor the quantitative analysis of air toxic VOCs[J].Anal Lett,2004,34(12):2203-2219.
[10]曲培青,施润和,刘剋,等.基于遥感和BP人工神经网络的城乡气象站点划分分析[J].地球信息科学学报,2010,12(5):726-732.
基本信息:
中图分类号:O657.33
引用信息:
[1]胡兰萍,石玉军,张跃华.多种校准方法对多组分体系的定性定量分析比较[J].南通大学学报(自然科学版),2011,10(04):26-30.
基金信息:
江苏省高校自然科学基础研究项目(08KJB610007);; 南通市科学技术局科技计划项目(S2009010)
2011-12-20
2011-12-20