[1]胡碧霞,张红光,卢建刚,等.汽油辛烷值近红外光谱检测的改进极限学习机建模方法[J].南京理工大学学报(自然科学版),2017,41(05):660.[doi:10.14177/j.cnki.32-1397n.2017.41.05.019]
 Hu Bixia,Zhang Hongguang,Lu Jiangang,et al.Novel modeling method based on improved extreme learningmachine algorithm for gasoline octane number detectionby near infrared spectroscopy[J].Journal of Nanjing University of Science and Technology,2017,41(05):660.[doi:10.14177/j.cnki.32-1397n.2017.41.05.019]
点击复制

汽油辛烷值近红外光谱检测的改进极限学习机建模方法()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
41卷
期数:
2017年05期
页码:
660
栏目:
出版日期:
2017-10-31

文章信息/Info

Title:
Novel modeling method based on improved extreme learningmachine algorithm for gasoline octane number detectionby near infrared spectroscopy
文章编号:
1005-9830(2017)05-0660-06
作者:
胡碧霞张红光卢建刚鄢 悦李雪园韩金厚刘 彤陈金水孙优贤
浙江大学 工业控制技术国家重点实验室,浙江 杭州 310027
Author(s):
Hu BixiaZhang HongguangLu JiangangYan YueLi XueyuanHan JinhouLiu TongChen JinshuiSun Youxian
State Key Laboratory of Industrial Control Technology,Zhejiang University,Hangzhou 310027,China
关键词:
汽油辛烷值 近红外光谱 模型 极限学习机 偏最小二乘 变量投影重要性系数
Keywords:
gasoline octane number near infrared spectroscopy models extreme learning machine partial least square variable importance in the projection
分类号:
O657.3
DOI:
10.14177/j.cnki.32-1397n.2017.41.05.019
摘要:
为提高近红外光谱法检测汽油辛烷值的精度,该文提出一种汽油辛烷值近红外光谱检测的改进极限学习机(iELM)新型建模方法。该算法融合了极限学习机算法(ELM)与基于变量投影重要性系数的改进叠加偏最小二乘回归(VIP-SPLS)模型算法,有效解决了ELM模型隐含层输出矩阵维数高和高度共线性的问题。采用该算法对汽油辛烷值的近红外光谱检测数据进行建模,发现改进极限学习机模型的精度比现有的偏最小二乘回归模型和极限学习机模型分别提高20.0%和29.3%,验证了方法的有效性。实验表明,该文方法可用于汽油辛烷值的近红外光谱检测,检测精度良好。
Abstract:
In order to improve the accuracy of gasoline octane number detection by the near infrared(NIR)spectroscopy,an improved extreme learning machine(iELM)algorithm combined with the extreme learning machine(ELM)algorithm and the improved stacked partial least square regression based on the variable importance in the projection(VIP-SPLS)algorithm is proposed here.And it solves the problem of high dimension and high collinearity in the output matrix of hidden layer of the ELM algorithm effectively.Then the proposed method is applied to a commonly used benchmark NIR spectral data of gasoline octane number detection.The results show that,compared with the PLS model and the ELM model,the accuracy of iELM model is increased by 20.0% and 29.3% respectively.The experiment shows that the iELM algorithm can be applied to the gasoline octane number detection by the near infrared spectroscopy and its accuracy is satisfactory.

参考文献/References:

[1] 沈义涛,汪建忠,帅石金,等.辛烷值对汽油机性能的影响[J].内燃机工程,2008,29(5):52-56.
Shen Yitao,Wang Jianzhong,Shuai Shijin,et al.Effects of octane number on gasoline engine performance[J].Chinese Internal Combustion Engine Engineering,2008,29(5):52-56.
[2]王计广.汽油辛烷值对汽车节能技术及CO2排放影响[C]//Proceedings of the Fifteenth Annual Conference of Automotive Fuel and Lubricating Oil Branch of China Automotive Engineering Society.天津:中国汽车工程学会汽车燃料与润滑油分会,2012.
[3]李兵.影响车用汽油辛烷值测定准确度因素分析[J].广东化工,2015,42(16):136-137.
Li Bing.Analysis of factors affecting the accuracy of gasoline octane number determination[J].Guangdong Chemical Industry,2015,42(16):136-137.
[4]韩言正,戴连奎.基于近红外光谱的汽油辛烷值在线分析仪[J].化工自动化及仪表,2005,32(3):68-71.
Han Yanzheng,Dai Liankui.Online analyzer of gasoline octane number based on NIR spectrogram[J].Control and Instruments in Chemical Industry,2005,32(3):68-71.
[5]陆婉珍.现代近红外光谱分析技术[M].北京:中国石化出版社,2007.
[6]Roggo Y,Chalus P,Maurer L,et al.A review of near infrared spectroscopy and chemometrics in pharmaceutical technologies[J].Journal of Pharmaceutical & Biomedical Analysis,2007,44(3):683-700.
[7]Bohács G,Ovád Z,Salgó A.Prediction of gasoline properties with near infrared spectroscopy[J].Journal of Near Infrared Spectroscopy,1998,6(1):341-348.
[8]Macho S,Larrechi M S.Near-infrared spectroscopy and multivariate calibration for the quantitative determination of certain properties in the petrochemical industry[J].TrAc Trends Analytical Chemistry,2002,21(12):799-806.
[9]何楚文,王立.近红外光谱的发展背景及在石油行业中的应用[J].广州化工,2015(7):44-47.
He Chuwen,Wang Li.The development of near-infrared spectra and its applications in petroleum field[J].Guangzhou Chemical Industry,2015(7):44-47.
[10]吴烈刚.在线NIR油品质量检测系统的设计与应用[J].仪器仪表与分析监测,2016(1):10-14.
Wu Liegang.Design and application of on-line NIR qualitydetector for gasoline products[J].Instrumentation.Analysis.Monitoring,2016(1):10-14.
[11]陈沅涛,徐蔚鸿,吴佳英.一种增量向量支持向量机学习算法[J].南京理工大学学报,2012,36(5):873-878.
Chen Yuantao,Xu Weihong,Wu Jiaying.Incremental vector support vector machine learning algorithm[J].Journal of Nanjing University of Science and Technology,2012,36(5):873-878.
[12]Huang G B,Zhou H,Ding X,et al.Extreme learning machine for regression and multiclass classification[J].IEEE Transactions on Systems Man & Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man & Cybernetics Society,2012,42(42):513-29.
[13]Ouyang Q,Chen Q,Zhao J,et al.Determination of amino acid nitrogen in soy sauce using near infrared spectroscopy combined with characteristic variables selection and extreme learning machine[J].Food & Bioprocess Technology,2012,6(9):2486-2493.
[14]Chen Q,Ding J,Cai J,et al.Rapid measurement of total acid content(TAC)in vinegar using near infrared spectroscopy based on efficient variables selection algorithm and nonlinear regression tools[J].Food Chemistry,2012,135(2):590-595.
[15]Huang Z,Tao W,Fang J,et al.Multivariate calibration of on-line enrichment near-infrared(NIR)spectra and determination of trace lead in water[J].Chemometrics & Intelligent Laboratory Systems,2009,98(2):195-200.
[16]Li Z P,Wang J,Song Q H,et al.A review of application of near-infrared spectroscopy in food detection and quality control[J].Food & Fermentation Industries,2012,38(3):125-131.

备注/Memo

备注/Memo:
收稿日期:2016-10-12 修回日期:2017-02-13

基金项目:国家自然科学基金(61590925; U1509211)
作者简介:胡碧霞(1994-),女,博士生,主要研究方向:工业大数据分析,E-mail:hubx@zju.edu.cn; 通讯作者:卢建刚(1968-),男,博士,教授,博士生导师,主要研究方向:复杂工程系统的智能感知、建模、控制与优化,E-mail:lujg@zju.edu.cn。
引文格式:胡碧霞,张红光,卢建刚,等.汽油辛烷值近红外光谱检测的改进极限学习机建模方法[J].南京理工大学学报,2017,41(5):660-665.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 1900-01-01