拉曼光谱结合后向间隔偏最小二乘法用于调和汽油辛烷值定量分析

引用本文: 王拓, 戴连奎, 马万武. 拉曼光谱结合后向间隔偏最小二乘法用于调和汽油辛烷值定量分析[J]. 分析化学, 2018, 46(4): 623-629. doi: 10.11895/j.issn.0253-3820.170278 shu

Citation: WANG Tuo, DAI Lian-Kui, MA Wan-Wu. Quantitative Analysis of Blended Gasoline Octane Number Using Raman Spectroscopy with Backward Interval Partial Least Squares Method[J]. Chinese Journal of Analytical Chemistry, 2018, 46(4): 623-629. doi: 10.11895/j.issn.0253-3820.170278 shu

拉曼光谱结合后向间隔偏最小二乘法用于调和汽油辛烷值定量分析

1.
浙江大学工业控制技术国家重点实验室, 杭州 310027;
2.
中国石化青岛石油化工有限责任公司, 青岛 266043

摘要: 采用后向间隔偏最小二乘（Backward interval partial least squares，BiPLS）提取汽油拉曼光谱特征谱段，并用于研究法辛烷值（Research octane number，RON）的定量分析。实验中首先使用SPXY（Sample set partitioning based on joint x-y distances）方法划分训练集、交叉验证集和测试集，并采用稳健回归方法剔除异常的样本数据，再结合BiPLS方法筛选特征谱段，利用特征谱段建立偏最小二乘模型。与全谱段偏最小二乘模型的预测性能对比结果表明，后向间隔偏最小二乘方法可使输入模型的特征数据维数降低50.00%，交叉验证均方根误差（Root mean square error of cross validation，RMSECV）降低18.92%，预测均方根误差（Root mean square error of prediction，RMSEP）降低13.86%。后向间隔偏最小二乘方法可有效提取汽油拉曼光谱的特征谱段，降低模型复杂度，同时提高模型预测精度，在调和汽油研究法辛烷值定量分析方面有较好的应用前景。

关键词:

English

Quantitative Analysis of Blended Gasoline Octane Number Using Raman Spectroscopy with Backward Interval Partial Least Squares Method

1.
State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China;
2.
Sinopec Qingdao Petrochemical Co., Ltd, Qingdao 266043, China
Received Date: 04 July 2017
Revised Date: 28 February 2018

Abstract: The feature of gasoline Raman spectra which were used to study the quantitative analysis of the research octane number (RON) were extracted for the first time using backward interval partial least squares (BiPLS). In the experiment, the sample set partitioning based on joint x-y distances (SPXY) method was used to divide the training set, the cross validation set and the test set. And the robust regression algorithm was used to remove the abnormal sample. The partial least squares model was established using feature selected by the BiPLS algorithm. Compared with the model without feature selection, it was shown that the backward interval partial least squares algorithm could reduce the input dimension by 50.00%, and the root mean square error of cross validation(RMSECV) by 18.92% and the root mean square error of prediction (RMSEP) by 13.86%. The backward interval partial least squares algorithm can effectively extract the feature from gasoline Raman spectrum, reduce the model complexity, and improve the prediction accuracy of the model, and has great application prospect in the quantitative analysis of research octane number.

Key words:

Blended gasoline
/ Raman spectroscopy
/ Octane number
/ Backward interval partial least squares

1. [1]
  CHU Xiao-Li, LU Wan-Zhen. Instrumentation Customer,2013,20(2):11-13 褚小立, 陆婉珍.仪器仪表用户,2013,20(2):11-13
2. [2]
  LI Dong-Yang. Sino-Global Energy,2012,17(4):89-92 李东阳.中外能源,2012,17(4):89-92
3. [3]
  CHU Xiao-Li, TIAN Gao-You, YUAN Hong-Fu, LU Wan-Zhen. Chinese J. Anal. Chem.,2006,34(s1):175-178 褚小立, 田高友, 袁洪福, 陆婉珍.分析化学,2006,34(s1):175-178
4. [4]
  CHU Xiao-Li, YUAN Hong-Fu, LU Wan-Zhen. Chinese J. Anal. Chem.,2005,33(6):745-750 褚小立, 袁洪福, 陆婉珍.分析化学,2005,33(6):745-750
5. [5]
  Norgaard L, Saudland A, Wagner J, Nielsen J P, Munck L, Engelsen S B. Appl. Spectrosc.,2000,54(3):413-419
6. [6]
  Zou X B, Zhao j W, Povey M J W, Holmes M, Hanpin M. Anal. Chem. Acta,2010,667(1-2):14-32
7. [7]
  Corsetti S, McGloin D, Kiefer J. Fuel,2016,166:488-494
8. [8]
  Tan K M, Barman I, Dingari N C, Singh G P, Chia T F, Tok W L. Anal. Chem.,2013,85(3):1846-1851
9. [9]
  BAO Xin, DAI Lian-Kui. Chinese J. Anal. Chem.,2008,36(1):75-78 包鑫, 戴连奎.分析化学,2008,36(1):75-78
10. [10]
  TAN Xu-Song, DAI Lian-Kui. Control and Instruments in Chemical Industry,2004,(05):65-68 覃旭松, 戴连奎.化工自动化及仪表,2004,(05):65-68
11. [11]
  RUAN Hua, DAI Lian-Kui. Chinese J. Scientific Instrument,2010,(11):2440-2446 阮华, 戴连奎.仪器仪表学报,2010,(11):2440-2446
12. [12]
  Farkas A, Vajna B, Soti P L, Nagy Z K, Pataki H, van der G F, Marosi G. J. Raman Spectrosc.,2015,46(6):566-576
13. [13]
  Cramer J A, Kramer K E, Johnson K J, Morris R E, Rose-Pehrsson S L. Chemometr. Intell. Lab.,2008,92(1):13-21
14. [14]
  Yang G. Applying wavelet Frequency Component Correlative Selection in Raman Spectral Analysis:Proceedings-2009 2nd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2009, 2009[C].2009
15. [15]
  Lieber C A, Mahadevan-Jansen A. Appl. Spectrosc.,2003,57(11):1363-1367
16. [16]
  Krishna H, Majumder S K, Gupta P K. J. Raman Spectrosc.,2012,43(12):1884-1894
17. [17]
  Kennard R W, Stone L A. Technometrics,1969,11(1):137-148
18. [18]
  Galvão R K H, Araujo M C U, José G E, Pontes M J C, Silva E C, Saldanha T C B, Talanta,2005,67(4):736-740
19. [19]
  BAO Xin, DAI Lian-Kui. Chinese J. Scientific Instrument,2009,30(09):1829-1835 包鑫, 戴连奎. 仪器仪表学报,2009,30(09):1829-1835

扫一扫看文章

计量

PDF下载量: 17
文章访问数: 1390
HTML全文浏览量: 148

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

拉曼光谱结合后向间隔偏最小二乘法用于调和汽油辛烷值定量分析

English

Quantitative Analysis of Blended Gasoline Octane Number Using Raman Spectroscopy with Backward Interval Partial Least Squares Method

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

拉曼光谱结合后向间隔偏最小二乘法用于调和汽油辛烷值定量分析

English

Quantitative Analysis of Blended Gasoline Octane Number Using Raman Spectroscopy with Backward Interval Partial Least Squares Method

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs