1. Research Institute of Petroleum Processing, Beijing 100083, China 2. Beijing University of Chemical Technology, Beijing 100029, China 3. Beijing Yanhua Petrochemical Co. Ltd., Beijing 102500, China
Abstract：In petrochemical industries, the molar ratio between methanol and isobutylene is one of the most important control parameters in methyl tertiary butyl ether (MTBE) production plant. However, traditional on-line gas chromatography method is difficult to use in practice because of its high maintenance and low speed. On-line near infrared spectroscopy is hopeful to become an excellent alternative method for determining the parameter due to its rapidness, convenience, and less maintenance. Because of the nonlinearity of the measured parameter and near infrared spectra, support vector regression, a novel powerful nonlinear calibration method, was used to build calibration model in the present paper. Compared with the results of partial least squares (PLS) and artificial neural network (ANN) method, the prediction accuracy of support vector regression model is high enough to meet the demand for process control of MTBE unit. This calibration method can be applied to real online analysis of the molar ratio between methanol and isobutylene by near infrared spectroscopy.
Key words：Near infrared spectroscopy;Nonlinear calibration;Support vector regression;Artificial neural network;Molar ratio between methanol and isobutylene;Methyl tertiary butyl ether
褚小立1,袁洪福2,骆献辉3,许育鹏1,陆婉珍1. 支持向量回归建立测定醇烯比的近红外光谱校正模型[J]. 光谱学与光谱分析, 2008, 28(06): 1227-1231.
CHU Xiao-li1,YUAN Hong-fu2,LUO Xian-hui3,XU Yu-peng1,LU Wan-zhen1. Developing Near Infrared spectroscopy Calibration Model of Molar Ratio between Methanol and Isobutylene by Support Vector Regression. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2008, 28(06): 1227-1231.
[1] LIU Hai-yun（刘海云）. Control and Instruments in Chemical Industry（化工自动化及仪表），1999，26（5）：16. [2] CHU Xiao-li，YUAN Hong-fu, LU Wan-zhen（褚小立, 袁洪福，陆婉珍）. Modern Scientific Instrument（现代科学仪器），2004，（2）：3. [3] LUO Xian-hui，CHU Xiao-li, YUAN Hong-fu（骆献辉, 褚小立，袁洪福）. Automation in Petro-Chemical Industry（石油化工自动化），2006，（3）：8. [4] WANG Yong，ZHANG Zhuo-yong，LIU Si-dong（王 勇, 张卓勇, 刘思东）. Chinese J. Anal. Chem.（分析化学），1998，26（9）：1146. [5] XU Lu，HU Chang-yu（许 禄, 胡昌玉）. Progress in Chemistry（化学进展），2000，12（1）：19. [6] WANG Hua-zhong, YU Jin-shou（王华忠, 俞金寿）. Control and Decision（控制与决策），2005，20（5）：549. [7] QU Hai-bin, LIU Xiao-xuan, CHENG Ji-yu（瞿海斌, 刘晓宣，程翼宇）. Chem. J. Chinese Universities（高等学校化学学报），2004，25（1）：39. [8] HOU Zhen-yu, CAI Wen-sheng, SHAO Xue-guang（侯振雨, 蔡文生, 邵学广）. Chinese J. Anal. Chem.（分析化学），2006，34（5）：617. [9] CHEN Nian-yi，LU Wen-cong（陈念贻, 陆文聪）. Computers and Applied Chemistry（计算机与应用化学），2002，19（6）：673. [10] ZHANG Lu-da，JI Ze-huan，SHEN Xiao-nan, et al（张录达, 金泽宸, 沈晓南，等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析），2005，25（9）：1400. [11] Yao X J，Panaye A，Doucet J P, et al. J. Chem Inf. Comput. Sci.，2004，44（4）：1257. [12] Thissena U，van Brakela R，de Weijerb A P，et al. Chemo. Intell. Lab. Syst.，2003，69（1）：35. [13] Vapnik V. Statistical Learning Theory. New York: Wiley，USA，1998. [14] Smola A J, Scholkopf B. A Tutorial on Support Vector Regression, Neuro COLT<sub>2</sub> Technical Report Series NC2-TR-1998-030, Royal Holloway College, University of London, UK, 1998. [15] Kennard R W，Stone L A. Technometrics，1969，11（3）：137.
