摘要： 近红外漫反射光谱和紫外吸收光谱分别用于燃油的辛烷值和单芳香族化合物含量的测定，偏最小二乘回归(partial least squares regression, PLSR)用于光谱多元校正模型的构建。基于互信息(mutual information, MI)理论的变量筛选方法用于模型优化以提高模型的预测精度，降低模型的复杂度。结果表明，MI-PLSR可以有效的提高燃油品质模型的预测精度，简化分析模型。辛烷值的预测均方根误差(root mean square error of prediction, RMSEP)由0.288减小为0.111，预测相关系数R从0.985提高到0.998，建模变量由401减小为112;单芳香族化合物含量的RMSEP从0.753减小为0.478，R由0.996提高为0.998，建模变量由572缩减为37。说明振动光谱结合MI-PLSR方法可用于燃油品质检测，具有高效率低成本的特点。
关键词：近红外光谱;紫外光谱;偏最小二乘回归;互信息;燃油品质
Abstract：Near infrared diffuse reflectance (NIRS) and ultraviolet (UV) spectral analysis were adopted for quantitative determination of octane number and monoaromatics in fuel oil. Partial least squares regression (PLSR) was used for construction of vibrational spectral calibration models. Variables selection strategy based on mutual information (MI) theory was introduced to optimize the models for improving the precision and reducing the complexity. The results indicate that MI-PLSR method can effectively improve the predictive ability of the models and simplify them. For octane number models, the root mean square error of prediction (RMSEP) and the number of calibration variables were reduced from 0.288 and 401 to 0.111 and 112, respectively, and correlation coefficient (R) was improved from 0.985 to 0.998. For monoaromatics models, RMSEP and the number of calibration variables were reduced from 0.753 and 572 to 0.478 and 37, respectively, and R was improved from 0.996 to 0.998. Vibrational spectral analysis combined with MI-PLSR method can be used for quantitative analysis of fuel oil properties, and improve the cost-effectiveness.
郝 勇，孙旭东，蔡丽君，刘燕德* . 基于互信息方法的燃油品质光谱分析模型构建与简化[J]. 光谱学与光谱分析, 2012, 32(01): 175-178.
HAO Yong, SUN Xu-dong, CAI Li-jun, LIU Yan-de*. Construction and Simplification of the Calibration Model for Spectral Analysis of Fuel Oil Properties Based on Mutual Information Method . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2012, 32(01): 175-178.
[1] YUAN Jun, ZHOU Xiao-wei, YANG Bo-lun(袁 俊，周小伟，杨伯伦). Journal of Chemical Engineering of Chinese Universities(高校化学工程学报), 2010，24(2): 258. [2] XIAO Xue-xi(肖学喜). Chemical Analysis and Meterage(化学分析计量)，2008，17(5): 21. [3] KONG Wen-wen, LIU Fei, ZOU Qiang, et al((孔汶汶，刘 飞，邹 强，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2011, 31(4): 988. [4] LIU Yan-de, SUN Xu-dong, ZHANG Hai-liang(刘燕德，孙旭东，章海亮). Journal of East China Jiaotong University(华东交通大学学报)，2009, 26(3): 33. [5] Sorol N, Arancibia E, Bortolato S A, et al. Chemometrics and Intelligent Laboratory Systems, 2010, 102(2): 100. [6] Wiegand P,Pell R, Comas E. Chemometrics and Intelligent Laboratory Systems, 2009, 98(2): 108. [7] Hu Q H, Zhang L, Zhang D, et al. Expert Systems with Applications, 2011, 38(9): 10737. [8] Benoudjit N, Francois D, Meurens M, et al. Chemometrics and Intelligent Laboratory Systems, 2004, 74(2): 243. [9] Rossi F, Lendasse A, Francois D, et al. Chemometrics and Intelligent Laboratory Systems, 2006, 80(2): 215. [10] Xu L, Jiang J H, Zhou Y P, et al. Chemometrics and Intelligent Laboratory Systems, 2007, 87(2): 226. [11] Viscarra Rossel R A, Behrens T. Geoderma, 2010, 158(1): 46. [12] Durmus Ozdemir. Petroleum Science and Technology, 2005, 23(9): 1139. [13] Wentzell P D, Andrews D T, Walsh J M, et al. Canadian Journal of Chemistry, 1999, 77: 391. [14] Galvao R K H, Araujo M C U, Jose G E , et al. Talanta, 2005, 67(4): 736.
