当前位置: X-MOL 学术J. Chemometr. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Estimation of gasoline properties by 1 H NMR spectroscopy with repeated double cross-validated partial least squares models
Journal of Chemometrics ( IF 2.4 ) Pub Date : 2020-01-05 , DOI: 10.1002/cem.3212
Ana L. Leal 1, 2, 3 , Ricardo M. Albuquerque 2 , Artur M.S. Silva 1 , Jorge C. Ribeiro 2 , Fernando G. Martins 3
Affiliation  

Commercial gasoline must satisfy several product specifications before trading. In the present work, repeated double cross validation using partial least squares regression was applied to create reliable prediction models for 13 physicochemical parameters (eg, density, vapour pressure, evaporate at 70°C, evaporate at 100°C, evaporate at 150°C, final boiling point, research octane number, motor octane number, aromatic content, olefinic content, benzene content, oxygen content, and methyl tert‐butyl ether content) of gasoline produced in Matosinhos' refinery. The input variables for the regression are the 1H NMR spectral intensities of a total of 448 samples, which were recorded using a picoSpin NMR spectrometer operating at 80 MHz. The output variables are the corresponding property values, which were also measured according to ISO standard methods. A spectral feature elimination before multivariate analysis was done to remove noise and speed up the chemometric analysis. The optimum complexity of each model was achieved by repeated double cross‐validation strategy, consisting of 100 repetitions of two nested cross‐validation loops. Quantitative partial least squares yielded accurate predictions of 11 of 13 properties within the reproducibility of ISO standards. The methodology presented in this work has been proven effective in property estimation and enables a significant reduction in the total time of gasoline quality control.

中文翻译:

通过 1 H NMR 光谱和重复的双重交叉验证偏最小二乘模型估计汽油特性

商业汽油在交易前必须满足几个产品规格。在目前的工作中,使用偏最小二乘回归的重复双重交叉验证被用于为 13 个物理化学参数(例如,密度、蒸气压、70°C 蒸发、100°C 蒸发、150°C 蒸发)创建可靠的预测模型Matosinhos 炼油厂生产的汽油的终沸点、研究辛烷值、发动机辛烷值、芳烃含量、烯烃含量、苯含量、氧含量和甲基叔丁基醚含量)。回归的输入变量是总共 448 个样本的 1H NMR 光谱强度,这些强度是使用在 80 MHz 下运行的 picoSpin NMR 光谱仪记录的。输出变量是对应的属性值,这些也是根据 ISO 标准方法测量的。进行多变量分析之前的光谱特征消除,以消除噪声并加快化学计量分析。每个模型的最佳复杂度是通过重复的双重交叉验证策略实现的,由两个嵌套交叉验证循环的 100 次重复组成。在 ISO 标准的再现性范围内,定量偏最小二乘法对 13 项特性中的 11 项进行了准确预测。这项工作中提出的方法已被证明在性质估计方面是有效的,并且能够显着减少汽油质量控制的总时间。每个模型的最佳复杂度是通过重复的双重交叉验证策略实现的,由两个嵌套交叉验证循环的 100 次重复组成。在 ISO 标准的再现性范围内,定量偏最小二乘法对 13 项特性中的 11 项进行了准确预测。这项工作中提出的方法已被证明在性质估计方面是有效的,并且能够显着减少汽油质量控制的总时间。每个模型的最佳复杂度是通过重复的双重交叉验证策略实现的,由两个嵌套交叉验证循环的 100 次重复组成。在 ISO 标准的再现性范围内,定量偏最小二乘法对 13 项特性中的 11 项进行了准确预测。这项工作中提出的方法已被证明在性质估计方面是有效的,并且能够显着减少汽油质量控制的总时间。
更新日期:2020-01-05
down
wechat
bug