Data Fusion of Raman and Near-Infrared Spectroscopies for the Rapid Quantitative Analysis of Methanol Content in Methanol–Gasoline

• Published in: Energy & fuels 2019-12, Vol.33 (12), p.12286-12294
• Main Authors: Li, Maogang, Xue, Jia, Du, Yao, Zhang, Tianlong, Li, Hua
• Format: Article
• Language: English
• ISSN: 0887-0624; 1520-5029
• DOI: 10.1021/acs.energyfuels.9b03021

Rapid analysis of methanol content in methanol–gasoline is of great significance to monitor the methanol–gasoline quality. In this work, two different data-fusion strategies based on Raman and near-infrared (NIR) spectroscopies coupled with partial least square (PLS) were constructed and applied for a rapid and accurate analysis of the methanol content in methanol–gasoline. The Raman and NIR spectra of 49 methanol–gasoline samples were recorded, and the characteristic peaks of the methanol–gasoline samples in Raman and NIR spectroscopies were identified. For spectral data fusion, two different data-fusion strategies based on Raman and NIR spectroscopies coupled with PLS were proposed; normalization was used for low-level data fusion, and variable importance in projection (VIP) was used for mid-level data fusion. The different spectra pretreatment methods, latent variables, and variable importance thresholds of VIP were explored and optimized by 5-fold cross-validation (CV) to optimize the PLS calibration model for methanol content analysis. To further prove the predictive performance and stability of the PLS calibration model based on two data-fusion strategies, four PLS calibration models based on Raman, NIR, and two data-fusion strategies were applied to the quantitative analysis of methanol content in methanol–gasoline. The results show that the predictive performance of PLS calibration models based on the two data-fusion strategies is improved, and the PLS calibration model based on mid-level data fusion strategy gave an excellent predictive performance in methanol content analysis, with coefficients of determination of cross-validation (R cv 2) and validation set (R v 2) of 0.9988 and 0.9905, respectively, and root mean square error of cross-validation (RMSECV) and validation set (RMSEV) of 0.0068 and 0.0288%, respectively. Therefore, data fusion based on Raman and NIR spectroscopies coupled with PLS can give a rapid and accurate quantitative analysis of the methanol content in methanol–gasoline.