TITLE:
LSSVM Combined with SPA Applied to Near-Infrared Quantitative Determination of the Octane in Fuel Petrol Samples
AUTHORS:
Lili Xu, Jie Gu, Huazhou Chen, Jiangbei Wen, Gaili Xu
KEYWORDS:
Near-Infrared, Fuel Petrol, The Octane Number, SPA, LSSVM
JOURNAL NAME:
Open Journal of Applied Sciences,
Vol.8 No.9,
September
29,
2018
ABSTRACT: Least square support vector machine (LSSVM) combined with successive projection algorithm (SPA) method was applied fornear-infrared (NIR)quantitative determination of the octane number in fuel petrol. The NIR spectra of 87 fuel petrol samples werescannedfor model establishment and optimization. First order derivative Savitzky-Golay smoother(1st-d’SG) wasutilized to improve theNIR predictive ability. Its pretreatment effect was compared with the raw data.SPA wasapplied for the extraction of informative wavelengths. Considering the linear and non-lineartraining mechanism,LSSVMregression was employed to establish calibration models.The correlation coefficient (R) and root mean square error (RMSE) were used as the model evaluation indices; accordingly the octane number in fuel petrolwas quantitatively determined with the prospective predictive indices. Results showed thatafter pretreated by 1st-d’SG, 8 SPA-selected wavelengthswas generated as the inputs of LSSVM, so that the calibration models were optimized in the way of combining the SPA-LSSVM regression with the SG smoother.The prediction results were quite satisfactory, with the calibrating correlation coefficient of0.951 and the RMSEof 3.282. An independenttestingsample set was used to evaluate the optimal model, the testingcorrelation coefficientwas 0.903 and the RMSE was 4.128. We conclude thatNIR spectrometry is feasible to determine the octane in fuel petrolby establishing SPA-LSSVMmodels. The 1st-d’SG pretreatment hastheadvantage of selecting wavelengths containing the implicit information. The combination of 1st-d’SG pretreatment and SPA-LSSVM show its applicable potential to predict theoctane numberinfuel petrol.