Application of stable consistency wavelength in optimizing gasoline RON near‐infrared analysis model transfer

Abstract

AbstractThe purpose of model transfer is to solve the problem that multivariate calibration models cannot be shared among different near‐infrared spectrometers. Taking gasoline as the research object, the transfer analysis of its octane number model was carried out. The gasoline samples collected by two near‐infrared spectrometers of the same type were used as the research object. The screening wavelengths with consistent and stable signals (SWCSS) combined with competitive adaptive reweighted sampling (CARS), uninformative variable elimination (UVE), and successive projections algorithm (SPA) were used to reduce the adverse effects of invalid wavelengths in the SWCSS method; therefore, the analysis ability of the master model to the slave samples was improved. Partial least squares regression (PLSR) models based on SWCSS‐UVE, SWCSS‐CARS, and SWCSS‐SPA algorithms were established, and comparison was made between their analytical capabilities for slave samples and those of SWCSS, direct standardization (DS) algorithm , piecewise direct standardization (PDS) algorithm, and slope/bias (S/B) algorithm. The results shown that the SWCSS‐UVE and SWCSS‐CARS methods can be used to establish models from the 231 and 6 wavelengths selected from the consistent wavelengths, respectively. The root mean square error of prediction (RMSEP) of the gasoline octane number (RON) content of the direct analysis of the spectrum measured by the slave machine was reduced from 5.7490 to 0.3226 and 0.3250, respectively, which was better than the single SWCSS and DS, PDS, and SWCSS‐SPA methods, and was close to the model transfer accuracy of the S/B algorithm. The transfer accuracy of SWCSS‐UVE and SWCSS‐CARS was not much different, but the wavelength variable involved in the model transfer of the latter was much smaller than that of the former, and the AIC value of SWCSS‐CARS was −59.59, which was much smaller than the akaike information criterion (AIC) value of SWCSS‐UVE 398.42.