Regular supplies of crude oils during a 3 year period were used to develop and test a partial least-squares multivariate model for determining the total acid number (TAN) based on near-infrared spectra. Several models built automatically by chemometrics software were selected for testing in a series of cross-validations and via large, independent prediction data sets. Crossvalidation errors were largely consistent regardless of whether 2% or 20% of the data was left out of the calibration. Two of the three separate prediction sets were also predicted very satisfactorily, but one of the prediction sets, covering a full year of spectra and being the same size as the calibration model, showed some outliers and an obvious deterioration in prediction errors. Nevertheless, two of the selected models held satisfactorily after a small number of outliers were removed and thus proved very effective for determining the TAN in crude oil for all the spectra involved. The spectra from the poorest-performing prediction set were compared with the spectra from the calibration set and no meaningful spectral differences were identified.
Regular supplies of crude oils during a nominal two-year period were used to develop and test partial least squares (PLS) multivariate models for determining sulfur based on near-infrared (NIR) spectra. Several models built automatically by chemometrics software were selected for testing in a series of cross validations and via large, independent prediction data sets. Three "annual" multivariate models were created in this manner, comprising the spectra acquired in 2017, 2018, and 2019, with each of them tested with the remaining two sets used for independent predictions. One of those three models performed best in terms of combined calibration and prediction errors, with the other two being suboptimal either because of the higher calibration errors or because of the limited predictive abilities. This is followed by creating three biannual models with the respective remaining set used for the prediction. Updating the models in this manner largely proved beneficial primarily due to alleviating the issues seen in the suboptimal models. The overall prediction error based on the analysis of about 1300 industrially relevant samples and across two years of acquisitions steadily indicates the prediction error of about 0.1 wt % for crude oils with the average content of ∼3 wt % of sulfur.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.