Prediction of degrees API values of crude oils by use of saturates/aromatics/resins/ asphaltenes analysis: computational-intelligence-based models
| Title | Prediction of degrees API values of crude oils by use of saturates/aromatics/resins/ asphaltenes analysis: computational-intelligence-based models |
| Publication Type | Journal Article |
| Year of Publication | 2017 |
| Authors | Goel, P, Saurabh, K, Patil-Shinde, V, Tambe, SS |
| Journal | SPE Journal |
| Volume | 22 |
| Issue | 3 |
| Pagination | 817-853 |
| Date Published | JUN |
| Type of Article | Article |
| Abstract | The degrees API value is an important physicochemical characteristic of crude oils often used in determining their properties and quality. There exist models-predominantly linear ones-for predicting the degrees API magnitude from the molecular composition of a crude oil. This approach is tedious and time-consuming because it requires quantitative determination of numerous crude-oil components. Usually, the hydrocarbons present in a crude oil are grouped according to their molecular average structures into saturates, aromatics, resins, and asphaltenes (SARA) fractions. An degrees API-value prediction model dependent on these four fractions is relatively easier to develop, although this approach has been rarely used. A rigorous scrutiny suggests that some of the dependencies between the individual SARA fractions and the corresponding degrees API value could be nonlinear. Accordingly, in this study, SARA-fraction-based nonlinear models have been developed for the prediction of values using three computational-intelligence (CI) formalisms: genetic programming (GP), artificialneural networks (ANNs), and support-vector regression (SVR). The SARA analyses and degrees API values of 403 crude-oil samples covering wide ranges have been used in developing these models. A comparison of the CI-based models with an existing linear model indicates that all the former class of models possess a significantly better degrees API-value prediction and generalization performance than those exhibited by the linear model. Also, the SVR-based model has been found to be the most accurate degrees API-value predictor. Because of their better prediction accuracy, CI-based models can be gainfully used to predict degrees API values of crude oils. |
| DOI | 10.2118/184391-PA |
| Type of Journal (Indian or Foreign) | Foreign |
| Impact Factor (IF) | 1.442 |
Divison category:
Chemical Engineering & Process Development