Experimental study and machine learning modeling of water removal efficiency from crude oil using demulsifier

Abstract

Abstract This study deals with the investigation of the water removal efficiency (WRE) from crude oil using a commercial demulsifier. The impacts of time, demulsifier concentration, and temperature on WRE were experimentally studied. The results implied the fact that temperature plays a substantial role in the demulsification and has a direct correlation with WRE. In addition, while increasing the concentration up to 40 ppm contributed to reaching a higher WRE, it did not have positive effects on efficiency at higher concentrations (overdose) and just led to more demulsifier consumption. The concentration dependence of WRE was also diminished at high temperatures. At higher levels of temperature and concentration, the time required to reach a high WRE was noticeably reduced. In order to generalize the findings of this study, the measured experimental data were employed to design predictive methods for WRE based on two smart soft-computing paradigms, including Multilayer perceptron (MLP) and Gaussian process regression (GPR). Despite the high accuracy of both models, the MLP model presented the best consistencies with experimental data with average absolute relative error and relative root mean squared error of 0.84%, and 0.01%, respectively during the testing (validation) step. Also, a visual description through the contour diagram confirmed the capability of the recently proposed models to describe the physical variations of WRE under various operating conditions. Ultimately, a sensitivity analysis based on the MLP model was undertaken to shed light on the order of significance of operational factors in controlling WRE. Overall, the findings of the current research, in turn, have a satisfactory contribution to the efficient design of the water removal process from crude oil based on demulsifiers.

Keywords

• Demulsifier
• Crude oil
• Water removal efficiency
• Machine learning