Experimental and artificial neural network based analysis of solvent blends for dewaxing of crude oil

Abstract

Sustainability in flow condition by maintaining the pour point and cloud point in storage and transportation of crude oil is always a challengeable task for petroleum industry. Thus solvent dewaxing is an effective process used in oil refinery for monitoring before the transportation of crude oil in pipelines with an efficient and selective blended chemical. The present work describes the solvent dewaxing process through by analysis of basic fundamental interactions with computations of different acoustic parameters in presence of a high frequency ultrasonic wave. Experiments were performed to investigate the molecular interaction in rheological properties of waxy crude oil by blended solvent over a temperature range of 293 K to 323 K. The wax yield efficiency in the crude oil indicates that the performance of solvents blends depends on its mole fraction, compatibility of blends and on temperature of treatment. Addition of sonicated solvent blends in the ratio of 10:1, 15:1 and 20:1 improves flow conditions in crude oil pipe lines and increases its pour point. The sonication study was also designed by artificial neural network (ANN) model using R-Software which has been developed for ultrasonic velocity and other related parameters. The proposed ANN model for dewaxing of crude oil with blended solvent in different operating conditions provides comparable results with average absolute deviation (AAD) less than 0.5%.