A new model for predicting asphaltene precipitation of diluted crude oil by implementing LSSVM-CSA algorithm

One of the severe problems in all the oil production stages from the pore walls of the reservoir rocks to the wellhead, transfer pipelines, and production units of a large portion of the world's hydrocarbon reservoirs, is asphaltene precipitation and deposition from crude oil on solid surfaces. In this article, least squares support vector machine optimized by coupled simulated annealing is employed for estimation of the amount of asphaltene precipitated weight percent of diluted crude oil with paraffin based on titration tests data from a recently published article. The results indicated that there is an excellent correlation between predicted and experimental values with an average absolute relative deviation percent, mean square error, and a determination coefficient of 0.0727%, 0.0242, and 0.9972, respectively. The developed predicting model can be applied to estimate the amount of asphaltene precipitated when the crude oil is diluted with paraffin and to eschew experimental titration test that is tedious and time-consuming.