Transcripción del resumen del autor. Asphaltene precipitation affects enhanced oil recovery processes through the mechanism of wettability alteration and blockage. Asphaltene precipitation is very sensitive to the reservoir conditions and fluid properties, such as pressure, temperature, dilution ratio, and injected fluid molecular weight. A Bayesian belief network (BBN) was used in this study as an artificial intelligence modeling tool to investigate the effect of different variables/parameters on asphaltene precipitation. The predicted results from the BBN model were compared to the experimental precipitation data obtained using high-resolution images captured in a high-pressure cell and processed by image analysis software. The cell accessories facilitate in situ visual monitoring of nuclei growth of asphaltene at high pressures and specified temperatures. The average relative absolute deviation between the model predictions and the experimental data was found to be less than 4.6%. Burst of nucleation or the onset of asphaltene precipitation was also determined at different conditions directly by the developed BBN model. A comparison between the prediction of this model and the alternatives showed that the BBN model predicts asphaltene precipitation more accurately and covers a wider range of affected variables/parameters.

4