Asphaltene precipitation and deposition in oil reservoirs – Technical aspects, experimental and hybrid neural network predictive tools

• Hybrid ANN is more reliable compared to conventional methods.
• Experiments and predictive tools are conducted within wide range of process conditions.
• Temperature and pressure drop have the greatest effects on asphaltene deposition.
• Convergence rate of ICA-ANN is higher than that of PSO-ANN.
• A good agreement is observed between experiments and connectionist modeling.

Precipitation of asphaltene is considered as an undesired process during oil production via natural depletion and gas injection as it blocks the pore space and reduces the oil flow rate. In addition, it lessens the efficiency of the gas injection into oil reservoirs. This paper presents static and dynamic experiments conducted to investigate the effects of temperature, pressure, pressure drop, dilution ratio, and mixture compositions on asphaltene precipitation and deposition. Important technical aspects of asphaltene precipitation such as equation of state, analysis tools, and predictive methods are also discussed. Different methodologies to analyze asphaltene precipitation are reviewed, as well. Artificial neural networks (ANNs) joined with imperialist competitive algorithm (ICA) and particle swarm optimization (PSO) are employed to approximate asphaltene precipitation and deposition with and without CO2 injection. The connectionist model is built based on experimental data covering wide ranges of process and thermodynamic conditions. A good match was obtained between the real data and the model predictions. Temperature and pressure drop have the highest influence on asphaltene deposition during dynamic tests. ICA-ANN attains more reliable outputs compared with PSO-ANN, the conventional ANN, and scaling models. In addition, high pressure microscopy (HPM) technique leads to more accurate results compared with quantitative methods when studying asphaltene precipitation.