Application of LSSVM strategy to estimate asphaltene precipitation during different production processes

ABSTRACT Asphaltene precipitation is a critical problem in petroleum reservoirs that reduce the permeability of rocks significantly and has damagingly impacted production. To that end, determination of amount of asphaltene precipitation is an essentially task to overcome this problem. In this contribution, the authors estimate the asphaltene precipitation as a function of temperature, dilution ratio, and molecular weight of different n-alkanes based on the least squares support vector machine. Moreover, the present tool has been compared with other previous models and its accuracy was confirmed against them. The obtained values of R2 and mean squared error were 0.9968 and 0.021, respectively. This tool is simple to use and can be applied as a great predictive approach for estimating the asphaltene precipitation as a function of temperature, dilution ratio, and molecular weight of different n-alkanes.

[1]  H. Yarranton,et al.  Investigation on the reversibility of asphaltene precipitation , 2001 .

[2]  J. W. Bunger,et al.  Ion-exchange, coordination, and adsorption chromatographic separation of heavy-end petroleum distillates , 1972 .

[3]  Alireza Baghban,et al.  Prediction carbon dioxide solubility in presence of various ionic liquids using computational intelligence approaches , 2015 .

[4]  Ahmad Habibizad Navin,et al.  Using Adaptive Neuro-Fuzzy Inference System in Alert Management of Intrusion Detection Systems , 2012 .

[5]  Alireza Baghban,et al.  Phase equilibrium modeling of semi-clathrate hydrates of seven commonly gases in the presence of TBAB ionic liquid promoter based on a low parameter connectionist technique , 2015 .

[6]  Kosta J. Leontaritis.  PARA-Based (Paraffin-Aromatic-Resin-Asphaltene) Reservoir Oil Characterizations , 1997 .

[7]  Alireza Bahadori,et al.  Modelling of gas to hydrate conversion for promoting CO2 capture processes in the oil and gas industry , 2016 .

[8]  L. H. Ali,et al.  Investigations into asphaltenes in heavy crude oils. I. Effect of temperature on precipitation by alkane solvents , 1981 .

[9]  J. G. Meijer,et al.  Influence of Temperature and Pressure on Asphaltene Flocculation , 1984 .

[10]  G. A. Mansoori,et al.  Organic deposition from reservoir fluids : a thermodynamic predictive technique , 1991 .

[11]  T. Guo,et al.  Effect of temperature and molecular weight of n-alkane precipitants on asphaltene precipitation , 2001 .

[12]  Ali Abbas,et al.  Estimation of air dew point temperature using computational intelligence schemes , 2016 .

[13]  Ali Abedini,et al.  Comparison of scaling equation with neural network model for prediction of asphaltene precipitation , 2010 .

[14]  Alireza Bahadori,et al.  Modeling of true vapor pressure of petroleum products using ANFIS algorithm , 2016 .

[15]  A. Bahadori,et al.  Estimation of natural gases water content using adaptive neuro-fuzzy inference system , 2016 .

[16]  G. Ali Mansoori,et al.  Modeling of asphaltene and other heavy organic depositions , 1997 .

[17]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[18]  M. Sahimi,et al.  Asphalt flocculation and deposition: I. The onset of precipitation , 1996 .

[19]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[20]  J. Pfeiffer,et al.  Asphaltic Bitumen as Colloid System. , 1940 .

[21]  James G. Speight,et al.  Factors influencing the separation of asphaltenes from heavy petroleum feedstocks , 1984 .

[22]  Alireza Bahadori,et al.  Estimation of oil and gas properties in petroleum production and processing operations using rigorous model , 2016 .

[23]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[24]  Lipo Wang.  Support vector machines : theory and applications , 2005 .

[25]  T. Guo,et al.  A study on the application of scaling equation for asphaltene precipitation , 2000 .