A Novel ANFIS-PSO Network for forecasting oil flocculated asphaltene weight percentage at wide range of operation conditions

Abstract

ABSTRACTAsphaltene precipitation is known as one of the challenging problems in petroleum industries which have significant effects on production such as formation damage and wellbore plugging, that consequently impose a serious restriction on production and in turn increases total cost of entire operation. Through decades an extensive research has been performed in order to identify asphaltene molecular structure, its behavior at different condition, and its departure mechanism from oil. One of most critical parameter associated with asphaltene precipitation modeling is flocculated asphaltene weight percentage in oil at given operation condition. In this investigation, to eliminate cost and time related with experimental procedure that concern with determining this critical parameter, a novel hybrid structure of ANN and FIS with the help of Genetic algorithm has been developed, which trained and tested by over 350 experimental data. The constructed network show good performance regarding flocculated weight percentage forecasting, and therefore can be used as a universal tool in order to provide input for any asphaltene-related modeling, with assurance.