Application of artificial neural networks (ANN) and genetic programming neural network (GPNN) for prediction of wax precipitation in crude oil systems

An intelligent framework is developed for calculating wax precipitation in petroleum mixtures over a wide temperature range. The tendency of wax to precipitation has posed great challenges for the petroleum industry. Theoretical results and practical experience indicate that feed forward network can approximate a wide class of function relationships very well. This property is exploited in petroleum engineering process. In this work, a conventional feed forward multilayer neural network (ANN) and genetic programming neural network approach (GPNN) have been proposed to predict the amount of wax precipitation. The accuracy of the methods is evaluated by its application for the amount of wax precipitation estimation of various reservoir fluids not used in the development of the models. Furthermore, the performance of the models is compared against the performance of multisolid model for wax precipitation prediction and also experimental data. Results of this comparison show that the proposed method out performs the other alternatives, both in accuracy and generality.