Neural network based unified particle swarm optimization for prediction of asphaltene precipitation

The precipitation and deposition of crude oil polar fractions such as asphaltenes in petroleum reservoirs reduce considerably the rock permeability and the oil recovery. In the present paper, the model based on a feed-forward artificial neural network (ANN) to predict asphaltene precipitation of the reservoir is proposed. After that ANN model was optimized by unified particle swarm optimization (UPSO). UPSO is used to decide the initial weights of the neural network. The UPSO-ANN model is applied to the experimental data reported in the literature. The performance of the UPSO-ANN model is compared with scaling model. The results demonstrate the effectiveness of the UPSO-ANN model.

► An artificial neural network combine with unified particle swarm optimization has been presented.
► UPSO-ANN model combines local and global searching ability of the back propagation and UPSO, respectively.
► It has improved the fitting between UPSO-ANN prediction of the model and the measured values.
► The UPSO parameters of the algorithm have been carefully designed to optimize the neural network, avoiding premature convergence.