Prediction of minimum miscible pressure by using neural network based hybrid genetic algorithm and particle swarm optimization

Abstract

Miscible gas injection is considered as an effective enhanced oil recovery (EOR) technique for conventional oil reservoirs. Minimum miscibility pressure (MMP) is an important parameter in design of a gas injection project as sweep efficiency from gas injection highly depends on the value of MMP. Obtaining MMP using laboratory techniques is cost, labor, and time intensive. Hence, finding a rapid, inexpensive, and robust technique to estimate the gas–oil MMP is inevitable. In this work, the model based on a feed-forward artificial neural network (ANN) optimized by Hybrid Genetic Algorithm and Particle Swarm Optimization (HGAPSO) to estimate gas–oil MMP is proposed. Genetic Algorithm is used to decide the initial weights of the neural network. The performance of the HGAPSO–ANN model is compared with experimental gas–oil MMP and the calculated results for the common gas–oil MMP correlations. The results demonstrate the effectiveness of the HGAPSO–ANN model.