An intelligent integrated approach of Jaya optimization algorithm and neuro-fuzzy network to model the stratified three-phase flow of gas–oil–water

Abstract

The problem of how to accurately measure the volume fractions of oil–gas–water mixtures in a pipeline remains as one of the key challenges in the petroleum industry. The current research highlights the capability of a hybrid system of the Jaya optimization algorithm and the adaptive neuro-fuzzy inference system (ANFIS), to model the stratified three-phase flow of gas–oil–water. As a matter of fact, the present study devotes to forecast the volume fractions in the stratified three-phase flow, on the basis of a dual-energy metering system, including the 152Eu and 137Cs and one NaI detector, using the aforementioned hybrid model. Since the summation of volume fractions are constant (equal to 100%), a constraint modelling problem exists, meaning that the hybrid model must forecast only two volume fractions. In this paper, three main hybrid models are employed. The first network is applied to forecast the gas and water volume fractions, the next one to forecast the water and oil volume fractions, and the last one to forecast the oil and gas volume fractions. For the next step, the hybrid models are trained based on numerically obtained data from the MCNP-X code.