Enhancing the performance of a dual-energy gamma ray based three-phase flow meter with the help of grey wolf optimization algorithm

Abstract

In recent years, there has been an increasing interest in implementing artificial intelligence in radiation based multiphase flow meter systems. This study revolves around an approach in which the grey wolf optimization (GWO) algorithm was employed to train the artificial neural network (ANN), and a hybrid network called as the GWO-trained ANN was introduced to predict the volume fractions in a gas-oil-water multiphase flow system. After that, the obtained GWO-based neural network was employed to measure 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. The first network was utilized to predict the oil and gas, the next one to predict the gas and water, and the last one to predict the water and oil volume fractions. In the next step, the GWO-based networks were trained based on numerically obtained data from MCNP-X code. The accuracy of the nets were evaluated and compared with each other. Based on the results, the best GWO-based net could predict the oil and gas volume fractions with the mean absolute percentage error of less than 0.8% and 0.4% for the testing and checking data, respectively.