The used metering technique in this paper is based on the multienergy (at least dual) gamma-ray attenuation. The aim of the current study is investigation of different combinations of sources in order to find the best combination for precise metering gas, oil and water percentages in annular three-phase flows. The required data were generated numerically using Monte Carlo N Particle extended (MCNPX) code. As a matter of fact, the current investigation devotes to predict the volume fractions in the annular three-phase flow, on the basis of a multienergy metering system including different radiation sources and one sodium iodide detector, using the hybrid model. Since the summation of volume fractions is constant, a constraint modeling problem exists, meaning that the hybrid model must predict only two volume fractions. Six hybrid models associated with the number of applied radiation sources are employed. The models are applied to predict the oil and gas volume fractions. For the next step, the hybrid models are trained based on numerically obtained data from the MCNPX code. The results show that the best prediction results are obtained for the oil and gas volume fractions of a system with the (241Am & 137Cs) radiation sources.
