Calculation of volume fractions regardless scale deposition in the oil industry pipelines using feed-forward multilayer perceptron artificial neural network and MCNP6 code

Abstract

During the production of oil and gas, barium sulfate (BaSO4) scale occurs on the inner walls of the tubes leading the reduction of the internal diameter, making the fluid passage difficult and complicating the calculation of volume fractions of fluids. In this sense, this study presents a methodology for the development of volume fractions of fluids multiphase meters and the prediction of barium sulfate (BaSO4) scale thickness. The spectra obtained by two NaI(Tl) detectors that record the transmitted and scattered beams are used as input data for the artificial neural network without the need of any parametrization method. Theoretical models for annular flow regime were developed using MCNP6 code. Different volume fractions and scale thickness values of oil-water-gas were generated as a data set to train and evaluate the neural network. The results indicate that it is possible to calculate the volume fraction regardless the scale thickness in offshore oil industry pipes. More than 88% of the results showed errors below 5% for all investigated samples.