Flow regimes classification and prediction of volume fractions of the gas-oil-water three-phase flow using Adaptive Neuro-fuzzy Inference System

‎The used metering technique in this study is based on the dual energy (Am-241 and Cs-137) gamma ray attenuation‎. ‎Two transmitted NaI detectors in the best orientation were used and four features were extracted and applied to the model‎. ‎This paper highlights the application of Adaptive Neuro-fuzzy Inference System (ANFIS) for identifying flow regimes and predicting volume fractions in gas-oil-water multiphase systems‎. ‎In fact‎, ‎the aim of the current study is to recognize the flow regimes based on dual energy broad-beam gamma-ray attenuation technique using ANFIS‎. ‎In this study‎, ‎ANFIS is used to classify the flow regimes (annular‎, ‎stratified‎, ‎and homogenous) and predict the value of volume fractions‎. ‎To start modeling‎, ‎sufficient data are gathered‎. ‎Here‎, ‎data are generated numerically using MCNPX code‎. ‎In the next step‎, ‎ANFIS must be trained‎. ‎According to the modeling results‎, ‎the proposed ANFIS can correctly recognize all the three different flow regimes‎, ‎and other ANFIS networks can determine volume fractions with MRE of less than 2% according to the recognized regime‎, ‎which shows that ANFIS can predict the results precisely‎.

Keywords:

‎Three-phase flow , ‎Pattern recognition , ‎Volume fraction , ‎Adaptive neuro-fuzzy inference system , ‎Monte Carlo simulation‎