Flow regime identification and gas volume fraction prediction in two-phase flows using a simple gamma-ray gauge combined with parallel artificial neural networks

Abstract

Volume fraction and regime identification are considered as two main goals in the multiphase flow measurement. By developing the applications of artificial neural networks (ANN), new approaches have been introduced in the multiphase measurements. In the present work, prediction of gas volume fraction and identification of five different flow regimes including Bubble, Dispersed, Pluged, Annular, and Slug regimes were carried out using the simplest form of a radiation measurement system and proposing a simple structure of ANN including two independent MLP networks which are working in parallel. All data used for training and testing the networks were recorded using a simple radiation-based setup involving a137Cs gamma-ray source and one NaI(Tl) detector in the experimental setup with real dynamic conditions of fluids in a test loop. Extracted features from the recorded spectrum by the detector include full-energy peak and total counts. Overall results showed that all introduced flow regimes have been successfully identified by one of the proposed ANNs while GVFs have been predicted precisely using another one with a mean relative error of less than 3%.