Abstract
In this work, an intelligent gamma densitometer gauge for non-intrusive real-time measurement of the two-phase flow void fraction has been designed and constructed. It has been implemented in a horizontal pipe over a wide range of gas and liquid superficial velocities. Moreover, a Long Short-Term Memory (LSTM) neural network has been used for analyzing the data sequence from a dedicated high sampling rate dual-beam gamma densitometer. This approach considerably reduced the complexity of the data processing and regression operations while providing a high capability to identify and compensate for the errors caused by intermittent, and inhomogeneous flow regimes in a real-time mode. A comprehensive sensitivity analysis has been performed to adjust the network parameters for the most accurate void fraction prediction in all studied flow regimes including slug, plug, wavy, stratified, bubbly, and semi-annular. The experimental evaluations revealed that considering a sampling time of a few seconds, the optimized model approximated the actual data with an R-squared of 0.98, and almost all measurements were carried out with the maximum absolute error of 10%. The high accuracy and relatively fast response of the proposed method make it a reliable technique for developing a high-performance real-time multiphase flow meter.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
