Back to Search Start Over

Salinity and flow pattern independent flow rate measurement in a gas-liquid flow with optimum feature selection and novel detection geometry using ANNs.

Authors :
ShadSanjabad, Maasoumeh
Feghhi, AmirHossein
Ghaderi, Reza
Boorboor, Saeed
Source :
Flow Measurement & Instrumentation. Jul2024, Vol. 97, pN.PAG-N.PAG. 1p.
Publication Year :
2024

Abstract

This paper presents a study on the salinity determination and flow rate estimation in a two-phase air-water system. For this purpose, an automated air-water test loop capable of generating different flow patterns in a horizontal pathway was utilized to do numerous experiments at varying flow rates. A nuclear measuring setup, comprising Cs-137 and Am-241 as radiation sources, one NaI (Tl) scintillation detector to register transmission counts of Cs and three scintillator detectors for registering transmission and scattering counts from Am, was prepared. A pressure drop pipe was also employed for flow rate measurement, with MLPs were selected as the processing element. Notable innovations of this paper can be considered from two perspectives. Firstly, a novel paradigm in nuclear measurement geometry. This novelty uses the benefits of three scintillator detectors to extract features with the maximum potential for classifying and determining salinity. Secondly, there is a new method in data processing and utilizing optimum features to achieve the best performance in predicting flow rates. Results in flow rate prediction independent of salinity and flow regime indicate that the proposed paradigm and method are reliable for using in industrial fields related to multi-phase metering. • This paper proposes a novel paradigm in nuclear measurement geometry. • This paper employs seven ANNs to develop the optimal prediction model. • The combination of wavelet transform and statistical features shows the best performance to determine the flow rates. • The results indicated that the proposed prediction model achieved an MAE of less than 4/237 L/min and an MRE% of 4/842 % for predicting flow rates. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
09555986
Volume :
97
Database :
Academic Search Index
Journal :
Flow Measurement & Instrumentation
Publication Type :
Academic Journal
Accession number :
177880651
Full Text :
https://doi.org/10.1016/j.flowmeasinst.2024.102605