An artificial neural network and a combined capacitive sensor for measuring the void fraction independent of temperature and pressure changes for a two-phase homogeneous fluid

Void fraction plays a vital role in diverse industries like oil, petrochemical, etc., which involve a wide range of fluids, including two-phase and three-phase fluids. Various procedures are used for the measurement of the void fraction, with one of the most popular being capacitance-based sensors. The characteristics of the fluid inside the pipe affect the output of this type of sensor, and every property, such as temperature, pressure, and density, plays a role. This paper presents the use of an Artificial Neural Network (ANN) and a combined capacitance-based sensor to measure the void fraction of a two-phase air-water homogeneous fluid. The aim is to develop a system that can predict void fraction independent of temperature and pressure changes. To achieve this, the COMSOL Multiphysics software was used to design and simulate two widely used sensors, concave and ring, to create a combined capacitance sensor. Simulations were conducted for the implemented sensor in different temperature ranges (275–370 K) and pressure ranges (1–500 Bar). After a large number of simulations and producing 3780 data from the combined sensor, they were used as inputs to train the proposed MLP ANN network. The presented model provides a new metering system that can accurately estimate the amount of the void fraction of a two-phase air-water homogeneous fluid independent of temperature and pressure changes and had a low error which means the MAE is equal to 4.868. © 2023 Elsevier Ltd