Determining the amount of void fraction of multiphase flows in pipelines of the oil, chemical and petrochemical industries is one of the most important challenges. Performance of capacitance based two phase flow meters highly depends on the fluid properties. Fluctuation of the liquid phase properties such as density, due to temperature and pressure changes, would cause massive errors in determination of the void fraction. A common approach to fix this problem is periodic recalibration of the system, which is a tedious task. The aim of this study is proposing a method based on artificial intelligence (AI), which offers the advantage of intelligent measuring of the void fraction regardless of the liquid phase changes without the need for recalibration. To train AI, a data set for different liquid phases is required. Although it is possible to obtain the required data from experiments, it is time-consuming and also incorporates its own specific safety laboratory consideration, particularly working with flammable liquids such as gasoline, oil and gasoil. So, COMSOL Multiphysics software was used to model a homogenous regime of two-phase flow with five different liquid phases and void fractions. To validate the simulation geometry, initially an experimental setup including a concave sensor to measure the capacitance by LCR meter for the case that water used as the liquid phase, was established. After validation of the simulated geometry for concave sensor, a ring sensor was also simulated to investigate the best sensor type. It was found that the concave type has a better sensitivity. Therefore, the concave type was used to measure the capacitance for different liquid phases and void fractions inside the pipe. Finally, simulated data were used to train a Multi-Layer Perceptron (MLP) neural network model in MATLAB software. The trained MLP model was able to predict the void fraction independent of the liquid phase density changes with a Mean Absolute Error (MAE) of 1.74.

Measuring the void fraction of different multiphase flows in various fields such as gas, oil, chemical, and petrochemical industries is very important. Various methods exist for this purpose. Among these methods, the capacitive sensor has been widely used. The thing that affects the performance of capacitance sensors is fluid properties. For instance, density, pressure, and temperature can cause vast errors in the measurement of the void fraction. A routine calibration, which is very grueling, is one approach to tackling this issue. In the present investigation, an artificial neural network (ANN) was modeled to measure the gas percentage of a two-phase flow regardless of the liquid phase type and changes, without having to recalibrate. For this goal, a new combined capacitance-based sensor was designed. This combined sensor was simulated with COMSOL Multiphysics software. Five different liquids were simulated: oil, gasoil, gasoline, crude oil, and water. To estimate the gas percentage of a homogeneous two-phase fluid with a distinct type of liquid, data obtained from COMSOL Multiphysics were used as input to train a multilayer perceptron network (MLP). The proposed neural network was modeled in MATLAB software. Using the new and accurate metering system, the proposed MLP model could predict the void fraction with a mean absolute error (MAE) of 4.919.

Two-phase fluids are widely utilized in some industries, such as petrochemical, oil, water, and so on. Each phase, liquid and gas, needs to be measured. The measuring of the void fraction is vital in many industries because there are many two-phase fluids with a wide variety of liquids. A number of methods exist for measuring the void fraction, and the most popular is capacitance-based sensors. Aside from being easy to use, the capacitance-based sensor does not need any separation or interruption to measure the void fraction. In addition, in the contemporary era, thanks to Artificial Neural Networks (ANN), measurement methods have become much more accurate. The same can be said for capacitance-based sensors. In this paper, a new metering system utilizing an 8-electrode sensor and a Multilayer Perceptron network (MLP) is presented to predict an air and water volume fractions in a homogeneous fluid. Some characteristics, such as temperature, pressure, etc., can have an impact on the results obtained from the aforementioned sensor. Thus, considering temperature changes, the proposed network predicts the void fraction independent of pressure variations. All simulations were performed using the COMSOL Multiphysics software for temperature changes from 275 to 370 degrees Kelvin. In addition, a range of 1 to 500 Bars, was considered for the pressure. The proposed network has inputs obtained from the mentioned software, along with the temperature. The only output belongs to the predicted void fraction, which has a low MAE equal to 0.38. Thus, based on the obtained result, it can be said that the proposed network precisely measures the amount of the void fraction.

Multiphase fluids are common in many industries, such as oil and petrochemical, and volume fraction measurement of their phases is a vital subject. Hence, there are lots of scientists and researchers who have introduced many methods and equipment in this regard, for example, photon attenuation sensors, capacitance-based sensors, and so on. These approaches are non-invasive and for this reason, are very popular and widely used. In addition, nowadays, artificial neural networks (ANN) are very attractive in a lot of fields and this is because of their accuracy. Therefore, in this paper, to estimate volume proportion of a three-phase homogeneous fluid, a new system is proposed that contains an MLP ANN, standing for multilayer perceptron artificial neural network, a capacitance-based sensor, and a photon attenuation sensor. Through computational methods, capacities and mass attenuation coefficients are obtained, which act as inputs for the proposed network. All of these inputs were divided randomly in two main groups to train and test the presented model. To opt for a suitable network with the lowest rate of mean absolute error (MAE), a number of architectures with different factors were tested in MATLAB software R2023b. After receiving MAEs equal to 0.29, 1.60, and 1.67 for the water, gas, and oil phases, respectively, the network was chosen to be presented in the paper. Hence, based on outcomes, the proposed approach’s novelty is being able to predict all phases of a homogeneous flow with very low error.