Related Experiment Video
Updated: Jul 19, 2025
05:11
High-precision Electromagnetic Flowmeter with Empty Pipe Detection via Complex Programmable Logic Device-based Waveform Recognition
Published on: June 27, 2025
60
Intelligent Measuring of the Volume Fraction Considering Temperature Changes and Independent Pressure Variations for
Ramy Mohammed Aiesh Qaisi1, Farhad Fouladinia2, Abdulilah Mohammad Mayet3
1Department of Electrical and Electronics Engineering, College of Engineering, University of Jeddah, Jeddah 21589, Saudi Arabia.
Sensors (Basel, Switzerland)
|August 12, 2023
Summary
This study introduces a new system using an 8-electrode sensor and a Multilayer Perceptron (MLP) network to accurately measure void fraction in two-phase fluids. The method effectively predicts air and water fractions, even with temperature variations.
Area of Science:
- * Fluid dynamics and multiphase flow measurement.
- * Application of artificial intelligence in industrial sensing.
Background:
- * Accurate measurement of void fraction is crucial for industries utilizing two-phase fluids like oil and petrochemicals.
- * Capacitance-based sensors are popular for void fraction measurement due to their non-intrusive nature.
- * Artificial Neural Networks (ANN) have significantly improved the accuracy of measurement techniques.
Purpose of the Study:
- * To present a novel metering system for predicting air and water volume fractions in homogeneous two-phase fluids.
- * To develop a Multilayer Perceptron (MLP) network integrated with an 8-electrode sensor for void fraction measurement.
- * To ensure the system's ability to predict void fraction independently of pressure variations, considering temperature changes.
Main Methods:
- * Utilized an 8-electrode capacitance-based sensor.
- * Developed and trained a Multilayer Perceptron (MLP) network using COMSOL Multiphysics simulation data.
- * Simulated temperature variations from 275 to 370 K and pressure from 1 to 500 Bars.
Main Results:
- * The proposed MLP network accurately predicts void fraction.
- * Achieved a low Mean Absolute Error (MAE) of 0.38 for void fraction prediction.
- * The system demonstrated independence from pressure variations while accounting for temperature effects.
Conclusions:
- * The developed 8-electrode sensor and MLP network system offers a precise method for measuring void fraction in two-phase fluids.
- * The system's ability to predict void fraction accurately under varying temperatures and pressures enhances its industrial applicability.
- * This approach represents a significant advancement in non-intrusive void fraction measurement techniques.
