Application of Neural Network and Dual-Energy Radiation-Based Detection Techniques to Measure Scale Layer Thickness in Oil Pipelines Containing a Stratified Regime of Three-Phase Flow

Over time, oil pipes are scaled, which causes problems such as a reduction in the effective diameter of pipe, an efficiency reduction, waste energy, etc. Determining exact value scale inside pipe is very important order to take timely action and prevent mentioned problems. One accurate detection methodology use non-invasive systems based on gamma-ray attenuation. For this purpose, research, thickness system consisting test dual-energy gamma source (241Am 133Ba radioisotopes), two sodium iodide detectors were simulated using Monte Carlo N Particle (MCNP) code. In three-phase flow water, gas, was stratified regime volume percentages range from 10% 80%. addition, with different thicknesses 0 3 cm placed rays irradiated onto pipe; other side photon intensity recorded by detectors. A total 252 simulations performed. From signal received detectors, four characteristics extracted, named Photopeaks 241Am for first second After training many Multi-Layer Perceptron(MLP) neural networks various architectures, it found that structure hidden layers could predict connection between input, extracted features, output, thickness, Root Mean Square Error (RMSE) less than 0.06. This low error guarantees effectiveness proposed method usefulness petrochemical industry.