Application of Feature Extraction and Artificial Intelligence Techniques for Increasing the Accuracy of X-ray Radiation Based Two Phase Flow Meter

The increasing consumption of fossil fuel resources in the world has placed emphasis on flow measurements oil industry. This generated a growing niche flowmeter In this regard, study, an artificial neural network (ANN) and various feature extractions have been utilized to enhance precision X-ray radiation-based two-phase flowmeters. detection system proposed article comprises tube, NaI detector record photons, Pyrex-glass pipe, which is between source. To model mentioned geometry, Monte Carlo MCNP-X code was utilized. Five features time domain were derived from collected data be used as input. Multi-Layer Perceptron (MLP) applied approximate function related input-output relationship. Finally, introduced approach able correctly recognize pattern predict volume fraction flow’s components with root mean square error (RMSE), absolute (MAE), percentage (MAPE) less than 0.51, 0.4 1.16%, respectively. obtained study better those reported previous works.