Search

Abstract: This work presents a new methodology for flow regimes identification and volume fraction predictions in water–gas–oil multiphase systems. The approach is based on gamma-ray pulse height distributions (PHDs) pattern recognition by means the artificial neural networks (ANNs). The detection system uses appropriate fan beam geometry, comprised of a dual-energy gamma-ray source and two NaI(Tl) detectors adequately positioned in order measure transmitted and scattered beams, which makes it less dependent on the regime flow. The PHDs are directly used by the ANNs without any parameterization of the measured signal. The system comprises four ANNs. The first identifies the flow regime and the other three ANNs are specialized in volume fraction predictions for each specific regime. The ideal and static theoretical models for annular, stratified and homogeneous regimes have been developed using MCNP-X mathematical code, which was used to provide training, test and validation data for the ANNs. The energy resolution of NaI(Tl) detectors is also considered on the mathematical model. The proposed ANNs could correctly identify all three different regimes with satisfactory prediction of the volume fraction in water–gas–oil multiphase system, demonstrating to be a promising approach for this purpose. [Copyright &y& Elsevier]

The methodology presented in this study is based on a 149.5 keV X-ray beam and two planar germanium detectors for X-ray transmission and scattering measurements for prediction of volume fractions in a three-phase system. Fluid volume fractions have been modeled using the MCNP6 code for an annular flow regime. A mathematical algorithm based on an artificial neural network was used to correlate the energy spectra from both detectors with the fluids volume fractions. The pulse height distributions obtained by the detectors are used as input data of the network that outputs the volume fractions of gas and water. The mean relative error, using the procedure presented here, for all data, was below 2.5% for both phases investigated. These results show that the methodology based on an X-ray beam has the potential to be used with flow meters. • An artificial neural network was used to predict volume fraction of gas, water, and oil. • X-ray beam and two planar germanium detectors for X-ray transmission and scattering measurements for prediction of volume fractions. • Fluid volume fractions have been modeled using the MCNP6 code for an annular flow regime. • The spectra obtained by the detectors are used as input data of the network that outputs gas and water volume fractions. [ABSTRACT FROM AUTHOR]

• The proposed geometry composes gamma-rays and two NaI(Tl) detectors. • Different thicknesses and relative positions of scale for the annular flow regime were modeled using the MCNP code. • A Backpropagation 5-layer perceptron network was used for scale prediction. • The gamma-ray scattering was used to quantify the maximum thickness of eccentric scales (BaSO 4). • The maximum scale was predicted independently of its position inside the tube and the presence of the fluids. This study investigates a methodology to study the deposition of barium sulfate scales (BaSO 4) commonly found in the oil industry; it causes an internal diameter decrease, making it difficult for the flow. A measurement procedure was elaborated on gamma-ray scattering with three NaI(Tl) detectors and a 137Cs gamma-ray source to detect and quantify the maximum thickness of eccentric scale. The detectors data were used to train the artificial neural network for the prediction of the maximum scale thickness values regardless of oil, saltwater, gas and scale inside the tube. A data subset for training and evaluation of the artificial neural network generalization capability was generated using the MCNP6 code. Different thicknesses and positions of the maximum scale value were considered. The results show that more than 90% of the patterns presented relative errors lower than ±10%. [ABSTRACT FROM AUTHOR]

This paper presents the simulation of a water-gas biphasic system in annular and stratified flow regimes using a neutron beam from a241Am–Be radiation source. The objective is to evaluate the potential of prompt gamma neutron activation analysis (PGNAA) and artificial intelligence-based algorithms in flow measurements. A measurement geometry consisted of a neutron flat source with parallel emission and a spherical detector was developed using the MCNP6 code. Prompt gamma rays spectra were used as input data of a feed-forward multilayer perceptron (MLP) artificial neural network aiming to predict void fraction and to identify the investigated flow regimes. The results showed that the MLP was able to predict void fraction, for both flow regimes, with mean absolute percentage error within 1.58%. In addition, the same MLP achieved 100% of success in flow regime identification. Therefore, it is possible to combine PGNAA with MLP in order to investigate flow characteristics. • Simulated water-gas system using neutron beam from a241Am–Be radiation source. • Neutron source with parallel emission and a spherical detector using MCNP6 code. • Neutron spectra were used to predict void fraction and to identify flow regimes. • Prompt gamma neutron activation analysis and AI to investigate flow characteristics. [ABSTRACT FROM AUTHOR]

Metal alloys are widely used in the aerospace, biological, civil and automotive industries, thus being very important to develop techniques to identify these alloys. Nuclear technique based on gamma densitometry is a non-invasive technique that is able to identify metal alloys using a radiation source and a scintillator detector. The measurement geometry and the dataset for training an artificial neural network were developed using the MCNP6 code. Therefore, this study proposes the thickness prediction of five aluminum alloys (2024-O, 2090-T83, 3003, 5086-O and 7075-O), a titanium alloy, and two steel carbon alloys (stainless 302 and stainless 316) ranging from 2 to 50 mm for four different gamma-ray radiation energies using gamma transmission and artificial neural network. A study to evaluate the reliability of the results was performed by analyzing the uncertainties in the data from the simulation with the MCNP6 code and the data predicted by ANN. The results indicate that it was possible to predict all the alloys thicknesses using the energy of 137Cs radiation source, in which more than 96% of the cases with 5% of relative error, even for a group of alloys with very close densities values as aluminum alloys. • Prediction of metal alloys' thicknesses using gamma transmission and ANN. • Application of neural network using backpropagation algorithm and cross-validation. • The proposed geometry investigates the use of one detector and four radiation sources. • A total of 1040 simulations with different thicknesses and metal alloys were performed. • Investigations and comparisons among different ANN designs and training strategies. [ABSTRACT FROM AUTHOR]

A recent investigation proposed a simulated radioactive particle tracking (RPT) system using eight scintillator detectors in order to predict instantaneous positions of a radioactive particle inside a concrete mixer using an artificial neural network as a location algorithm. In the context of RPT, the aim of the present study is to propose an optimization in the number of detectors in a single-phase flow RPT system. The new detection geometry consists of an array of six NaI(Tl) detectors, a 137Cs point source with isotropic emission of gamma-rays (radioactive particle) and a polyvinyl chloride mixer filled with concrete made with Portland cement as a homogenous flow regime. Another feature of this study is the use of MCNP6 code, which is based on Monte Carlo Method. In addition, three feed-forward multilayer perceptron networks with different configuration are tested as a location algorithm. All three networks showed good statistical results and the root mean square error is 1.18 in the worst scenario. The results also showed an agreement with previous study, which indicates that this methodology reducing two detectors works satisfactorily and maintain a good accuracy in position prediction. • Optimization of the detection system reducing two detectors. • Radioactive Particle Tracking methodology developed using MCNP6 code. • An artificial neural network predicts the position of the radioactive particle. • System based on RPT to evaluate industrial agitators in a homogeneous flow regime. [ABSTRACT FROM AUTHOR]