Search

To continuously monitor information about the transport of fluids by sequential batches in polyduct, found in the petrochemical industry, it is necessary to manage the mixing zone – transmix – that occurs when two fluids are being transported. This scenario demonstrates the need to estimate the interface region and the purity of the fluids in this region to improve the management of the pipeline and, thus, reduce associated costs. This study presents a measurement system based on the dual-modality gamma densitometry technique in combination with a deep neural network with seven hidden layers to predict the purity level of four different fluids (Gasoline, Glycerol, Kerosene and Oil Fuel) in the transmix. The detection geometry is composed of a137Cs radioactive source (emitting gamma rays of 661.657 keV) and two NaI(Tl) scintillator detectors to record the transmitted and scattered photons. The study was performed by computer simulations using the MCNP6 code, and the information recorded in the detectors was used as input data for training and evaluating the deep neural network. The proposed intelligent measurement system is able to predict the purity level of fluids with errors with mean squared error values below 1.4 and mean absolute percentage error values below 5.73% for all analyzed data. • A methodology to identify the interface region of petroleum by-products transportation in polyducts. • The identification of the interface region was performed for several petroleum by-products. • This study has been used the MCNP6 code and deep neural network. • The geometry consists of a gamma-ray source and uses dual-modality measurements. • The static models used for a stratified flow regime on the biphasic system were developed using the MCNP6. [ABSTRACT FROM AUTHOR]

Scale formation is one of the major problems in the oil industry as it can accumulate on the surface of the pipelines, which could even fully block the fluids' passage. It was developed a methodology to detect and quantify the maximum thickness of eccentric scale inside pipelines using nuclear techniques and an artificial neural network. The measurement procedure is based on gamma-ray scattering using NaI(Tl) detectors and a137Cs radiation source that emits gamma-rays of 662 keV. The simulations considered an annular flow regime composed of barium sulfate scale, oil, saltwater and gas, and three percentages of these fluids were used. In the present investigation, a study of detectors configuration was carried out to improve the measurement geometry and the simulations were made using the MCNP6 code, which is a mathematical code based on the Monte Carlo method. The counts registered in the detectors were used as input data to train a deep neural network (DNN) that uses rectifier activation functions instead of the usually sigmoid-based ones. In addition, a hyperparameters search was made using open software to develop the final DNN architecture. Results showed that the best detector configuration was able to predict 100% of the patterns with the maximum relative error of 5%. Moreover, the achieved mean absolute percentage error was 0.42% and the regression coefficient was 0.99996 for all data. The results are promising and encourage the use of DNN to calculate inorganic scale regardless of the fluids volume fraction inside pipelines. • Prediction of the maximum eccentric scale thickness using gamma-ray scattering. • Application of deep neural network using hyperparameters search software. • The prediction is made regardless of the fluids volume fraction in the multiphase system. • Measurement geometry is composed of two detectors and a137Cs radiation source. • Patterns of the eccentric scale thickness were simulated using the MCNP6 code. [ABSTRACT FROM AUTHOR]

A multiphase flow is defined as the transport of two or more fluids with different properties flowing together inside a pipeline. After offshore oil production, it is necessary to control the amount of transported fluids based on flow rate measurements. Therefore, in this study, we developed a simulation method for predicting the volume fraction and calculating the superficial velocity for a two-phase flow based on radioactive particle tracking, which involves using a sealed radiation source inside the pipeline in order to obtain volume fraction measurements. The test section for the multiphase flow comprised oil and saltwater under a stratified flow regime, with a polyvinyl chloride pipe, four NaI(Tl) detectors, and a137Cs radioactive particle that emitted gamma-rays at 662 keV. Simulations were conducted using the MCNP6 code, which is a mathematical code based on the Monte Carlo method. Volume fraction predictions were obtained using a multilayer perceptron neural network with a backpropagation algorithm. The novel feature of this method is the combination of radioactive particle tracking with an artificial neural network in order to predict volume fractions in multiphase flows. The results showed that 91.65% of the predicted patterns were within 5% of the relative error. In addition, the time delay was determined using the cross-correlation function to obtain the superficial velocity in three different volume fractions, which allowed each phase flow rate to be calculated in these cases. • Application of radioactive particle tracking to multiphase flows. • Volume fraction predicted using an artificial neural network. • Flow velocity calculated using a cross-correlation function. • Flow rate calculated in a stratified flow regime. [ABSTRACT FROM AUTHOR]

Radioactive particle tracking is a nuclear technique that tracks a sealed radioactive particle inside a volume through a mathematical location algorithm, which is widely applied in many fields such as chemical and civil engineering in hydrodynamics flows. It is possible to reconstruct the trajectory of the radioactive particle using a traditional mathematical algorithm or artificial intelligence methods. In this paper, the traditional algorithm is based on solving a minimization problem between the simulated events and a calibration dataset, and it was written using C++ language. The artificial intelligence method is represented by a deep neural network, in which hyperparameters were defined using a Python optimization library called Optuna. This paper aims to compare the potentiality of both methods to evaluate the accuracy of the radioactive particle tracking technique. This study proposes a simplified model of a concrete mixer, six NaI(Tl) detectors, and a137Cs sealed radioactive particle. The simulated measurement geometry and the dataset (3615 patterns) were developed using the MCNPX code, which is a mathematical code based on the Monte Carlo Method. The results show a mean absolute percentage error (MAPE) of 20.81%, 10.33%, and 16.84% for x, y and z coordinates, respectively, for the traditional algorithm. For the deep neural network, MAPE is 6.87%, 2.70%, and 22.79% respectively for x, y and z coordinates. In addition, an investigation is carried out to analyze whether the size of the calibration dataset influences the performance of both methods. • Comparison of location algorithms applied in a radioactive particle tracking system. • RPT system is a simplified concrete mixer, six NaI(Tl) detectors and 137Cs source. • Traditional algorithm was written in C++ and is based on solving a minimization problem. • Deep learning model is represented by a deep neural network developed in Python. • Dataset with 3615 patterns was developed using the MCNPX code. [ABSTRACT FROM AUTHOR]

In the oil industry, during the production of oil and gas, barium sulfate (BaSO 4) scale may occur on the inner walls of the pipelines leading to the reduction of the internal diameter, making the fluids' passage difficult and complicating the calculation of the fluids volume fraction. This paper presents a methodology to predict volume fraction of fluids and BaSO 4 scale thickness from obtaining spectra of two NaI(Tl) detectors that record the transmitted and scattered beams of gamma-rays. Theoretical models for a multiphase annular flow regime (gas-saltwater-oil-scale) were developed using MCNP6 code, which is a mathematical code based on the Monte Carlo method. The simulated data was used to train a deep neural network (DNN) to predict the volume fraction of gas, saltwater and oil, and the concentric scale thickness. A Python optimization library called Optuna was used for the hyperparameters search to design the DNN architecture. The methodology presented great results, especially for scale thickness prediction. Although the results for saltwater did not reach the same level, it was still possible to predict approximately 70% of the patterns up to 10% relative error. This achievement indicates the possibility to calculate the volume fraction of fluids and the concentric scale thickness in the offshore oil industry using gamma densitometry and deep learning models. • Prediction of the volume fraction of fluids and scale in an annular multiphase system. • Methodology based on transmitted and scattered beams of gamma-rays (dual-modality). • Application of deep neural network using Python hyperparameters library. • Dataset was developed using the MCNP6 code. [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]