RESUMO
This study presents a methodology based on the dual-mode gamma densitometry technique in combination with artificial neural networks to simultaneously determine type and quantity of four different fluids (Gasoline, Glycerol, Kerosene and Fuel Oil) to assist operators of a fluid transport system in pipelines commonly found in the petrochemical industry, as it is necessary to continuously monitor information about the fluids being transferred. The detection system is composed of a 661.657 keV (137Cs) gamma-ray emitting source and two NaI(Tl) scintillation detectors to record transmitted and scattered photons. The information recorded in both detectors was directly applied as input data for the artificial neural networks. The proposed intelligent system consists of three artificial neural networks capable of predicting the fluid volume percentages (purity level) with 94.6% of all data with errors less than 5% and MRE of 1.12%, as well as identifying the pair of fluids moving in the pipeline with 95.9% accuracy.
Assuntos
Redes Neurais de Computação , Petróleo , Raios gama , FótonsRESUMO
This study presents a method based on gamma-ray densitometry using only one multilayer perceptron artificial neural network (ANN) to identify flow regime and predict volume fraction of gas, water, and oil in multiphase flow, simultaneously, making the prediction independent of the flow regime. Two NaI(Tl) detectors to record the transmission and scattering beams and a source with two gamma-ray energies comprise the detection geometry. The spectra of gamma-ray recorded by both detectors were chosen as ANN input data. Stratified, homogeneous, and annular flow regimes with (5 to 95%) various volume fractions were simulated by the MCNP6 code, in order to obtain an adequate data set for training and assessing the generalization capacity of ANN. All three regimes were correctly distinguished for 98% of the investigated patterns and the volume fraction in multiphase systems was predicted with a relative error of less than 5% for the gas and water phases.
RESUMO
This research presents a methodology for volume fraction predictions in water-gas-oil multiphase systems based on gamma-ray densitometry and artificial neural networks. The simulated geometry uses a dual-energy gamma-ray source and dual-modality (transmitted and scattered beams). The Am-241 and Cs-137 sources and two NaI(Tl) detectors have been used in this methodology. Different data from the pulse height distribution were used to train the artificial neural network to evaluate the volume fraction prediction. The MCNPX code has been used to develop the theoretical model for stratified regime and to provide data for the artificial neural network. 5-layers feed-forward multilayer perceptron using backpropagation training algorithm and General Regression Neural Networks has been used with different designs. The artificial neural network design that presented the best results of volume fraction prediction has a mean relative error below 2.0%.
RESUMO
This work presents a new methodology for density prediction of petroleum and derivatives for products' monitoring application. The approach is based on pulse height distribution pattern recognition by means of an artificial neural network (ANN). The detection system uses appropriate broad beam geometry, comprised of a (137)Cs gamma-ray source and a NaI(Tl) detector diametrically positioned on the other side of the pipe in order measure the transmitted beam. Theoretical models for different materials have been developed using MCNP-X code, which was also used to provide training, test and validation data for the ANN. 88 simulations have been carried out, with density ranging from 0.55 to 1.26gcm(-3) in order to cover the most practical situations. Validation tests have included different patterns from those used in the ANN training phase. The results show that the proposed approach may be successfully applied for prediction of density for these types of materials. The density can be automatically predicted without a prior knowledge of the actual material composition.