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%.

这项研究提出了一种基于伽马射线密度法和人工神经网络的水-油气多相系统中体积分数预测的方法。模拟的几何体使用双能量伽马射线源和双模态（透射光束和散射光束）。该方法中使用了Am-241和Cs-137源以及两个NaI（Tl）检测器。来自脉冲高度分布的不同数据用于训练人工神经网络以评估体积分数预测。MCNPX代码已用于开发分层方案的理论模型，并为人工神经网络提供数据。使用反向传播训练算法和通用回归神经网络的5层前馈多层感知器已用于不同的设计。