Artificial neural network (ANN) modeling of dynamic effects on two-phase flow in homogenous porous media
Artificial neural network (ANN) modeling of dynamic effects on two-phase flow in homogenous porous media
复制标题
DOI：
10.2166/hydro.2012.119
复制
发表时间：
2013-04
影响因子：
2.7
通讯作者：
N. Hanspal;Babatunde A. Allison;Lipika Deka;D. Das
中科院分区：
文献类型：
--
作者：
N. Hanspal;Babatunde A. Allison;Lipika Deka;D. Das
多孔介质中两相流的动力效应由动力系数τ表示，它取决于许多因素（例如介质和流体性质）。在数学模型中以参数方式改变这些参数以计算τ会导致大量的时间和计算成本。为了解决这个问题，我们提出了一种基于人工神经网络（ANN）的技术，用于预测影响流动的多孔介质和流体的物理参数范围内的τ。用于训练人工神经网络算法的数据已经从以前的建模研究中获得。据观察，人工神经网络建模可以适当地表征介质和流体性质的变化之间的关系，从而确保可靠的预测动态系数作为含水饱和度的函数。我们的研究结果表明，一个双隐藏层人工神经网络相比，单隐藏层人工神经网络模型进行的大多数性能测试的表现更好。虽然单隐层神经网络模型可以可靠地预测复杂的动态系数（如含水饱和度关系）在高含水饱和度含量，双隐层神经网络模型优于在低含水饱和度含量。在所有的情况下，单和双隐藏层人工神经网络模型是更好的预测相比，回归模型在这项工作中尝试。
The dynamic effect in two-phase flow in porous media indicated by a dynamic coefficient τ depends on a number of factors (e.g. medium and fluid properties). Varying these parameters parametrically in mathematical models to compute τ incurs significant time and computational costs. To circumvent this issue, we present an artificial neural network (ANN)-based technique for predicting τ over a range of physical parameters of porous media and fluid that affect the flow. The data employed for training the ANN algorithm have been acquired from previous modeling studies. It is observed that ANN modeling can appropriately characterize the relationship between the changes in the media and fluid properties, thereby ensuring a reliable prediction of the dynamic coefficient as a function of water saturation. Our results indicate that a double-hidden-layer ANN network performs better in comparison to the single-hidden-layer ANN models for the majority of the performance tests carried out. While single-hidden-layer ANN models can reliably predict complex dynamic coefficients (e.g. water saturation relationships) at high water saturation content, the double-hidden-layer neural network model outperforms at low water saturation content. In all the cases, the single- and double-hidden-layer ANN models are better predictors in comparison to the regression models attempted in this work.