Wu Jinlong, Yin Xiaolong, Xiao Heng
Kevin T. Crofton Department of Aerospace and Ocean Engineering, Virginia Tech, Blacksburg, VA 24060, USA.
Department of Petroleum Engineering, Colorado School of Mines, Golden CO 80401, USA.
Sci Bull (Beijing). 2018 Sep 30;63(18):1215-1222. doi: 10.1016/j.scib.2018.08.006. Epub 2018 Aug 22.
Fast prediction of permeability directly from images enabled by image recognition neural networks is a novel pore-scale modeling method that has a great potential. This article presents a framework that includes (1) generation of porous media samples, (2) computation of permeability via fluid dynamics simulations, (3) training of convolutional neural networks (CNN) with simulated data, and (4) validations against simulations. Comparison of machine learning results and the ground truths suggests excellent predictive performance across a wide range of porosities and pore geometries, especially for those with dilated pores. Owning to such heterogeneity, the permeability cannot be estimated using the conventional Kozeny-Carman approach. Computational time was reduced by several orders of magnitude compared to fluid dynamic simulations. We found that, by including physical parameters that are known to affect permeability into the neural network, the physics-informed CNN generated better results than regular CNN. However, improvements vary with implemented heterogeneity.
通过图像识别神经网络直接从图像快速预测渗透率是一种具有巨大潜力的新型孔隙尺度建模方法。本文提出了一个框架，包括：（1）生成多孔介质样本；（2）通过流体动力学模拟计算渗透率；（3）使用模拟数据训练卷积神经网络（CNN）；以及（4）与模拟结果进行验证。机器学习结果与真实情况的比较表明，在广泛的孔隙率和孔隙几何形状范围内，尤其是对于具有扩张孔隙的情况，具有出色的预测性能。由于这种非均质性，无法使用传统的柯曾尼-卡曼方法估计渗透率。与流体动力学模拟相比，计算时间减少了几个数量级。我们发现，通过将已知影响渗透率的物理参数纳入神经网络，基于物理信息的CNN比常规CNN产生了更好的结果。然而，改进程度因实现的非均质性而异。
