基于深度神经网络模拟复杂多孔介质中两相驱替过程

Deep learning for pore-scale two-phase flow:Modelling drainage in realistic porous media

为了预测复杂孔隙结构中毛管压力主导下两相流排驱过程中的流体分布,从仿真多孔介质和岩石CT图像中抽取子样本,并采用孔隙形态模拟器(PMS)生成流体分布,以创建多样化的数据集,将距离图及像素大小、界面张力、接触角、压力作为输入参数,通过改造、训练、评估卷积神经网络(CNN)、递归神经网络(RNN)和视觉转换器(ViT),优选用于预测流体分布的模型。模拟分析表明,常用的卷积和递归神经网络在捕捉流体连通性方面存在不足。基于ViT构建了一个高维视觉转换器(HD-ViT),该转换器先忽略孔隙的空间位置仅根据其大小进行排驱,再在后处理步骤中追加流体连通要求,这种方法允许在任何坐标方向预设出入口,并使用不同尺寸和不同分辨率的图像进行渗流状态推断。通过在砂岩和碳酸盐岩大图像上验证,并与微流控驱替测试的实验结果比较,证实了HD-ViT模型的有效性、精确性和速度优势,且在捕捉孔隙尺度三维流动方面存在较大的潜力。

In order to predict phase distributions within complex pore structures during two-phase capillary-dominated drainage,we select subsamples from computerized tomography(CT)images of rocks and simulated porous media,and develop a pore morphology-based simulator(PMS)to create a diverse dataset of phase distributions.With pixel size,interfacial tension,contact angle,and pressure as input parameters,convolutional neural network(CNN),recurrent neural network(RNN)and vision transformer(ViT)are transformed,trained and evaluated to select the optimal model for predicting phase distribution.It is found that commonly used CNN and RNN have deficiencies in capturing phase connectivity.Subsequently,we develop a higher-dimensional vision transformer(HD-ViT)that drains pores solely based on their size,regardless of their spatial location,with phase connectivity enforced as a post-processing step.This approach enables inference for images of varying sizes and resolutions with inlet-outlet setup at any coordinate directions.We demonstrate that HD-ViT maintains its effectiveness,accuracy and speed advantage on larger sandstone and carbonate images,compared with the microfluidic-based displacement experiment.In the end,we train and validate a 3D version of the model.