基于卷积神经网络的砂岩数字岩心绝对渗透率计算方法  

Calculation methods for absolute permeability of sandstone digital cores based on convolutional neural networks

作　　者：隋微波[1] 程思 SUI Weibo;CHENG Si(College of Petroleum Engineering,China University of Petroleum(Beijing),Beijing City,102249,China)

机构地区：[1]中国石油大学(北京)石油工程学院,北京102249

出　　处：《油气地质与采收率》2022年第1期128-136,共9页Petroleum Geology and Recovery Efficiency

摘　　要：基于卷积神经网络深度学习理论探讨了砂岩数字岩心绝对渗透率的计算方法和相关的重要影响因素。研究选取了3种具有代表性的砂岩样品包括Bentheimer砂岩、Berea砂岩和Doddington砂岩的数字岩心,比较了采用N-S方程法和孔隙网络模型法计算绝对渗透率的差异性;探讨了对砂岩样品进行切割生成子样品时,3种不同子样品尺寸对绝对渗透率均值和不同方向渗透率分量的影响。在此基础上基于200×200×200尺寸对原砂岩数字岩心进行切割获取子样品,并对全部子样品进行微观渗流模拟计算获得相应的绝对渗透率,建立了用于深度学习的数字岩心子样品数据库。基于该数据库讨论了卷积神经网络系统搭建过程中的关键参数如学习率和丢弃率等的选择方法。训练学习后对测试集子样品进行测试,预测值与真实值差异在5%以内,证明了该方法的有效性。On the basis of the convolutional neural network(CNN)of deep learning theory,the calculation methods for the absolute permeability of sandstone digital cores and related important influencing factors were discussed.The study selected three representative sandstone samples,including digital cores of Bentheimer sandstone,Berea sandstone,and Doddington sandstone.First,the permeability of these samples was calculated through the N-S equation and the pore network model separately,and the difference was compared.Then,we explored the influence of three different subsample sizes on the mean absolute permeability and permeability components in different directions when the sandstone samples were cut into subsamples.On this basis,the original sandstone digital cores were cut by the size of 200×200×200 to obtain subsamples,and all subsamples were subjected to microscopic seepage simulation and calculations to produce the corresponding absolute permeability.Finally,the digital core subsample database for deep learning was constructed.Given this database,we discussed the selection methods of key parameters for CNN system construction,such as learning rates and dropout rates.Upon training and learning,the subsamples of the testing set were tested,and the difference between the predicted values and the true values was within 5%,which proves the effectiveness of the method.

关 键 词：卷积神经网络 砂岩 数字岩心 绝对渗透率 渗透率分量 

分 类 号：TE319[石油与天然气工程—油气田开发工程]