基于小样本数据的储层渗透率预测方法  

A Method for Reservoir Permeability Prediction Based on Small Sample Data

作　　者：李鹏飞[1] 李鹏举[2] 张强[1] 王辉[1] LI Peng-fei;LI Peng-ju;ZHANG Qiang;WANG Hui(School of Computer and Information Technology,Northeast Petroleum University,Daqing 163318,China;School of Earth Sciences,Northeast Petroleum University,Daqing 163318,China)

机构地区：[1]东北石油大学计算机与信息技术学院,黑龙江大庆163318 [2]东北石油大学地球科学学院,黑龙江大庆163318

出　　处：《计算机技术与发展》2024年第7期199-206,共8页Computer Technology and Development

基　　金：国家自然科学基金(42002138);黑龙江省自然科学基金(LH2022F008)。

摘　　要：针对Timur/Coates和SDR公式计算储层渗透率处理步骤繁琐的缺点,设计了一个实现非线性回归的单隐层前馈神经网络(single hidden layer feedforward neural network,SLFNN),该网络包含一个具有非线性激活函数的隐含层、两个线性全连接层和一个dropout层。为了防止学习过程中陷于局部最优和小样本数据集造成的过拟合,使用了Adam优化器、ReLU激活函数、何恺明均匀分布权重初始化方法和余弦退火热重启学习率调整算法。以某油田A~D四口生产井不同层位上的测井和岩心构成的小样本数据作为训练集和验证集,采用5折交叉验证方法,确定了隐含层神经元个数、初始学习率和dropout层神经元失活概率。最后以同区块E井数据作为测试集,使用4种模型(SLFNN、随机森林回归、支持向量回归和极端梯度提升回归)分别对渗透率进行了预测和对比。实验结果表明,在测试集下SLFNN模型的平均绝对误差(MAE)和决定系数(R 2)均比其他3种模型的优,说明SLFNN模型对储层渗透率的预测是有效的。A single hidden layer feedforward neural network(SLFNN)is designed to realize nonlinear regression in order to overcome the shortcomings of complicated processing steps in reservoir permeability calculation by Timur/Coates and SDR formulas.The SLFNN contains a hidden layer with a nonlinear activation function,two linear fully connected layers and a dropout layer.In order to prevent the learning process from falling into local optimum and over-fitting caused by small sample data set,Adam optimizer,ReLU activation function,Kaiming He’s uniform distribution weight initialization method and cosine annealing hot restart learning rate adjustment algorithm are used.The number of neurons in the hidden layer,initial learning rate,and inactivation probability of neurons in the dropout layer are determined by using the 5-fold cross validation method based on the small sample data composed of the NMR logging and core from different layers of four production wells from A to D in an oilfield as the training set and validation set.Finally,taking the data of Well E in the same block as the test set,the four models of SLFNN,RFR,SVR and XGBR are used to compare the permeability prediction results.The experimental results show that the MAE and R 2 of the SLFNN model are better than those of the other three models under the test set,which indicates that the SLFNN model is effective for the prediction of reservoir permeability.

关 键 词：核磁共振测井 储层渗透率 何恺明权重初始化 模型评价 相关性系数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]