基于F-score协同支持向量机算法的孔隙结构类别测井识别  

Pore structure categories logging identification based on F-score assisted with support vector machine algorithm

作　　者：路研 刘宗宾 李超 王亚 宋洪亮 于阳 LU Yan;LIU Zongbin;LI Chao;WANG Ya;SONG Hongliang;YU Yang(Tianjin Branch of CNOOC China Limited,Tianjin 300452,China;School of Geosciences in China University of Petroleum(East China),Qingdao 266580,China)

机构地区：[1]中海石油(中国)有限公司天津分公司,天津300452 [2]中国石油大学(华东)地球科学与技术学院,山东青岛266580

出　　处：《中国石油大学学报（自然科学版）》2024年第6期37-47,共11页Journal of China University of Petroleum(Edition of Natural Science)

基　　金：国家科技重大专项(2017ZX05009001)。

摘　　要：以渤海湾盆地G油田沙四上亚段的低渗透砂岩为研究对象,综合运用岩相学、高压压汞、核磁共振及岩心物性分析将岩心样本的孔隙结构划分为4种类型(Ⅰ、Ⅱ、Ⅲ、Ⅳ)。在此基础上,通过岩心标定测井的方式并结合支持向量机算法和特征筛选方法(F-score)建立孔隙结构类型的测井识别模型,并选取215组测试样本开展模型泛化性能验证。在单井孔隙结构类型的测井识别基础上,采用序贯高斯模拟的方法建立G油田主力含油层系孔隙结构类型的三维地质模型,实现有利孔渗发育带的预测。结果表明:215组测试样本中仅22组样本被错判为邻类样本,测试样本的整体正判率为89.77%。基于F-score协同支持向量机算法的孔隙结构类型的预测模型与早期的统计学方法和神经网络算法相比,展现出更好的预测性能。This paper focuses on the low-permeability sandstones of the upper Es 4 member in the Boxing Sag,where pore structures in core samples were categorized into four types(Ⅰ,Ⅱ,ⅢandⅣ)based on poroperm analysis,mercury injection capillary pressure,nuclear magnetic resonance,and petrophysical property analysis.Using this classification,a logging identification model for pore structures was established by calibrating logging samples with core samples and applying the support vector machine(SVM)algorithm with an F-score feature selection.The model's performance was validated using 215 test samples.Based on the logging identification of pore structures from single wells,a three-dimensional geological model of pore structure types for key oil-bearing layers in the G oilfield was developed using sequential Gaussian simulation,enabling the prediction of favorable porosity and permeability zones.The results indicate that there are only 22 misjudgments in 215 test samples,all of which were among adjacent samples,achieving a prediction accuracy of 89.77%.Compared with the early statistical methods and neural network algorithms,the pore structure prediction model established with SVM-assisted F-score algorithm exhibits superior predictive performance.

关 键 词：渤海湾盆地 低渗透砂岩 孔隙结构 支持向量机 

分 类 号：TE122.2[石油与天然气工程—油气勘探]