裴家学,郭晗,周立国,张甲明,田涯,李皓,李雪英,隋强
PEI Jiaxue,GUO Han,ZHOU Liguo,ZHANG Jiaming,TIAN Ya,LI Hao,LI Xueying,SUI Qiang

• 1:中国石油辽河油田公司
• 2:东北石油大学地球科学学院

摘要(Abstract)：

开鲁盆地陆西凹陷九佛堂组储层复杂岩性与测井曲线之间存在非线性响应关系，致使常规岩性识别方法存在多解性和不确定性。为此引入4个与储层岩性相关的复合测井参数，增强测井曲线描述复杂岩性非线性响应特征能力；结合高斯核函数和多项式核函数各自的优良特性，构建组合核函数，改善核主元分析方法的全局识别能力；采用K-折交叉验证法确定合理的核半径参数，从而建立一套基于多复合测井参数表征的复杂岩性核主元识别方法。实际岩性数据测试分析结果表明，引入多复合测井参数后，复杂岩性数据在核主元空间具有显著的线性可分性，岩性相对位置集中、固定且区带划分标准明确，表明该岩性划分方法具有良好的稳定性，后验识别符合率92.7%以上，证明该方法在复杂岩性识别中的有效性。研究成果为开鲁盆地复杂岩性区的岩性精确识别提供了一种新的技术思路。
Nonlinear response relationship between complex lithology and logging curves of Jiufotang Formation reservoir in Luxi Sag of Kailu Basin causes ambiguity and uncertainty of conventional lithology identification methods.Therefore, 4 composite logging parameters related to reservoir lithology are introduced to enhance the capability of logging curves to describe nonlinear response characteristics of complex lithology. Combining with excellent characteristics of Gaussian kernel function and polynomial kernel function, a composite kernel function is constructed to improve global identification capability of kernel principal component analysis method. K-fold cross validation method is used to determine rational kernel radius parameters, thereby establishing a set of complex lithology kernel principal component identification methods based on characterization of multi-composite logging parameters. Analysis results of actual lithology data test show that, after introduction of multi-composite parameters, complex lithology data have significant linear separability in kernel principal component space, with lithology relative position concentrated, fixed and zones division criteria clear, indicating high stability of this lithology classification method.Posteriori identification coincidence rate is >92.7%, proving the effectiveness of this method in complex lithology identification. The research provides new technical idea for accurate identification of lithologies in complex lithological zone of Kailu Basin.

关键词(KeyWords)： 核主元分析;岩性识别;复合测井参数;组合核函数;K-折交叉验证法
analysis of kernel principal component;lithology identification;composite logging parameter;mixed kernel function;K-fold cross validation method

Abstract:

Keywords:

基金项目(Foundation): 黑龙江省自然科学基金联合引导项目“基于马尔科夫链的厚度随机分布薄互层时频响应机理研究”（LH2021D010）

作者(Author): 裴家学,郭晗,周立国,张甲明,田涯,李皓,李雪英,隋强
PEI Jiaxue,GUO Han,ZHOU Liguo,ZHANG Jiaming,TIAN Ya,LI Hao,LI Xueying,SUI Qiang

DOI: 10.19597/J.ISSN.1000-3754.202310052

参考文献(References)：

• [1]范宜仁，黄隆基，代诗华.交会图技术在火山岩岩性与裂缝识别中的应用[J].测井技术，1999,23(1):53-56,64.FAN Yiren, HUANG Longji, DAI Shihua. Application of crossplot technique to the determination of lithology composition and fracture identification of igneous rock[J]. Well Logging Technology,1999,23(1):53-56,64.
• [2]孙健，周魁，冉小丰，等. Bayes判别分析方法在岩性识别中的应用[J].石油天然气学报，2009,31(2):74-77.SUN Jian, ZHOU Kui, RAN Xiaofeng, et al. Bayes discriminant analysis method in lithology recognition[J]. Journal of Oil and Gas Technology,2009,31(2):74-77.
• [3]马峥，张春雷，高世臣.主成分分析与模糊识别在岩性识别中的应用[J].岩性油气藏，2017,29(5):127-133.MA Zheng,ZHANG Chunlei,GAO Shichen. Lithology identification based on principal component analysis and fuzzy recognition[J]. Lithologic Reservoirs,2017,29(5):127-133.
• [4]刘爱疆，左烈，李景景，等.主成分分析法在碳酸盐岩岩性识别中的应用：以YH地区寒武系碳酸盐岩储层为例[J].石油与天然气地质，2013,34(2):192-196.LIU Aijiang,ZUO Lie,LI Jingjing,et al. Application of principal component analysis in carbonate lithology identification:A case study of the Cambrian carbonate reservoir in YH field[J].Oil&Gas Geology,2013,34(2):192-196.
• [5]周游，张广智，高刚，等.核主成分分析法在测井浊积岩岩性识别中的应用[J].石油地球物理勘探，2019,54(3):667-675.ZHOU You,ZHANG Guangzhi,GAO Gang,et al. Application of kernel principal component analysis in well logging turbidite lithology identification[J]. Oil Geophysical Prospecting,2019,54(3):667-675.
• [6]印兴耀，孔国英，张广智.基于核主成分分析的地震属性优化方法及应用[J].石油地球物理勘探，2008,43(2):179-183.YIN Xingyao,KONG Guoying,ZHANG Guangzhi. Seismic attributes optimization based on kernel principal component analysis(KPCA)and application[J]. Oil Geophysical Prospecting,2008,43(2):179-183.
• [7]林楠，姜琦刚，陈永良，等.基于核主成分支持向量机的火成岩QAPF分类：以青海格尔木地区为例[J].地球学报，2014,35(4):487-494.LIN Nan,JIANG Qigang,CHEN Yongliang,et al. The classification of igneous rocks with QAPF based on kernel principal component SVM:A case study of Golmud area in Qinghai province[J]. Acta Geologica Sinica,2014,35(4):487-494.
• [8]高楚桥，詹旺，赵彬，等.基于层次分解、主成分和高斯混合聚类的火成岩岩性识别[J].长江大学学报（自然科学版），2024,21(2):36-44.GAO Chuqiao,ZHAN Wang,ZHAO Bin,et al. Identification of igneous rock lithology based on hierarchical decomposition,principal component and Gaussian mixture clustering[J]. Journal of Yangtze University(Natural Science Edition),2024,21(2):36-44.
• [9]王祝文，刘菁华，任莉.基于K均值动态聚类分析的地球物理测井岩性分类方法[J].东华理工大学学报（自然科学版），2009,32(2):152-156.WANG Zhuwen,LIU Jinghua,REN Li. The method for Lithology classification in geophysical well logging based on the K-means dynamic clustering analysis[J].Journal of East China University of Technology(Natural Science Edition), 2009, 32(2):152-156.
• [10]许振浩，马文，李树才，等.岩性识别：方法、现状及智能化发展趋势[J].地质论评，2022,68(6):2290-2304.XU Zhenhao,MA Wen,LI Shucai,et al. Lithology identification:Methods, status and intelligent development trend[J].Geological Review,2022,68(6):2290-2304.
• [11]林香亮，朱建伟，刘光寿，等.基于PCA-SVM的砂砾岩岩性识别[J].长江大学学报（自然科学版），2020,17(1):21-26.LIN Xiangliang,ZHU Jianwei,LIU Guangshou,et al. Lithologic identification of glutenite based on PCA-SVM[J]. Journal of Yangtze University(Natural Science Edition),2020,17(1):21-26.
• [12]宋延杰，张剑风，闫伟林，等.基于支持向量机的复杂岩性测井识别方法[J].大庆石油学院学报，2007,31(5):18-20.SONG Yanjie, ZHANG Jianfeng, YAN Weilin, et al. A new identification method for complex lithology with support vector machine[J]. Journal of Daqing Petroleum Institute, 2007, 31(5):18-20.
• [13]李雄炎，周金昱，李洪奇，等.复杂岩性及多相流体智能识别方法[J].石油勘探与开发，2012,39(2):243-248.LI Xiongyan,ZHOU Jinyu,LI Hongqi,et al. Computational intelligent methods for predicting complex lithologies and multiphase fluids[J]. Petroleum Exploration and Development,2012,39(2):243-248.
• [14]安鹏，曹丹平.基于深度学习的测井岩性识别方法研究与应用[J].地球物理学进展，2018,33(3):1029-1034.AN Peng,CAO Danping. Research and application of logging lithology identification based on deep learning[J]. Progress in Geophysics,2018,33(3):1029-1034.
• [15]曹茂俊，巩维嘉，高志勇.基于Stacking集成学习的岩性识别研究[J].计算机技术与发展，2022,32(7):161-166.CAO Maojun,GONG Weijia,GAO Zhiyong. Research on lithology identification based on Stacking integrated learning[J].Computer Technology and Development, 2022, 32(7):161-166.
• [16]邹琪，何月顺，杨希，等.基于集成学习的测井岩性识别模型的构建[J].智能计算机与应用，2020,10(3):91-94.ZOU Qi,HE Yueshun,YANG Xi,et al. Construction of lithology identification model by well logging based on ensemble learning[J]. Intelligent Computers and Applications, 2020, 10(3):91-94.
• [17]赵娅，管玉，李盼池，等.基于量子衍生涡流算法和T-S模糊推理模型的储层岩性识别[J].石油地球物理勘探，2024,59(1):23-30.ZHAO Ya, GUAN Yu, LI Panchi, et al. Reservoir lithology identification based on quantum vortex search algorithm and T-S fuzzy reasoning model[J]. Oil Geophysical Prospecting,2024,59(1):23-30.
• [18]裴家学.辽河外围盆地岩性油藏形成条件及识别[J].特种油气藏，2015,22(4):62-65.PEI Jiaxue. Forming conditions and identification of lithologic reservoirs in Peripheral Basin,Liaohe Oilfield[J]. Special Oil&Gas Reservoirs,2015,22(4):62-65.
• [19]孙超，朱筱敏，昝国军，等.陆西凹陷九佛堂组砂体成因类型及储集性能[J].石油勘探与开发，2008, 35(5):569-575.SUN Chao,ZHU Xiaomin,ZAN Guojun,et al. Sand body types and reservoir properties in Cretaceous Jiufotang Formation in Luxi Sag[J]. Petroleum Exploration and Development, 2008, 35(5):569-575.
• [20]冉波.开鲁盆地陆家堡凹陷九佛堂组火山碎屑岩油藏形成控制因素分析[J].石油地质与工程，2016,30(1):1-5.RAN Bo. Volcanic clastic rock reservoir formation control factors analysis of Jiufotang Formation in Lujiapu sag, Kailu Basin[J]. Petroleum Geology and Engineering,2016,30(1):1-5.
• [21]江淮，王振宇，冉波，等.陆西凹陷九佛堂组混积岩的岩石学特征及分类：以辽河油田庙35井为例[J].重庆科技学院学报（自然科学版），2021,23(1):31-36.JIANG Huai,WANG Zhenyu,RAN Bo,et al. Petrological characteristics and classification of migmatites of Jiufotang Formation in Luxi Sag:A case study of Miao-35 well, Liaohe Oilfield[J]. Journal of Chongqing University of Science and Technology(Natural Science Edition),2021,23(1):31-36.
• [22] SCH?LKOPF B, SMOLA A, MüLLER K-R. Kernel principal component analysis[C]. Berlin:International Conference on Artificial Neural Networks,1997.
• [23] MARUKATAT S. Tutorial on PCA and approximate PCA and approximate kernel PCA[J]. Artificial Intelligence Review,2023,56(6):5445-5477.
• [24]赵莹.支持向量机中高斯核函数的研究[D].上海：华东师范大学，2007.ZHAO Ying. The study on Gauss kernel function in support vector machine[D]. Shanghai:East China Normal University,2007.
• [25]段会川.高斯核函数支持向量分类机超级参数有效范围研究[D].济南：山东师范大学，2012.DUAN Huichuan. Research on the effective range of hyperparameters of support vector machine with Gaussian Kernel function[D]. Ji’nan:Shandong Normal University,2012.