基于自组织神经网络算法的低渗透砂岩孔隙结构自动分类  

Automatic classification of pore structures of low-permeability sandstones based on self-organizing-map neural network algorithm

作　　者：路研 刘宗宾 廖新武 李超 李扬 LU Yan;LIU Zongbin;LIAO Xinwu;LI Chao;LI Yang(Tianjin Branch of CNOOC China Limited,Tianjin 300452,China)

机构地区：[1]中海石油(中国)有限公司天津分公司,天津300452

出　　处：《地质科技通报》2024年第6期318-330,共13页Bulletin of Geological Science and Technology

基　　金：国家科技重大专项(2017ZX05009001)。

摘　　要：低渗透砂岩储层的孔隙系统复杂,孔隙-喉道大小分布多变,是决定储层宏观岩石物理性质和控制流体在砂岩中渗流行为的关键因素。以往的低渗透砂岩孔隙结构分级评价工作多基于孔隙-喉道大小分布的几何形态或参数回归分析,受人为因素干扰大,缺乏精确的分级评价标准。以渤海湾盆地G油田沙四上亚段低渗透砂岩储层为研究对象,综合运用岩相学分析、高压压汞、核磁共振及X射线CT扫描等技术手段,详细探讨了低渗透砂岩微观孔隙结构特征。在此基础上,选取了15个能够反映低渗透砂岩微观孔隙结构特征的储层评价参数,并采用无监督模式下的自组织映射神经网络算法将取心层段的70组岩心样本自动划分为4类孔隙结构。研究结果表明,Ⅰ类孔隙结构以大孔喉为主,中值喉道半径r50主要分布在0.38~2.35μm的范围内;孔喉连通性好,对渗透率贡献作用显著。Ⅱ类孔隙结构的渗流性能和连通性能仅次于Ⅰ类孔隙结构,可动流体孔隙度在2.76%~5.61%之间,中值喉道半径r50主要分布在0.01~0.23μm的范围内。Ⅲ类孔隙结构具有较好的孔喉连通性和较强的微观非均质性,储集和渗流性能与Ⅰ类和Ⅱ孔隙结构相比明显较差。Ⅳ型孔隙结构内小孔喉占主导,孔喉连通性差,不利于流体在砂岩中的渗流。基于自组织映射神经网络算法可以实现多参数情况下的孔隙结构类型自动分类。分类结果不受不准确的用户自定义信息的影响,并且对参与训练过程的参数数量没有限制,在基于多参数的孔隙结构分类方面应用效果显著。建立的基于自组织特征映射(self-organizing feature map,简称SOM)神经网络算法的孔隙结构分类评价标准,对于研究低渗透砂岩储层的微观渗流行为和储层质量评价意义重大。[Objective]The pore system of low-permeability sandstone reservoirs is intricate,and the distribution of pore-throat sizes is highly variable.The microscopic pore structure significantly influences the reservoir′s petro-physical properties and plays a critical role in controlling fluid flow within sandstone reservoirs.Traditional approa-ches for evaluating pore structures primarily rely on morphological analyses of pore throat size distributions or regres-sion analyses of pore structure parameters.These methods are significantly affected by human bias and often lack precise evaluation frameworks.[Methods]Poroperm analysis,mercury injection capillary pressure,nuclear mag-netic resonance(NMR)measurements,and X-ray computed tomography(X-ray CT)scanning experiments were performed to characterize the pore structures of the Ess4 low-permeability sandstones in the G oilfield,Bohai Bay Ba-sin.On this basis,15 parameters that reflect the microscopic features of low-permeability sandstones were selected,and four types of pore structures were classified by applying an unsupervised self-organizing-map neural network al-gorithm.[Results]The findings reveal that the TypeⅠpore structure predominantly features large pore throats,with a median throat radius(r50)ranging from 0.38 to 2.35μm.This type exhibits excellent pore connectivity,contributing significantly to permeability.The petrophysical properties and pore connectivity of TypeⅡpore struc-tures are second only to those of TypeⅠpore structures.The movable fluid porosity ranges from 2.76%to 5.61%,and the median throat radius(r50)is primarily distributed in the range of 0.01 to 0.23μm.TypeⅢpore structures display good pore connectivity along with considerable microscopic heterogeneity.The petrophysical prop-erties and seepage properties of TypeⅢpore structures are comparable to those of TypeⅠand TypeⅡpore struc-tures.The TypeⅣpore structures are characterized by small pore throats and poor microscopic connectivity,which hinders fluid movement within the sa

关 键 词：渤海湾盆地 低渗透砂岩 孔隙结构 自组织神经网络 无监督模式 

分 类 号：P618.13[天文地球—矿床学]