检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:窦玉坛[1] 李斐[2] 杜广宏[2] 刘峰[2] 王大兴[2] 王永刚[2] 张盟勃[2] 黄研 DOU Yutan;LI Fei;DU Guanghong;LIU Feng;WANG Daxing;WANG Yonggang;ZHANG Mengbo;HUANG Yan(Research Institute of Petroleum Exploration&Development-Northwest,PetroChina,Lanzhou 730020,China;PetroChina Changqing Oilfield Company,Xi’an 710018,China)
机构地区:[1]中国石油勘探开发研究院西北分院,甘肃兰州730020 [2]中国石油长庆油田分公司勘探开发研究院,陕西西安710018
出 处:《天然气地球科学》2022年第5期820-830,共11页Natural Gas Geoscience
基 金:中国石油“十四五”前瞻性基础性重大科技项目(编号:2021DJ2205)资助.
摘 要:鄂尔多斯盆地SD地区为典型的低孔、低渗致密气区,但该区上古生界二叠系山2段和太原组普遍发育煤层,形成的强反射会掩盖其上下有效储层的响应特征,同时背景沉积作用也掩盖了储层的部分特征。为此将地震记录定义为均一反射层和岩性体反射的组合,均一反射层地震特征表现为低频、相位稳定,对有效储层预测会有干扰作用,提出一种基于改进的Hebb神经网络主分量分析的均一反射体提取方法,引入Ricker子波核函数,将原始地震数据通过内积操作变换到特征空间,提取非线性特征,解决原始样本空间地震数据样本线性不可分的问题,利用该方法的非监督在线学习能力,设计迭代算法计算,可以得到均一反射体,最终变换得到岩性体,实现储层的精细刻画。通过构建含煤层的二维模型验证了该方法去除均一反射层的可行性,并应用于SD地区A工区,可以有效去除均一反射层(包括去除强反射地层)影响,有利于提高利用高维度地震数据进行有效储层精细描述的准确度。SD area in Ordos Basin is a typical tight gas area with low porosity and low permeability,but coal seams are generally developed in Shan 2 Member and Taiyuan Formation of Upper Paleozoic Permian in this area. The strong reflection will mask the effective reservoir response characteristics above and below,and the background sedimentation also masks some characteristics of the reservoir. Therefore,in this paper,seismic records are defined as the combination of homogeneous reflector and lithologic body reflection. The seismic characteristics of homogeneous reflector are low frequency and stable phase,which will interfere with effective reservoir prediction. A homogeneous reflector extraction method based on improved Hebb neural network principal component analysis is proposed,and Ricker wavelet kernel function is introduced. The original seismic data is transformed into the feature space through the inner product operation,and the nonlinear features are extracted to solve the problem that the seismic data samples in the original sample space are linearly inseparable. Using the unsupervised online learning ability of this method,the iterative algorithm is designed to obtain the uniform reflector,and finally the lithologic body is transformed to realize the fine characterization of the reservoir. By constructing a two-dimensional model containing coal seams,the feasibility of removing uniform reflection layer by this method is verified,and applied to work area of SD area,which can effectively remove the influence of uniform reflection layer(including removing strong reflection layer),which is conducive to improving the accuracy of effective reservoir fine reservoir description using high-dimensional seismic data.
关 键 词:致密砂岩 去除均一反射层 Hebb神经网络 岩性体 匹配追踪
分 类 号:TE122.2[石油与天然气工程—油气勘探]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.222