基于支持向量机法识别砂岩中流体类型
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
砂岩储层孔隙中的流体识别一直是石油勘探开发过程中重要的环节,传统方法主要依赖于测井数据,但是在测井数据缺失的条件下较难得到准确的流体识别结果.本文提出一种只依靠地震数据的砂岩中流体识别的新方法,并选择地球物理方法可测或可求的地球物理参数σ、ρλ和ρμ作为流体识别因子,然后进行模型实验.首先,设置典型流体状态,用Gassmann方程进行流体替换,将得到的流体识别因子作为支持向量机的训练集数据,并定义支持向量机的分类标签;之后,设置随机流体状态,利用Gassmann方程计算流体因子,将得到的结果作为支持向量机的测试集数据.将训练集、测试集数据集输入支持向量机,进行分类,得出测试集数据的分类结果.模型实验分类结果表明,支持向量机法可以判别砂岩孔隙中流体的主要属性.
Pore fluid identification in sandstone reservoir has always been a important step in the process of petroleum exploration and development,conventional methods depend on the logging data.Generally speaking,it is hard to get accurate fluid identification result under the condition of lack of logging data.In this paper,we present a new fluid identification method based on Support Vector Machine.This new method can achieve the fluid identification with only seismic data.We set geophysical parameters σ,ρλ and ρμ which can be observed or rectifiable by geophysical methods as fluid identification factor,then do model experiments.First,set up typical fluid states and do the fluid substitution with Gassmann equation,then set the fluid identification factors we get as training data for support vector machine.After that,we set up random fluid states,using Gassmann equation to calculate fluid identification factors,the results will be set as test data for support vector machine.Model experiments indicate that support vector machine method can determine the major fluid properties in the sandstone porosity.
引文
Bi M X,Huang H M,Bian Y J,et al.2011.A study on seismic signal HHT features extraction and SVM recognition of earthquake and explosion[J].Progress in Geophysics(in Chinese),26(4):1157-1164,doi:10.3969/j.issn.1004-2903.2011.04.004.
    Bing P P,Cao S Y,Lu J T.2012.Non-linear AVO inversion based on support vector machine[J].Chinese Journal of Geophysics(in Chinese),55(3):1025-1032,doi:10.6038/j.issn.0001-5733.2012.03.033.
    Cai M.2009.New method on fluid identification of low porosity and permeability reservoir based on support vector machine[J].Inner Mongulia Petrochemical Industry(in Chinese),35(22):41-22.
    Castagna J P,Batzle M L,Eastwood R L.1985.Relationships between compressional-wave and shear-wave velocities in clastic silicate rocks[J].Geophysics,50(4):571-581.
    Cheng H M,Zhang S Y.2014.Noise elimination for magnetotelluric sounding data based onε-SVR algorithm[J].Progress in Geophysics(in Chinese),29(2):668-673,doi:10.6038/pg20140226.
    Deng X Y,Yang D H,Liu T,et al.2010.Performance analysis of least squares support vector regression filtering system[J].Chinese Journal of Geophysics(in Chinese),53(8):2004-2011,doi:10.3969/j.issn.0001-5733.2010.08.027.
    Faruto.2009.LIBSVM(faruto ultimate version):a toolbox with implements for support vector machines based on libsvm[EB/OL].[2012-02-03].http://www.matlabsky.com.
    Gassmann F.1951.Elastic waves through a packing of spheres[J].Geophysics,16(4).673-685.
    Goodway W,Chen T,Downton J.1997.Improved AVO fluid detection and lithology discrimination using Lame petrophysical parameters;"λρ","μρ".and"λ/μfluid stack",from P and S inversion[C].//CSEG national convention,Expanded Abstracts,148-151.
    Guo Z Q,Liu C,Feng X,et al.2010.Attenuation anisotropy and AVO analysis[J].Journal of Jilin University(Earth Science Edition)(in Chinese),40(2):432-438.
    Huang X D.1981.Building-up and development of lithologic seismic prospecting[J].Chinese Journal of Geophysics(in Chinese),24(2):218-228.
    Li J K,Castagna J.2004.Support vector Machine(SVM)pattern recognition to AVO classification[J].Geophysical Research Letters,31(2),doi:10.1029/2003GL018299.
    Li W X,Wang H,Yao Z X,et al.2009.Shear-wave velocity estimation and fluid substitution by constraint method[J].Chinese Journal of Geophysics(in Chinese),52(3):785-791.
    Li Z Y,Feng X Q.2012.Shear wave velocity inversion based on fluid displacement[J].Journal of Oil and Gas Technology(in Chinese),34(7):98-102.
    Liu C,Lan H T,Guo Z Q,et al.2013.Pseudo-spectral modeling and feature analysis of wave propagation in two-phase HTI medium based on reformulated BISQ mechanism[J].Chinese Journal of Geophysics(in Chinese),56(10):3461-3473,doi:10.6038/cjg20131021.
    Liu W,Cao S Y.2009.Comparison and analysis of three fluid identification technologies based on seismic data[J].Progress in Geophysics(in Chinese),23(6):1918-1923.
    Vapnik V N.1995.The nature of statistical learning theory[M].New York,NY,USA,Springer-Verlag New York,Inc.,111-289.
    Wang X W.2004.The prediction and evaluation of lithological reservoir[J].Geophysical Prospecting for Petroleum(in Chinese),43(6):511-517.
    Xu J L,Wang G W,Wang Y J,et al.2012.Integrated research on well-logging evaluation methods for carbonate reservoir[J].Geophysical Prospecting for Petroleum(in Chinese),51(5):521-530.
    Yang W C.1986.A generalized inversion technique for potential field data processing[J].Chinese Journal of Geophysics(in Chinese),29(3):283-291.
    Yang Z L,Peng L C,Chen Q L,et al.2007.Seismic attributes analysis and lithological reservoir exploration[J].Geophysical Prospecting for Petroleum(in Chinese),46(2):385-389.
    Yi S H,Liu D Z,He Y L,et al.2013.Modeling and forecasting of the variable geomagnetic field by support[J].Chinese Journal of Geophysics(in Chinese),56(1):127-135,doi:10.6038/cjg20130113.
    Yin X Y,Zhang S X,Zhang F.2013.Delicate construction of fluid factor and its application based on two-phase media theory[J].Progress in Geophysics(in Chinese),28(6):2911-2918,doi:10.6038/pg20130611.
    Zhang J,Li H Q,Guo H F,et al.2009.Abnormal amplitude checking method of log data based on SVM[J].Progress in Geophysics(in Chinese),24(6):2181-2185.
    Zhang X G.2000.Introduction to statistical learning theory and support vector machines[J].Acta Automatica Sinica(in Chinese),26(1):32-43.
    Zhang Y D,Tong K J,Zheng J,et al.2008.Application of support vector machine method for identifying fluid in low-resistivity oil layers[J].Geophysical Prospecting For Petroleum(in Chinese),47(3):306-314.
    毕明霞.黄汉明.边银菊.等.2011.天然地震与人工爆破波形信号HHT特征提取和SVM识别研究[J].地球物理学进展,26(4):1157-1164,doi:10.3969/j.issn.1004-2903.2011.04.004.
    邴萍萍,曹思远,路交通.2012.基于支持向量机的非线性AVO反演[J].地球物理学报,55(3):1025-1032,doi:10.6038/j.issn.0001-5733.2012.03.033.
    蔡敏.2009.基于支持向量机的低孔低渗储层流体识别新方法[J].内蒙古石油化工,35(22):41-22.
    程怀蒙,张胜业.2014.基于ε-SVR算法的大地电磁测深资料去噪[J].地球物理学进展,29(2):668-673,doi:10.6038/pg20140226.
    邓小英,杨顶辉,刘涛,等.2010.最小二乘支持向量回归滤波系统性能分析[J].地球物理学报,53(8):2004-2011,doi:10.3969/j.issn.0001-5733.2010.08.027.
    郭智奇,刘财,冯晅,等.2010.各向异性衰减与AVO分析[J].吉林大学学报(地球科学版),40(2):432-438.
    黄绪德.1981.建立和发展岩性地震勘探法[J].地球物理学报,24(2):218-228.
    李维新,王红,姚振兴,等.2009.基于约束条件横波速度反演和流体替代[J].地球物理学报,52(3):785-791.
    李中元,冯兴强.2012.基于流体替换的横波速度反演[J].石油天然气学报,34(7):98-102.
    刘财,兰慧田,郭智奇,等.2013.基于改进BISQ机制的双相HTI介质波传播伪谱法模拟与特征分析[J].地球物理学报,56(10):3461-3473,doi:10.6038/cjg20131021.
    刘伟.曹思远.2009.基于地震资料的三种岩性流体预测方法对比分析[J].地球物理学进展,23(6):1918-1923.
    王西文.2004,岩性油气藏的储层预测及评价技术研究[J].石油物探,43(6):511-517.
    徐敬领,王贵文,王亚静.等.2012.碳酸盐岩储层测井评价方法综合研究[J].石油物探,51(5):521-530.
    杨文采.1986.用于位场数据处理的广义反演技术[J].地球物理学报,29(3):283-291.
    杨占龙,彭立才,陈启林,等.2007.地震属性分析与岩性油气藏勘探[J].石油物探,46(2):385-389.
    易世华,刘代志,何元磊,等.2013.变化地磁场预测的支持向量机建模[J].地球物理学报,56(1):127-135,doi:10.6038/cjg20130113.
    印兴耀,张世鑫,张峰.2013.双相介质理论指导下的流体因子精细构建与应用[J].地球物理学进展,28(6):2911-2918,doi:10.6038/pg20130611.
    张军,李洪奇,郭海峰,等.2009.基于支持向量机的测井资料幅度异常验收方法研究[J].地球物理学进展,24(6):2181-2185.
    张学工.2000.关于统计学习理论与支持向量机[J].自动化学报,26(1):32-43.
    张银德,童凯军,郑军,等.2008.支持向量机方法在低阻油层流体识别中的应用[J].石油物探,47(3):306-314.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心