用户名: 密码: 验证码:
基于核方法的井—震多属性碎屑岩储层预测技术研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
碎屑岩储层是当今石油天然气勘探开发的重点和热点之一,并形成了一套开发技术和方法系列。但因其致密、低孔隙、多层叠置和非均质性强等特点造成的复杂性和特殊性,目前还难以解决储层预测的准确性问题,因此,除了运用先进的技术装备外,还必须逐步探索并形成结合地质、测井、地震勘探、非线性科学等多学科的技术方法。
     本文从核方法的原理和统计学习理论出发,在介绍支持向量机分类、支持向量机回归、核Fisher判别方法、核主成分分析方法的基础上,研究了这些方法在储层参数预测、横波预测、岩性识别、流体识别、多维地震属性优化分析等方面的应用能力和前景。利用这些方法进行了仿真实验,并将其用于岩性识别、流体识别、地震属性优化,对结果进行了分析和讨论;最后以XC地区为例,利用优化的地震属性和岩性、流体识别的结果,并结合波形聚类、频谱分析和波阻抗反演,开展了多属性的有利砂体分布区的预测。本文的研究内容和主要认识有以下几个方面:
     (1)提出了将最小二乘支持向量回归机用于横波的预测。在深入研究支持向量机和横波预测方法的基础上,把基于统计学习理论的最小二乘支持向量机用于实测纵横波数据的拟合,获得了较好的预测精度且适应能力强。利用预测的纵横波数据,计算出了各种弹性参数。
     (2)将Fisher判别和核Fisher判别方法引入到碎屑岩岩性识别中,探讨了方法在岩性识别领域的应用潜力和前景。在XC地区须二段,针对岩性识别中存在的困难,分别采用测井曲线、弹性参数、及其二者的组合作为特征变量,运用Fisher判别和核Fisher判别方法进行了岩性识别,结果表明使用核Fisher判别方法能很好的识别砂岩和粉砂岩。
     (3)本文针对致密碎屑岩储层流体识别存在非线性这一特点,提出了基于核Fisher判别方法和最小二乘支持向量机的流体识别方法。首先在核Fisher判别方法成功应用于碎屑岩岩性识别基础上,把核Fisher判别方法用于XC地区须二段储层的流体识别,结果表明该方法能较好的区分气层和气水同层;其次,总结了现有的一对一、一对多、最小二乘支持向量分类器等多类支持向量机方法,提出将最小二乘支持向量机用于流体识别,提高了数据的分类精度。
     (4)在构建核Fisher判别方法和最小二乘支持向量机岩性识别与流体识别技术方法的基础上,分析比较了四种常用核函数的效果。结果表明支持向量机训练和分类的速度优于神经网络,高斯核函数的分类精度最高。
     (5)在分析比较地震属性分析方法特别是主成分分析的基础上,对核主成分算法进行了深入的研究,并作了仿真分析。针对地震属性这种大规模数据集,把基于矩阵的核主成分分析方法引入到地震属性的优化中,其结果表明经核主成分处理后得到的综合属性,能有效的表征有利砂体分布区。
     (6)运用波形聚类、频谱分析和地震反演等技术,分别对砂体的空间展布和储层的发育有利区进行了分析,并把KPCA优化得到的综合属性和波形聚类、地震反演的结果综合起来,预测了XC地区须二段的有利砂体分布区,结果与实钻情况吻合较好,表明了多属性预测方法的有效性。
With the developmernt of new theory and tecthnology prentation and itsapplication, explorationist pay attention to the unconventional tight clastic reservoirbacause of its industty latent capacity and economic worth,and a series of mothod andtechnology is presented.With the complication and peculiarity of tight clasticreservoir,which is caused by lower porosityand lower permeability,the accuracy can’tbe figured out in reservoir prediction. Except application of advanced technology anddevice,the multi-disciplinary techniques is need,which combines geology, welllogging, seismic exploration, nonlinear, multi-disciplinary techniques.
     In this paper, the first part summarily review the kernel methods and principlesof statistical learning theory,and introduces the support vector machine classifier,support vector machine regression, kernel Fisher discriminant method and kernelprincipal component analysis method.Moreover,the capabilities and prospects ofapplication of these methods is studied in the prediction of reservoir parameters, the Pand S data forecast, identification of lithology, fluid identification andmulti-dimensional seismic attribute optimization analysis,then experimental resultswere analyzed and discussed. Finally, with the optimized seismic attributes, combinedwith the waveform clustering spectrum analysis and acoustic impedance inversionresults, the favorable of oil and gas area is presented. The main achievements andinnovation are as follows:
     (1) Propose least squares support vector regression machine for shear waveforecast. On the basis of depth study of support vector machines, shear waveprediction of empirical formula and least-squares fitting method, least squares supportvector machine based on statistical learning theory is used for fitting the measuredS-wave data,and obtains a better prediction accuracy and adaptive ability. In thecalculated shear wave data,it gains a variety of elastic parameters.
     (2) Kernel Fisher discriminant method is introduced to lithologic identificationin tight clastic rock, and to explore the potential and prospects of its application inthis field.For lithology identification difficulties of XC2member, Fisherdiscriminant analysis and kernel Fisher Discriminant Analysis are used to calculatethe elastic parameters with well logs,elastic parameters and combinations.The resultsshow that kernel Fisher Discriminant Analysis can well identify the sandstone andsiltstone.
     (3)According to the nonlinear characteristics of fluid idenfification in the tightclastic reservoirs,KFDA and LS-SVM based on principles of statistical learning wasput forward.Firs take XC2member for example,kernel Fisher DiscriminantAnalysis,successfully applied to lithologic identification, is introduced into reservoirfluid identification.The results show that method can better distingiush between gasreservoir and gas with the water layer.Secondly,summarizes the existing1-against-1,1-against-rest and least squares support vector classifier, least squares support vectormachine was put forward for fluid identification,which improve the classificationaccuracy of the data.
     (4)Four common kernel function of KFDA and SVM were analyzed andcompared based on building technology system of lithology identification and fluididentification.The result shows support vector machine training and classificationspeed is superior to neural network,the classification accuracy of the Gaussian kernelfunction.
     (5) Throgh the analysis and compare of seismic attributes optimzation method inparticular PCA,KPCA algorithm is in-depth studied,then simulation is obtained.Whenfaced with the large-scale data set, Matrix-based Kernel Principal ComponentAnalysis is used for seismic attribtes optimation,the result suggest that the optimatedattributes effectively characterise of the reservoir.
     (6) In this article,pectrum decomposing,waveform clustering,seismic inversionmethods is applied to the prediction of sandstone district area; Combination KPCAattributes with the result of waveform clustering and seismic inversion,folding graphof favorite area shall be provided for range of profitability for tight sand of XC2member,which shows good prospects for exploration and development.
引文
[1]Satinder Chopra, Kurt J.Marfurt. Emerging and future trends in seismic attributes[J].TheLeading Edge,2008,27(3):298~318
    [2]Wollf,M., Pelissier-Combescure, J. Faciolog-automatic electrofacies determination[A]. SPWLA23rdAnnual Logging Symposium,1982,1~23
    [3]Busch,J.M., Fortney, W.G., Berry, L.N.. Determination of lithology from well logs by statisticalanalysis[J]. SPE Formation Evalution,1987,2(4):412~418
    [4]Doveton, J.H.. Geologic log analys is using computer methods[M]. AAGP ComputerApplications in Geology,Tulsa,1994
    [5]Yao,Z.H., Wu, L.D.. A cluster approach based on Marr’s operator with its application tolithologic recognition[J]. Pattern Recognition Letters,1991,12(8):451~456
    [6]Samuel,J.R., Fang, J.H., Karra,C.L., et al. Determination of lithology from well logs using aneural netword[J]. AAPG Bulletin,1992,76(5):731~739
    [7]Anouar, F., Badran,F., Thiria,S., Self-organized map, Aprobabilistic approach[A]. Proceedingsof the Wordshop on Self-Organized Maps[C].Helsinki University of Technology, Espoo,Finland,1997
    [8]Frayssinet,D.,Thiria,S.,Badran,F.,etal.Use of neural networks in log’s data processing:prediction and rebuilding of lithologic fzcies[A]. Petrophysics meets Geophysics, Paris,2000
    [9]Zhou,Z.H.,Chen,Z,Q.,Chen,S. F.. Neural network based lithology identification[A].Proceedingsof the International Conference on Intelligent Information Processing at16thIFIP WorldComputer Congress[C],2000,139~142
    [10]Wang, K. X., Zhang, L. B.. Predicting formation lithology from log data by using a neuralnetwork[J].Petroleum Science,2008,6(5):242~246
    [11]ALISTAIR R, BROWN.Seismic attributes and their classification[J],The Leading Edge,1996,15(10):1096
    [12]A. E. Barnes, Seismic attribute: past, present, and future [J],.1999,69th ANNU SEG INTMTG EXPANDED ABSTR BIOGR V1:892~895.
    [13]Chen,Q.and Sidney,S.,Advances seismic attribute technology,67th Ann. Internat.Mtg.,Soc.Expl. Geophys., Expanded abstracts,1997
    [14]Balch,A.H., Color sonograms a new dimension in seismic data interpretation, Geophysics,1971,36:1074~1098
    [15]N. A. Anstey.Seismic reflections yield more than structure.European Geophysical Society,Meeting, Abstracts.(1973),(1):1
    [16]Taner, M.T., Koehler, F., Sheriff, R. E. Complex seismic trace analysis [J].Geophysics,1979,44(1):1041~1063.
    [17]W. J. Ostrander.Plane wave reflection coefficients for gas sands at nonnormal angles ofincidence.Society of Exploration Geophysic ists,52nd annual meeting, Dallas,1982(1)pp.216~218
    [18]B. Russell, D. Hampson, J. Schuelke, and J. Quirein, Multiattribute seismic analysis, TheLeading Edge,1997,16(10):1439~1443.
    [19]Gary F. Margrave, Don C. Lawton, and Robert R. Stewart,Interpreting channel sands with3C-3D seismic data,The Leading Edge; April1998,17(4):509~513
    [20]Marc A. Lawrence,Hugh T. Logue, and Jess Kozman.Prospective features revealed by new3Dseismic in shallow waters of Chandeleur Sound/Viosca Knoll, AAPG Bulletin1999,83(8):1356~1357
    [21]J.Tenenbaum,V.De Silva and J.Langford.A global geometric framework for nonlineardeimension reduction. Science,2000,290:2319~2323
    [22]S.Roweis,L Saul.Nonlinear dementionality reduction by locally linear embededing. Science,2000,290:2323~2326
    [23]L Saul and S.Roweis.Think globally,fit locally:unsupervised learning of nonlinearmanifolds.Journal of Machine Learning Research,2003,4:119~155
    [24]Aronszajn.N.Universal approximation bounds for superpositions of a sigmoidal function.IEEETrans.Inf.Theory1993,39:930~945
    [25]Aizerman.Theoretical foundations of the ptertial function method in pattern recognitionlearning.Automation and remote control,1964,25:821~837
    [26]Vapnik V N. The Nature of Statistical Learning Theory [M]. New York: Springer-Verlag,1995.
    [27]Suykens J A K, Vandewalle J. Least Square Support Vector Machine Classifiers [J]. NeuralProcessing Letters,1999,9(3):293~300.
    [28]Burges C J C. A tutorial on Support Vector Machine for pattern recognition [J]. Data Miningand Knowledge discovery,1998,2(2):14~17.
    [29]Scholk pf B,Smola A,Muller K R.Nonlinear Component Analys is as a Kernel EigervalueProblem.Neural Computation,1998,10(5):1299~1319
    [30]Kazuhiro Hotta,Pose independent object classification form small number of training samplesbased on kernel principal component analysis of local parts[J].Image and Vision Computing,2008,doi:10.1016
    [31]Kenichi Kaieda,Shigeo Abe.KPCA-based training of a kernel fuzzy classifier with ellipsoidalregions[J].International Journal of Approximate Reasoning,2004(37):189~217
    [32]Jing Li,Xuelong Li,Dacheng Tao.KPCA for semantic object extraction in images[J].PatternRecognition,2008(41):3244~3250
    [33]Congde Lu,Chunmei Zhang,Taiyi Zhang,et al. Kernel based symmetrical principal componentanalysis for face classification[J].Neurocomputing,2007(70):904~911
    [34]Jong-Ming Lee,ChangKyoo Yoo,Sang Wook Choi, et al.NonLinear process monitoring usingkernel principal component analysis[J].Chemical Engineering Science,2004(59):223~234
    [35]A.R.Teixeira,A.M.tome,K.Stadlthanner,et al. KPCA denoising and the pre-image problemrevisited[J].Digital Signal Processing,2008(18):568~580
    [36]Vapnik, V.N. Satistical Learning Theory. New Youk:Join Wiley and Sons,1998
    [37]Vapnik, V., Chervonenkis,A,J.. On the uniform convergence of relative frequencies of eventsto their probabilities. Theory Probability Application,1971,16:264~280
    [38]Pai,P.-F.,Hong,W.-C.Forecasting regional electricity load based on recurrent support vectormachines with genetic algorithms.Electric Power Systems Research,2005,74(3):417~425
    [39]Ubeyli, E.D.ECG beats classification using multiclass support vector machines with errorcorrecting output codes.Digital Signal Processing,2007,17(3):675~684
    [40]Seo,K.-K.An application of one-class support vector machines in content-based imageretrieval.Expert Systems with Applications,2007,33(2):491~498
    [41]Widodo, A.,Yang,B.-S.Support vector machine in machine condition monitoring and faultdiagnosis.Mechanical Systems and Signal Processing,2006:1~15
    [42]Poyhonen, S., Negrea, M.,Arkkio,A., et al. Fault diagnostics of an electrical machine withmultiple support vector classifiers.in:International Symposium on Intelligent Control.Vancouver, Canada:2002,373~378
    [43]B.E. Boser,I.M.Guyon,and V.N.Vapnik. A Training Algorithm for Optimal Margin Classifiers.In D.Haussler, Editor, Proceedings of the5thAnnual ACM Workshop on ComputationalLearning Theory. ACM Press,1992:144~152
    [44]Muller K R,Smola A J,et al. Predicting Time Series with Support Vector Machines.[C].Proceeding of the International Conference on Artificial Neural Networks. LausaunneSwitzerland,Springer,1997:999~1004
    [45]Drucker H,Burges C J C,Kaufman L,Smola A,Vapnik V N. Support Vector RegressionMachines[C]. Advances Neural Information Processing Systems,Cambridge,MA,MIT Press,1997:155~161
    [46]Mukherjee S Osuna E,Girosi F. Nonlinear Prediction of Chaotic Time Series Using a SupportVeetor Machine[C]. Neural Networks for Signal Processing Vll-Proeeeding of the1997IEEEWorkshop,New York,1997:511~520.
    [47]Sjogerg J,Zhang Q,Ljung L. Nonlinear Black-box Modeling in System Identification:aUnified Overvies.[J]. Automatica,1995,31(12):1691~1724
    [48]Brown M,gunn S R.Empirical Data Modeling Algorithms: Additive Spline Models andSupport Vector Machines[C]. Proc of UKACC International Conference on Control,Swansea,UK,1998,1:709~714
    [49]Sch lklpf B., Platt J.C.,Smola A.J.Kernel Method for Percentile Feature Extraction. Techniclreport, MSR-TR-2000-22. Microsoft Research,2000
    [50]Mavko, G., Mukerji, T. and Dvokin,J. Rock physics handbook[M]. Cambridge UniversityPress,1998
    [51]Mavko, G., Chan,C. and Mukerji,T. Fluid substitution:Estimating changes in Vp withoutknowing Vs[J]. Geophysics,1995,60:1770~1775
    [52]Suykens.J.A.K.,Vandewalle J and De Moor B.Optimal Control by Least Squares SupportVector Machines.Neural Networks.2001,14(1):23~25
    [53]Castagna J.P.,Batzle M.L. and Eastwood R.L. Relationships between compressional-waveand shear-wave velocities in clastic rocks[J]. Geophysics,1984,V54(2):571~581
    [54]Han De-hua,Nur A and Morgan,D.,Effects of Porosity and clay content on wave Veloeitiesin sand stones[J].GeoPhysies,1986,51(11):2093~2107
    [55]Han De-hua and Batzle M.L. Gassmann’s equation and fluid-sattiration effeets ons eismicveocities[J]. Geophysics,2004,69(2):398~405.
    [56]Kuster G T. and Toks z M.N. Veloeity and attenuation of seismicwaves in two-phase media.Theoretical fonnulations [J].Geophysies,1974,39:587~606
    [57]Lee M.W. Proposed moduli of dry rock and their application to Predicting elastic velocities ofsandstones[J]. U.S.Geological Survey,Scientific Investigations,2005,5119
    [58]Lee M.W. A Simple method of Predicting S-waveve locity[J].Gcophysics,2006,V71(6):161~164
    [59]Piekett G. A coustic charater logs and their application in formation evaluation J Petr. Tech.,1961,15:650~667
    [60]Hudson J.A. Wave speeds and attenunation of elastic waves in materal containing cracks[J].Geophysics,1981,64:133~150
    [61]HudsonJ.A. The effect of fluid pressure on wave speeds in cracked solid[J].GeoPhysicalJournal lntemational,2000,143:302~310
    [62]Suykens J A K, Vandewalle J,De Moor B. Optimal Control by Least Squares Support VectorMachines[J]. Neural Networks,2001,14:105~113
    [63]S. Mika, G. Ratsch,Sch lkopf, et al. Fisher discriminant analysis with kernels[C].Processings of the1999IEEE Signal Processing Society Workshop. Madison, Wisconsin,USA:IEEE,1999,41~48
    [64]Volker Roth, Volker Steinhage. Nonlinear discriminant analysis using kernel functions[C].Proc of Neural Information Processing Systems[C].1999.568~574
    [65]Smith G C and Gidlow P M. Weighted stacking for rock property estimation and detection ofgas[J].Geophysical Procspecting.1987,35(9):993~1014.
    [66]J.A.K.Suykens,L.Lukal,J.Wandewalle. Least squares support vector machine classifier[J].Neural Processing Letter,1999,9:29~300
    [67]K.S.Chua. Efficient computation for large least square support vector machine classifiers[J].Pattern Recognition Letters,2003,24:75~80
    [68]Cortes C., Vapnik V. Support vector networks[J]. Machine Learning,1995,20(3):273~297
    [69]Krebel U. Pairwise Classification and support vector mac hines[M]. In:Sch lkopf B,Burges C,Smola A. Advances in Kernel Methods Support Vector Learning. Cambrige,MA:MIT Press:1999:225~268
    [70]Platt J.C., Cristianini N., Shawe-Taylor J. Large margin DAG for multiclass classification [M].Advances in Neural Information Proceessing Systems,MIT Press,Cambrige, MA,2000,547~543
    [71] Z.Pawlak. Rough Sets-Theoretical Aspects of Reasoning about Data. Kluwer AcademicPublishers,Dordrecht,1991.
    [72]K.Fukunaga and W.L.G.Koontz. Representation of random processes using the finiteKarhunen-Loeve expansion,Inform.And Contr,1970,16:85~101
    [73]Y.Young,The reliability of linear feature extractor,Trans.IEEE Computers,1971,20:967~971
    [74]Gao Jun,Wang Jianmin, Yun Meihou et al. Seismic attributes optimization and application inreservoir prediction[J]. APPLIED GEOPHYSICS,2006,Voi.3,No,4,PP243~247
    [75]L.J.Cao,K.S.Chua,W.K.Chong,et al..A component of PCA,HPCA and ICA for dimensionalityreduction in support vector machine[J].Neurocomputing55(2003)321~336
    [76]Rosipal R,Girolami M. An expectation-maximization approach to nonlinear componentanalysis[J].Neural computation,2001,13(1):505~510.
    [77]Zheng W M,Zou C R,Zhao L. An improveld algorithm for kernel principal componentanalysis[J].Neural processing letters,2005,22(1):49~56.
    [78]O.Chapelle, V. Vapnik,O.Bousquet,S.Mukherjee,Choosing multiple parameters for supportvector machines,Machine Learning,Vol.46(1),131~159,2002.
    [79]J.T.Kwok. The evidence framework applied to support vector machines[J]. IEEE Trans.NeuralNetworks,2000,11(5):1162~1173,.
    [80]P.Sollich. Bayes ian methods for support vector machines:Evidence and predictive classprobabilities[J].Machine Learning,Vol.46(1-3),21~52,2002.
    [81]Daoqiang Zhang,Songcan Chen and Zhi-Hua Zhou. Learning the kernel parameters in kernelminimum distance classifier[J]. Pattern Recognition,2006,Vol.39(1),133~135
    [82]W.M. Zheng,C.R. Zou, L. Zhao. An ImprovedAlgorithm for Kernel Principal ComponentsAnalysis[J]. Neural Processing Letters,2005,22:49~56
    [83]K.I. Kim, M.O. Franz, and B. Scholkopf. Iterative Kernel Principal Componert Analysis forImage Modeling[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2005,27(9):1351~1366
    [84]Sander TD. Optimal unsupervised learnig in a single-layer linear feedforward neuralnetwork[J]. Neurla Network,1989,12,459~473
    [85]Kurt J.Marfurt.Emerging and future trends in seismic attributes[J]. The Leading Edge,March2008,27(3):298~318
    [200] Kohonen T. Self-Organizing Maps[M]. Berlin: Springer,2001.
    [86]Partyka G,Gridley J,Lopez J.Interpretational application of spectral decomposition in reservoircharacterization[J]. The Leading Edge,1999,18(3):353~360
    [87]Raiehe A. A pattern reeognition approaeh to geophys ieal inversion using neuralnetworks[J],GeoPhysieal Journal International,1991,1(105):629~648.
    [88] Sambrige,M. and Drijkoningen,G.,Genetic algorithms in seismie waveform inversion[J].Geophys,1992,109:323~342
    [89]郭华军,刘庆成.地震属性技术的历史现状及发展趋势[J].物探与化探,2008,32(1):19~22
    [90]赵澄林,陈丽华,涂强等.中国天然气储层[M].北京:石油工业出版社,1999
    [91]甘其刚.川西坳陷深层致密非均质裂缝性气藏地震识别技术研究[D].成都:成都理工大学,2005
    [92]宋岩,洪峰.四川盆地川西坳陷深盆气地质条件分析[J].石油勘探与开发,2001,28(2):11~14
    [93]张金亮,常象春,王世谦.四川盆地上三叠盆气藏研究[J].石油学报,2002,23(3):27~33
    [94]王金琪.川西坳陷须家河组(T_3x)气藏再认识[J].天然气工业,2002,23(3):1~5
    [95]曾文冲.低电阻率油气层的类型、成因及评价方法(上)[J].地球物理测井,1991,15(1):6~12
    [96]邵维志,李浩等.大港白头水地区低阻油气气层测井评价[J].测井技术,2001,25(2):127~130
    [97]杨斌,匡立春,孙中春等.一种用于测井油气层综合识别的支持向量机方法[J].大庆石油地质开发,2004,23(6):78~79
    [98]潘和平,樊政军,马勇.低阻油气层识别方法研究[J].天然气工业,2006,26(2):66~68
    [99]岳文正,陶果.小波变换在识别储层流体性质中的应用[J].地球物理学报,2003,46(6):863~869
    [100]李舟波.地球物理测井数据处理与综合解释[M].长春:吉林大学出版社,2003
    [101]寻知峰,余继峰.聚类和判别分析在测井岩性识别中的应用[J].山东科技大学学报,2008,27(5):10~13
    [102]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
    [103]潘保芝,李舟波,付有升等.测井资料在松辽盆地火成岩岩性识别和储层评价中的应用[J].石油物探,2009,48(1):48~52
    [104]左晓娜,刘冀伟,王志良.基于TAN贝叶斯网络分类器的测井岩性预测[J].微计算机信息,2006,22(9-1):284~286
    [105]李中亚,韩家新,杜美华.基于生长分层自组织映射网络的岩性识别模型[J].石油矿场机械,2007,36(12):10~13
    [106]张平,潘保芝,张莹等.自组织神经网络在火成岩岩性识别中的应用[J].石油物探,2009,48(1):53~56
    [107]李继安,赵军辉.基于人工神经网络的岩性识别方法[J].铀矿地质,25(4):236~239
    [108]程国建,周冠武,王潇潇.概率神经网络方法在岩性识别中的应用[J].微计算机信息,2007,23(6):288~289
    [109]赵宇,王志良,刘冀伟.一种基于支持向量机的测井岩怀预测新方法[J].微计算机信息,2004,20(6):50~51
    [110]程国建,郭瑞华.PSSO-LSSVM分类模型在岩性识别中的应用[J].西安石油大学学报(自然科学版),2010,25(1):96~99
    [111]张莹,潘保芝.基于主成分分析的SOM神经网络在火山岩岩性识别中的应用[J].测井技术,2009,33(6):550~554
    [112]张小平.用三维地震信息研究碳酸盐岩裂缝性油气藏.天然气工业,1997,17(5):16~19
    [113]尹志军,黄述旺,陈崇河.用三维地震资料预测裂缝[J].石油勘探与开发,1999,26(1):78~80
    [114]徐丽萍,杨勤勇.多波多分量地震技术发展与展望[J].勘探地球物理进展,2002,25(3):47~52
    [115]覃天.多属性相干方法识别微小断层[J].工程地球物理学报,2008,5(5):538~542
    [116]张进铎,杨平,王云雷.地震信息的谱分解技术及应用[J].勘探地球物理学进展,2006,29(4):19~22
    [117]鲍祥生.时移地震属性分析技术的研究与应用[D].成都:西南石油大学,2006
    [118]刘诚,郭科,罗德江.地震属性优化及物性参数反演的一种非线性处理方法[J].地球物理学进展,2007,22(6):1880~1883)
    [119]龚灏,周仲礼,倪艳.基于Isomap算法的地震属性参数降维处理[J].天然气工业,2008,28(5):38~40
    [120]李映,雷晓刚,白本督.基于KPCA的多频极化SAR图像信息压缩和噪声抑制[J].西北工业大学学报,2007,25(5):708~711
    [121]方建斌.基于KPCA的图像匹配算法研究[D].武汉:武汉理工大学,2006
    [122]吴群.基于心电信号的驾驶疲劳检测方法研究[D].杭州:浙江大学,2008
    [123]杨国亮,任金霞,刘细平.基于小波分析和KPCA的人脸识别[J].模式识别与仿真,2003,22(9):29~32
    [124]李学华.基于核与软计算方法的模式分析[D].成都:电子科技大学,2009
    [125]赵峰.基于核方法与累积随机学习的模式分类研究[D].西安:西安电子科技大学,2007
    [126]邓小英,李月.基于Ricker子波核的支持向量回归方法及其在地震勘探记录去噪处理中的应用[J].吉林大学学报(地球科学版),2007,37(4):821~827
    [127]张恒喜.小样本多元数据分析方法及应用[M].西安:西北工业大学出版社,2002
    [128]董辉.基于支持向量机的岩土非线性变形行为预测研究[D].长沙:中南大学,2007
    [129]牟少敏.核方法的研究及其应用[D].北京:北京交通大学,2008
    [130]钟仪华,李榕.基于主成分分析的最小二乘支持向量机岩性识别方法[J].测井技术,2009,33(5):425~429
    [131]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):18~21
    [132]李新虎.基于不同测井曲线参数集的支持向量机岩性识别对比[J].煤田地质与勘探,2007,35(3):72~76
    [133]张翔,肖小玲,严良俊等.基于模糊支持向量机方法的岩性识别[J].石油天然气学报(江汉石油学院学报),2009,31(6):115~118
    [134]许建华,张学工,李衍达.基于最小二乘支持向量机的油气判别技术[J].模式识别与人工智能,2002,15(4):507~510
    [135]乐友喜,袁全社.支持向量机方法在油气储层参数预测中的应用[J].天然气工业,2005,25(12):45~47
    [136]彭新俊.支持向量机若干问题及应用研究[D].上海:上海大学,2008
    [137]乐友喜,王永刚.非参数回归法在孔隙度参数预测中的应用[J].地质科学,2002,37(1):118~126
    [138]郭巧占.基于神经网络的LM算法预测储层声波孔隙度[J].石油钻采工艺,2007,29:99~101
    [139]罗银河,刘江平,肖长度.优化遗传算法在孔隙度预测中的应用[J].地学前缘,2003,10(1):213~217
    [140]顾伟欣,周红.基于逐步回归分析的孔隙度预测方法[J].石油地质与工程,2008,22(1):37~39
    [141]连承波,李汉林,渠芳等.基于测井资料的BP神经网络模型在孔隙度定量预测中的应用[J].天然气地球科学,2006,17(3):382~384
    [142]张彦周.基于支持向量机的测井曲线预测储层参数[D].西安:西安科学大学,2006
    [143]李巍华.基于核方法的机械故障特征提取与分类技术研究[D],武汉:华中科技大学,2003
    [144]张曦.基于统计理论的工业过程综合性能监控、诊断及质量预测方法研究[D].上海:上海交通大学,2008
    [145]王学民.应用多元分析[M].上海:上海财经大学出版社,2004
    [146]甘利灯.四维地震技术及其在水驱油藏监测中的应用[D].北京:中国地质大学,2002.
    [147]李庆忠.岩石的纵、横波速度规律[J].石油地球物理勘探,1992,27(l):1~12.
    [148]张家政,关泉生,谈继强等.Fisher判别红山嘴油田火山岩岩性识别中的应用[J].新疆石油地质,2008,29(6):761~764
    [149]文得进,胡松,曾波等.Fisher判别技术在火成岩流体识别中的应用[J].油气地球物理,2009,7(4):38~41
    [150]刘跃辉,范翔宇,赵建等.基于Fisher判别法的储层流体识别方法[J].石油工业计算机应用,2008,60(4):33~35
    [151]张璐.基于岩石物理的地震储层预测方法应用研究[D].北京:中国石油大学,2009
    [152]杨建礼.叠前敏感弹性参数反演及在西湖凹陷的应用研究[D].北京:中国地质大学,2006
    [153]刘爱疆.川西XC地区典型致密碎屑岩储层岩石物理研究[D].成都:成都理工大学,2010
    [154]吴朝容.致密碎屑岩气藏裂缝性储层预测方法以川西坳陷XC气田须二段为例[D].成都:成都理工大学,2005
    [155]乐友喜,袁全社.支持向量机方法在油气储层参数预测中的应用[J].天然气工业,2005,25(12):45~47
    [156]刘冬娥,黄婧芝,吴国平.用灰色支持向量机进行储层油气、水模式识别[J].石油天然气学报(江汉石油学院学报)2009,31(4):261~264
    [157]苗放,王权海,贺振华.非线性支持向量机在油气预测中的应用[J].矿物岩石,2009,29(4):111~114
    [158]姜静清.最小二乘支持向量机算法及应用研究[D].长春:吉林大学,2007
    [159]陶少逃.最小二乘支持向量机的改进及其在化学化工中的应用[D].杭州:浙江大学,2006
    [160]周绮凤.基于支持向量机的若干分类问题研究[D].厦门:厦门大学,2007
    [161]徐正光,王淑盛,刘冀伟等.基于主成分分析的核Fisher判别方法在油水识别中的应用[J].北京科技大学学报,2005,27(1):126~128
    [162]许建华,张学工,李衍达.应用核Fisher判别技术预测油气储集层[J].石油地球物理勘探,2002,37(2):170~174
    [163]王玉梅,季玉新,李东波等.应用地震属性技术预测A地区储层[J].石油物探,2001,40(4):69~76
    [164]何琰,彭文,殷军.利用地震属性预测渗透率[J].石油学报,2001,22(6):34~36
    [165]居春荣.地震属性技术在岩性油藏开发中的应用[J].现代地质,2004,18(2):244~248
    [166]聂勋碧,施继承等.多参数油气预测系统[J].石油地球物理勘探,1997;32(3):357~364.
    [167]董立生,刘书会等.地震属性分析技术的研究与应用[J].石油物探,2004,43(增刊):17~19.
    [168]王永刚.地震属性分析技术[M].北京:中国石油大学出版社,2006
    [169]陈遵德.储层地震属性优化方法[M].北京:石油工业出版社,1998
    [170]陈冬.地震多属性分析及其在储层预测中的应用研究[D].北京:中国地质大学,2008
    [171]郭刚明.地震属性技术的研究与应用[D].成都:西南石油学院,2005
    [172]周宗良,肖建玲,张枫.地震属性的优化处理及储层厚度的定量解释[J].新疆地质,2002,20(3):262~266
    [173]印兴耀,周静毅.地震属性优化方法综述[J].石油地球物理勘探,2005,8,40(4),482~489
    [174]于建国,姜秀清.地震属性优化在储层预测中的应用[J].2003,24(3):292~294
    [175]孙即祥.现代模式识别[M].长沙:国防科技大学出版社,2002
    [176]郭科等.多元统计方法及其应用[M].成都:电子科技大学出版社,2003
    [177]史卫亚.大规模数据集下核方法的技术研究[D].上海:复旦大学,2008
    [178]赵力民,郎晓玲,金凤鸣等.波形分类技术在隐蔽油藏预测中的应用[J].石油勘探与开发,2001,28(6):53~55
    [179]江春明.大庆太190地区复杂断块油藏描述及剩余油分布研究[D].北京:中国地质大学,2008
    [180]郭淑军,陈开远,唐小梅.波形分析在番禺4洼陷古近系储层研究中的应用[J].石油天然气学报,2008,30(2):81~84
    [181]王玉学,丛玉梅,黄见等.地震波形分类技术在河道预测中的应用[J].资源与产业,2006,8(2):71~74
    [182]胡水清,韩大匡,刘文岭等.频谱分解技术在岩相建模中的应用[J].大庆石油学院学报,2008,32(3):1~4;
    [183]姜秀清.储层地震属性优化及属性体综合解释[D].广州:中国科学院广州地球化学研究所,2006
    [184]张厚柱.综合储层物性参数约束反演[D].北京:清华大学,1996
    [185]王家映.地球物理反演理论[M].北京:中国地质大学出版社,1998
    [186]叶泰然,刘兴艳,苏锦义.地震分频解释技术在川西陆相砂岩储层预测中的应用[J].天然气工业,2007,27(增刊A):454~456
    [187]罗明红.量子遗传算法及其在地球物理反演中的应用研究[D].北京:中国地质大学,2007
    [188]付志方.地震储层预测技术及应用研究[D].北京:中国地质大学,2007
    [189]杨林.地震谱分解技术应用中有关问题的讨论[J].石油物探,2008,47(4):405~409
    [190]敬荣中.地球物理非线性联合反演方法研究[D].长沙:中南大学,2002
    [191]倪凤田.基于地震属性分析的储层预测方法研究[D].北京:中国石油大学,2008
    [192]吴世旗.基于测井地震多属性分析的储层预测方法及应用[D].北京:中国地质大学,2005
    [193]于雪莲.基于核方法和流形学习的雷达目标距离像识别研究[D].成都:电子科技大学,2008
    [194]张学工译.统计学习理论的本质[M].北京:清华大学出版社,2000
    [195]王朝勇.支持向量机若干算法研究及应用[D].长春:吉林大学,2008
    [196]李海生.支持向量机回归算法与应用研究[D].广州:华南理工大学,2005
    [197]张永.基于模糊支持向量机的多类分类算法研究[D].大连:大连理工大学,2007
    [198]边肇祺,张学工.模式识别[M].北京:清华大学出版社,2002
    [199]黎华继.新场气田须二气藏储层评价及综合预测研究[D].成都:成都理工大学,2008
    [200]罗德江.地震属性优化和神经网络在储层预测中的应用.成都:成都理工大学,2006
    [201]苏锦义.新场气田须二段裂缝孔隙性储层综合预测[D].成都:成都理工大学,2008
    [202]何碧竹,周杰,汪功怀.利用多元地震属性预测储层信息[J].石油地球物理勘探.200,38(3):258~261
    [203]王宇超.叠前弹性参数反演应用研究-以塔中45井区为例[D].北京:中国地质大学
    [204]何灵敏.支持向量机集成及在遥感分类中的应用[D].杭州:淅江大学,2006
    [205]孙怡.陡坡带砂砾岩地球物理储声能预测方法应用研究[D].东营:中国石油大学,2008

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700