摘要
随着油田开发过程的持续进行,地下储层结构、储层物性、孔隙结构等都发生一定变化,这些变化使得油气开采变得困难。目前在油田地质建模研究中,三维静态模型从空间的角度对储层的分布和各种属性进行了定量的分析,但由于油田开发是一个随着时间不断变化的动态过程,三维模型在某种程度上不能满足油田的需求。因此,需要进行时空维数据建模技术的研究。
本课题针对油藏动态开发问题,从三维空间储层注采过程模拟角度建立时空维分析模型。在空间三维静态模型的基础上,结合指标变量随时间的变化进行时空维模型研究。在建模中,考虑时间变量的连续性,需要模型解决多元过程信号输入输出关系,并有快速处理信号的能力。论文对时空维模型进行研究,通过研究时空维建模的理论方法和研究算法,建立一种能够处理多个时间片段的网络模型。论文分析了时空维数据模型特征,研究了可用于构建地质动态模型的算法,如涉及油藏知识的渗流微分方程,整体建模的径向动态回归模型,以及在机制上可直接对时空维系统进行建模的多聚合过程神经元网络。多聚合过程神经网络是把传统的神经网络扩展到时间域上,网络的输入、输出、连接权函数均可为依赖于时间变化的多元连续函数,网络具有良好的自适应、较高的容错能力和模型适应能力强等优点,可作为时空维系统建模的一种通用方法。
本文针对时空维建模数据运算量大、信息变化机制复杂、训练时间长等问题,设计了分式多聚合神经网络和勒让德正交基变换多聚合神经网络两种网络模型。利用三维静态模型结合动态模型来对油藏储层进行可视化显示,通过对显示图像的分析处理可以为油田工作者提供直观的帮助,具有良好的应用前景。
With the continuous development of oilfield exploitation, the underground reservoirstructure, reservoir property, and pore structure have occurred some changes, which make theoil and gas exploitation difficult. At present in the field of geological modeling study, athree-dimensional static model on the spatial perspective is used to make a quantitativeanalysis of reservoir distribution and various properties, however oilfield exploitation is adynamic process with time, the3D model can not meet the needs of oil field to some extent.Therefore, spatiotemporal data modeling technology research is necessary.
In this paper, an analytical model of the space-time dimension on three-dimensionalreservoir injection and process simulation was established for dynamic reservoir developmentissues. We conduct research on indicator variables change with time based on threedimensional static model. Considering the continuity of the time variable, the model need tosolve the problem of multi-process signal input-output relationship and the ability of fastsignal processing on modeling. The paper do research on space-time dimensional model, anetwork model that can solve more than one time-slice problem is established by the theory ofspace-time dimensional modeling methods and algorithms. The algorithm can be used to buildthe geological dynamic model, involving the differential equations of seepage of the reservoirof knowledge, the overall modeling of the radial dynamic regression models, as well as aneural network that can be directly used on the space-time dimension system for modelingmulti-polymerization process neural network. Multi-polymerization process neural networkextends the traditional neural network to the time domain, the input and output connectionweights of the network function can depend on the time-varying multivariate continuousfunction, the network has the advantages of good adaption, high fault tolerance adaptability,and an the model can be used as a general method of space-time dimensional modeling.
In this paper, we designed two network model of fractional multi-polymerization processneural networks and legendre orthogonal basis transform polymer neural network forspace-time dimensional modeling data computation, the complex mechanism of informationchanges, long training time,3D static model and dynamic model used to the reservoir visualdisplay, the analysis processing for display of the image to provide intuitive help for the oilfield workers, which has a good application prospects.
引文
[1]彭仕宓.建立储层四维地质模型的尝试[J].地质评论,2004(06):662~663.
[2]王涛.系统建模方法综述[J].科技资讯,2008(28):34~36.
[3]任祖华.非线性倒立摆系统的神经网络辨识[J].计算技术与自动化,2004(04):20~22.
[4] LIU Chunying, ZHANG Chuang, YANG Xiaoman, GONG Haidong. A Multilayer Studyof pCO_2in the Surface Waters of the Yellow and South China Seas in Spring and theSea-Air Carbon Dioxide Flux[J]. Journal of Ocean University of China,2008-03(006),373~378.
[5] LIU He, HUANG Dao. A Multilayer Recurrent Fuzzy Neural Network for AccurateDynamic System Modeling[J]. Journal of Donghua University(English Edition),2008-04(004),263~268.
[6] WU Shi-qian, Joo Er M, YANG Gao. A fast approach for automatic generation of fuzzyrules by generalized dynamic fuzzy neural networks[J]. IEEE Transactions on FuzzySystems,2001,(04):578~593.
[7]王明明.多变量闭环辨识[D].北京化工大学,2008,1~12.
[8]张必银.小目标检测识别技术性能评价研究[D].华中科技大学,2007,14~24.
[9]田福全. Web QoS的辨识与控制器设计[D].江南大学,2011,4~10.
[10]陈德元.秘鲁Capahuari Sur油田三维精细地质建模[D].长安大学,2007,5~30.
[11]解伟.储层建模方法研究[J].黑龙江科技信息,2010(15),759~763.
[12]龙章亮.留西油田留17断块储层地质建模及开发技术研究[D].成都理工大学,2009,11~45.
[13]胡向阳,熊琦华,吴胜和.储层建模方法研究进展[J].石油大学学报,2001(01):107~111.
[14]吴建祥.陕北气田地质建模及其应用研究[D].西安石油大学,2009,2~12.
[15]盖凌云.随机建模方法的技术研究及软件应用[J].现代电子技术,2007(09):172~178.
[16]张敏.油气储层随机建模技术概述[J].内蒙古石油化工,2007(05):246~248.
[17]刘颖.储层地质建模方法[J].中外科技情报,2007(04):828~836.
[18] MACDONALD A C, AA SEN J O. A prototype procedure for stochastic modeling offacies tract distribution inshoreface reservoirs[A]. In: Yarus and chamber(eds.).Stochastic Modeling and Geostatist ics: Principles, Methods, and Case Studies[C]. AAPG Computer Application in Geology,1994,(07):77~89.
[19]李霞,王铜山,王建新.储层随机建模方法研究进展[J].物探化探计算技术,2009,31(05):454~459.
[20]江苗.靖安油田虎狼峁区长6油藏精细描述[D].西安石油大学,2006,5~68.
[21] JOURNEL A G. Non parametric estimation of spatial distributions[J]. MathematicalGeology,1983,(15):445~468.
[22] FARMER C L. The generation of stochastic fields of reservoir parameters with specifiedgeostatistical distribution[A]. Mathematics in Oil Production [C], Oxford, ClarendonPress,1988.235~252.
[23]徐志华.离散裂缝网络地质建模技术研究[D].中国石油大学(华东),2009,40~56.
[24]阳文锐,王如松,黄锦楼.反距离加权插值法在污染场地评价中的应用[J].应用生态学报,2007,18(09):2013~2018.
[25]程翔.基于GIS的地震动强度(烈度)速报系统研究[D].中国地震局工程力学研究所,2011,38~52.
[26]袁静国.自适应Kriging优化算法及其在PMLSM设计中的应用[D].沈阳工业大学,2010,5~38.
[27]张健.飞机多学科设计优化中的近似方法研究[D].西北工业大学,2006,30~45.
[28]刘鑫.活断层地理信息系统设计与相关问题研究[D].大连理工大学,2007,11~24.
[29]刘明.基于MPPNN时空维动态系统建模技术研究[D].东北石油大学,2011,8~45.
[30]刘素芹.数据库中的知识发现研究进展[J].油气田地面工程,2003(04),54~55.
[31]姜斌.基于二维主分量分析的光谱数据降维方法[J].现代电子技术,2007(14),21~23.
[32]黄柏龄.掘进机械的动态分析之管见[J].地球科学:中国地质大学学报,1991(04),453~458.
[33]王莉.线性控制系统动平衡状态分析[J].自动化与仪表,2007(03),21~25.
[34]赵世武.分数阶MIMO控制系统状态空间建模分析[J].合肥工业大学学报:自然科学版,2004,68~74.
[35]刘宁.火灾与气象因素的相关性研究[J].武警学院学报,2010(02),22~25.
[36]李国柱.应用多元线性方法对我国国债发行规模影响因素的分析[J].石家庄经济学院学报,2001(06),607~611.
[37]付旭云.基于双隐层径向基过程神经网络的润滑油金属含量预测[J].润滑与密封,2009(02),17~20.
[38]许少华.多聚合过程神经元网络及其学习算法研究[J].计算机学报,2007(01),48~56.
[39] Xu Shao-hua, He Xin-gui. Learning algorithms of process neural networks based onorthogonal function basis expansion[J]. Chinese Journal of Computers,2004,27(5):645~650,
[40] Lee K, Peng H. Identification and verification of a longitudinal human driving model forcollision warning and avoidance systems[J]. Int J Vehicle Autonomous Systems,2004,2(1/2):3~17.
[41] Kim T, Lovell D J, Park Y. Limitation of previous models on car-following behavior andresearch needs[C]. The82th Transportation Research Board Annual Meeting No.03-3721.Washington D. C.2003.
[42] Panwai S, Dia H. Development and evaluation of a reactive agent-Based car followingmodel[C]. Proceedings of the Intelligent Vehicles and Road InfrastructureConference(IVRI`05),16th and17th. Melbourne.2005.
[43]许少华.关于连续过程神经元网络的一些理论问题[J].电子学报,2006(10):1838~1841.
[44]许少华,何新贵,王兵.一种分式过程神经网络及其应用研究[J].计算机研究与发展,2006(12),2088~2095.
[45]何新贵等.一类反馈过程神经元网络模型及其学习算法[J].自动化学报,2004(06),801~806.
[46]许少华,何新贵.基于函数正交基展开的过程神经网络学习算法[J].计算机学报,2004,27(05),645~650.
[47] He Xin Gui, Liang Jiu Zhen.Some theoretical issues on process neural networks[J].Engineering Science,2000,2(12):40~44.
[48] He Xin Gui, Liang Jiu Zhen, Xu Shao Hua. Learning and applicat ionsof process neuralnetworks[J]. Engineering Science,2001,3(04):31~35.
[49] Wang, D. M, Zhao, L. S, Cheng, J. C, Wu, J. Z. Actual field data show that productioncosts of polymer flooding can be lower than water flooding[C]. SPE84849,2003.
[50] Wang Demin, Cheng Jiecheng, Wu Junzheng, etal. Experienceslearned after productionmore than300million barrels of oil bypolymer flooding in Daqing Oilfield[C].SPE77693.2002,9~29(2).
[51]刘义坤,刘云龙等.萨中开发区高台子油层的水洗特征[J].大庆石油地质与开发,2005.56~58.
[52]许少华,单彬.人工神经网络在储层地质建模中的应用研究[J].科学技术与工程,2011(31),7650~7654.