地质导向钻井随钻预测方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
在水平井钻井中,如何确定目标层的位置保证钻头在目标层内钻进是开发复杂储藏及薄油藏的一个非常关键的问题,也是目前我国地质导向钻井中一个急需解决的技术难点。
     本文以中石化重点攻关项目“地质导向钻井工艺技术研究”为背景,重点对地质导向钻井中随钻预测方法进行研究,分别利用支撑向量机、卡尔曼滤波理论、时间序列等理论分析综合测井参数、钻井参数及MWD随钻测量信息对钻头处的地质参数及井眼轨迹进行预测,以便进行实时地质导向。本文主要贡献如下:
     1、提出了基于支撑向量机统计学习理论的自然伽马随钻预测及校正方法,并进一步对地层电阻率进行了预测。试验表明,该方法能够及时有效的预测出钻头处的自然伽马和电阻率曲线,为井眼在产层中延伸提供了依据。
     2、根据参数估计理论,建立了基于卡尔曼滤波器的井眼轨迹预测模型,该模型可用于预测钻头处的井斜角和方位角,实验结果说明了该模型的有效性。
     3、将时间序列理论和支撑向量机相结合,建立了基于支撑向量机的时间序列预测模型,它通过机器学习的方法根据已钻井的轨迹参数构造支撑向量机进行井眼轨迹预测。实例分析表明,该方法简单有效且估计精度远远高于传统的定曲率法。
During the horizontal well drilling, it is very important to know theposition of the geological target and maintain the well path at a constantrelative position within the target while developing complicated reservoirs orthin reservoirs, which is also a key technique problem of geosteeringdemanding an immediate solution at present in china.
     Based on the key project of SinoPec---'Research on GeosteeringTechniques', this thesis mainly studies on the methods of predicting whilegeosteering drilling. After analysis of the well-logging parameter, drillingparameter and MWD data, some new methods are proposed to predict thegeological data and the trajectory data at the bit by some new informationprocessing techniques, and they can be used to geosteer the well whiledrilling in real time.
     The main contributions are as follows:
     1. A new method for predicting the gamma ray at the bit position isproposed based on support vector machine (SVM).The predicted gamma raycurve is then corrected by the data measured by LWD sensor along the wellpath, and the resistivity curve is predicted also. Experimental results show theproposed method can estimate the gamma ray and the resistivity curve at the bit effectively, and it can be used to geosteer the well while drilling in realtime.
     2. A novel wellbore trajectory prediction model is founded using thekalman filter, which is based on parameter estimation theory. It is used topredict the well inclination and azimuth angles. The experimental resultsshow that the proposed model is effective.
     3. Another well trajectory prediction model is established based on thecombination of time series and the SVM. The basic idea of this method is topredict the wellbore trajectory by learning using the trajectory data measuredby MWD. The experimental results show that the proposed method hashigher precision compared with the traditional methods and can be easilyused.
引文
[1] 地质导向钻井工艺技术研究开题报告(内部参考).胜利油田钻井工艺技术研究院,2001.1
    [2] 徐显广.新疆莫北油田砂砾岩油藏随钻跟踪地质目标钻井技术研究:[博士学位论文].西南石油学院,北京:2001.12
    [3] 徐显广等.地质导向钻井技术的现场应用.西南石油学院学报,2002;24(2):53~55
    [4] 时鹏程,许磊.地质导向钻井技术综述.断块油气田,1998;5(2):58~66
    [5] 时鹏程等.面向地质导向应用的前导模拟技术研究.测井技术,2000;24(6):415~419
    [6] 时鹏程.随钻测井技术在我国石油勘探开发中的作用.测井技术,2002;26(6):441~445
    [7] 时鹏程.MWDLWD 实践与操作指南.录井技术,2000;11(2):63~68
    [8] 陆黄生.地质导向:预测钻头前的地层.世界石油工业,1999;6(6):35~40
    [9] 江国法.地质导向.测井技术信息,2000;13(1):14~23
    [10] 林广辉.地质导向系统的研究与应用中国海上油气(工程),2000;12(5):39~47
    [11] 张建国.地质导向法在井下地质预测中的应用.石油勘探开发情,1998;3(5):39~45
    [12] 岳登进,冯明.过去10 年国外钻井技术的重要进步.钻采工艺,2001;24(4):10~13
    [13] 张绍槐等.石油钻井信息技术的智能化研究.石油学报,1996;17(4):114~119
    [14] 张绍槐,张洁等.关于21 世纪中国钻井技术发展对策的研究.石油钻探技术,2000;28(1):4~7
    [15] C.E.Jackson. Using pay zone steering in high-angle and horizontalwells. SPE 37819,1997:487~500
    [16] D.N. Meehan. Geological steering of horizontal wells. SPE 29242,1994:848~852
    [17] W.H.Meyer, et al. Brief:Geosteering with near-bit formation evaluationsensors. SPE 30142, 1995:117~118
    [18] M.R.Coutinho.Geosteering horizontal wells using resistivity anisotropyobtained in an offset vertical well. SPE 81137, 2003:1~8
    [19] A. Barry, et al. Geosteering horizontal wells in a thin oil column. SPE50072,1998:221~233
    [20] J.D.Prilliman,D.F. Allen,and L.R. Lehtonen. Horizontal wellplacement and petrophysical evaluation using LWD. SPE 30549, 1995:173~185
    [21] T.Schroeder,et al. Geosteering methods: Predicting the geology aheadof the bit. The Log Analyst,1998:44~50
    [22] J.Wu, M.M.Wisler. Method for drilling directional wells. U.S.PatentNo.5,230,386,1993
    [23] Chih-Wei Hsu, et al. A Practical Guide to Support Vector Classification.Department of Computer Science and Information Engineering, NationalTaiwan University.
    [24] Guozheng Li. OutLine of Support Vector Machines. A Course ofComputational Intelligence , Shanghai Jiao Tong University. 2002,3
    [25] Vapnik V N.统计学习理论的本质.张学工译,北京:清华大学出版社,2000
    [26] 边肇祺,张学工.模式识别.第2版.北京:清华大学出版社,2000.
    [27] JunShui Ma, James Theiler and Simon Perkins. Accurate OnlineSupport Vector Regression. NIS-2 Los Alamos National Laboratory ,LosAlamos, NM 87545, USA.
    [28] 张恒喜等.小样本多元数据分析方法及应用.西北工业大学出版社,2002
    [29] 张学工.关于统计学习理论与支持向量机.自动化学报,2000,26(1):32~42
    [30] 史清江,王延江.用于非线性回归估计的支持向量机,第19 届中国自动化学会青年学术会议,2004.7
    [31] 刘宜平.浅谈钻时在录井及钻井中得应用.江汉石油大学职工学报,2004,3
    [32] 吴华强,周艳琴.MWD GAMMA测量技术在地质导向钻井中的应用.断块油气田,2005,3
    [33] 夏宏泉等.随钻测井曲线的模拟生成及其地质导向应用研究.天然气工业,2003,23(3):51~55
    [34] 苏义脑著.水平井井眼轨道控制.北京:石油工业出版社,2000,09
    [35] 白家祉,苏义脑著.井斜控制理论与实践.北京:石油工业出版社,1990,04
    [36] Ho H-S. Prediction of drilling trajectory in directional wells via a newrock-bit interaction model. SPE 16685,1987
    [37] 苏义脑,张海.水平井钻具组合大变形有限元分析.石油钻探技术,1995,23(1):1~4
    [38] 帅健,蔡强康,吕英民.弯曲井眼中下部钻具组合有限元分析.石油学报,1990,11(4):95~105
    [39] 于长官著.现代控制理论.哈尔滨:哈尔滨工业大学出版社,1997.07
    [40] 张洪钺,陈新海著.最佳估计理论.北京:北京航空学院出版社,1987.12
    [41] 熊金志,胡金莲.卡尔曼滤波在某深控系统中的应用.华东交通大学学报,1996,13(3):57~63
    [42] 陈爱新,聂在平,钟兴水.卡尔曼滤波在钻井地层电阻率测量中的应用.电波科学学报,1998,13(3):270~274
    [43] 崔乃刚等.卡尔曼滤波方法在测井资料处理中的应用.哈尔滨工业大学,1995,27(6):34~37
    [44] 李象霖,温志勇等.卡尔曼滤波方法用于估计物体运动参数.电子学报,1995,23(1):93~98
    [45] Xangdong Xie ,et al. Real-Time Eye Feature Tracking From a VideoImage Sequence Using Kalman Filter . IEEE Trans. PAMI, 1995,25(12):1568~1577
    [46] 杨叔子,吴雅.时间序列分析的工程应用(上、下册).华中理工大学出版社,1996.
    [47] 范剑青.非线性时间序列-建模、预报及应用.等教育出版社
    [48] 王振隆等.时间序列分析.国统计出版社.2000(2)
    [49] 尉询楷,李应红等.基于支持向量机的航空发动机滑油监控分析.航空动力学报.2004(3):392~397
    [50] 李子丰.井眼轨道控制理论.北京:石油工业出版社,1996,1
    [51] Millheim K K. BHA analysis using the finite-element method. SPE6057,1978
    [52] Haruya Nakata, Satoshi Ujo, Satoshi Nakashima, et al. Development ofwell trajection prediction system of directional well and study ofgeological effect on directional drilling. Proceedings World GeothermalCongress 2000. Japan,May 28-June 10,2000
    [53] Alberto Malinverno, et al. Real-Time Earth Model Updating WhileDrilling a Horizontal Well. SPE 77525, 2002
    [54] T, Dahl and B. Schmalhorst, Eastman Christensen. A New BottomholeAssembly Analysis Program for the Prediction of the Borehole PathBased on a Sophisticated Static Algorithm. SPE/IADC 21948,1991
    [55] 蔡雨田,陈天成等.定向井水平井井眼轨迹控制技术及应用.中国新星石油文集.地质出版社,1999
    [56] 苏义脑.大庆树平1 井的井眼轨道控制.石油钻采工艺.1992(4):7~16
    [57] 高德利,刘希圣.钻头与地层相互作用新模型.石油钻采工艺,1989,11(5):23~30
    [58] 王珊,刘修善等.井眼轨道的空间挠曲形态.大庆石油学院学报,1993,17(3):32~35
    [59] 帅健.定向钻井的计算机模式.石油钻采工艺,1990,(3):1~8

© 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