基于粗糙集理论和支持向量机的套管损坏动态预报方法
|
摘要
针对油水井套管损坏受地质、工程综合因素影响,具有不确定性、模糊性和时变性的特点,提出基于粗糙集与支持向量机集成的套损动态预报方法。通过粗糙集理论对套损影响因素进行属性约简,确定导致油水井套管损坏的主导因素,进而应用支持向量机算法建立套管损坏动态预报模型,从而克服传统支持向量机无法处理动态数据以及大样本条件下易出现维数灾难的缺点。榆树林油田的现场应用结果表明,该方法具有较高的预报精度,预报吻合率达72.7%,可为油田现场调整开发参数、尽早制定套管防护措施提供指导。
Aiming at casing damage problem affected by both geological factors and engineering factors,with characteristics of uncertainty,fuzziness,time-varying,a dynamic prediction method of casing damage was proposed based on rough set integrated with support vector machine.The influencing factors for casing damage were reduced by using rough set theory and the main factors causing casing damage were obtained.Then prediction models were established based on support vector machine,and the problem that the traditional support vector machine can not deal with dynamic data and is prone to dimension disasters with large samples,was avoided in this method.The field application in Yushulin Oilfield indicates that the prediction consistent rate is 72.7% in this method,which provides guidance for oilfield adjusting development parameters and developing casing protection measures early.
Aiming at casing damage problem affected by both geological factors and engineering factors,with characteristics of uncertainty,fuzziness,time-varying,a dynamic prediction method of casing damage was proposed based on rough set integrated with support vector machine.The influencing factors for casing damage were reduced by using rough set theory and the main factors causing casing damage were obtained.Then prediction models were established based on support vector machine,and the problem that the traditional support vector machine can not deal with dynamic data and is prone to dimension disasters with large samples,was avoided in this method.The field application in Yushulin Oilfield indicates that the prediction consistent rate is 72.7% in this method,which provides guidance for oilfield adjusting development parameters and developing casing protection measures early.
引文
[1]刁顺,杨春和,刘建军,等.渗流诱发套损机制与数值计算[J].岩土力学,2008,29(2):327-331.DIAO Shun,YANG Chun-he,LIU Jian-jun,et al.Mechanism of seepage induced casing damage and numer-ical simulation[J].Rock and Soil Mechanics,2008,29(2):327-331.
[2]王仲茂,卢万恒,胡江明.油田油水井套管损坏的机理及防治[M].北京:石油工业出版社,1994.
[3]裴桂红,纪佑军.油水井套损的地质因素分析[J].武汉工业学院学报,2009,28(3):102-105.PEI Gui-hong,JI You-jun.Analysis on geological effectson oil and water well casing damage[J].Journal of Wu-han Polytechnic University,2009,28(3):102-105.
[4]张文修,吴伟志,梁吉业,等.粗糙集理念与方法[M].北京:科学出版社,2001.
[5]邓九英,王钦若,毛宗源,等.基于粗糙集的支持向量回归机混合算法[J].中国石油大学学报:自然科学版,2009,33(5):159-163.DENG Jiu-ying,WANG Qin-ruo,MAO Zong-yuan,etal.Support vector regression hybrid a lgorithm based onrough set[J].Journal of China University of Petroleum(Edition of Natural Science),2009,33(5):159-163.
[6]梁武科,赵道利,马薇,等.基于粗糙集-RBF神经网络的水电机组故障诊断[J].仪器仪表学报,2007,28(10):1806-1809.LIANG Wu-ke,ZHAO Dao-li,MA Wei,et al.Fault di-agnosis of hydroelectric units based on rough set&RBFnetwork[J].Chinese Journal of Scientific Instrument,2007,28(10):1806-1809.
[7]王威,马东辉,苏经宇,等.基于RS-SVM的地下管线震害预测方法研究[J].应用基础与工程科学学报,2009,17(2):274-279.WANG Wei,MA Dong-hui,SUJing-yu,et al.Study onpredicting method for earth quake damage to undergroundpipelines system based on rough set and support vectormachine[J].Journal of Basic Science and Engineering,2009,17(2):274-279.
[8]杨培杰,印兴耀.基于支持向量机的叠前地震反演方法[J].中国石油大学学报:自然科学版,2008,32(1):37-41.YANG Pei-jie,YIN Xing-yao.Prestack seismic inversionmethod based on support vector machine[J].Journal ofChina University of Petroleum(Edition of Natural Sci-ence),2008,32(1):37-41.
[9]徐长航,陈国明,谢静.基于支持向量机和蒙特卡洛的结构可靠性分析方法及应用[J].中国石油大学学报:自然科学版,2008,32(4):103-107.XU Chang-hang,CHEN Guo-ming,XIE Jing.Structuralreliability analysis method based on support vector ma-chines and Monte Carlo and its application[J].Journal ofChina University of Petroleum(Edition of Natural Sci-ence),2008,32(4):103-107.
[10]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.ZHANG Xue-gong.Introduction to statistical learningtheory and support vector machines[J].Acta AutomaticaSinica,2000,26(1):32-42.
[11]王国胜.基于支持向量机的数据挖掘研究[J].计算机工程,2008,34(8):47-49.WANG Guo-sheng.Research on data mining based onsupport vector machine[J].Computer Engineering,2008,34(8):47-49.
[2]王仲茂,卢万恒,胡江明.油田油水井套管损坏的机理及防治[M].北京:石油工业出版社,1994.
[3]裴桂红,纪佑军.油水井套损的地质因素分析[J].武汉工业学院学报,2009,28(3):102-105.PEI Gui-hong,JI You-jun.Analysis on geological effectson oil and water well casing damage[J].Journal of Wu-han Polytechnic University,2009,28(3):102-105.
[4]张文修,吴伟志,梁吉业,等.粗糙集理念与方法[M].北京:科学出版社,2001.
[5]邓九英,王钦若,毛宗源,等.基于粗糙集的支持向量回归机混合算法[J].中国石油大学学报:自然科学版,2009,33(5):159-163.DENG Jiu-ying,WANG Qin-ruo,MAO Zong-yuan,etal.Support vector regression hybrid a lgorithm based onrough set[J].Journal of China University of Petroleum(Edition of Natural Science),2009,33(5):159-163.
[6]梁武科,赵道利,马薇,等.基于粗糙集-RBF神经网络的水电机组故障诊断[J].仪器仪表学报,2007,28(10):1806-1809.LIANG Wu-ke,ZHAO Dao-li,MA Wei,et al.Fault di-agnosis of hydroelectric units based on rough set&RBFnetwork[J].Chinese Journal of Scientific Instrument,2007,28(10):1806-1809.
[7]王威,马东辉,苏经宇,等.基于RS-SVM的地下管线震害预测方法研究[J].应用基础与工程科学学报,2009,17(2):274-279.WANG Wei,MA Dong-hui,SUJing-yu,et al.Study onpredicting method for earth quake damage to undergroundpipelines system based on rough set and support vectormachine[J].Journal of Basic Science and Engineering,2009,17(2):274-279.
[8]杨培杰,印兴耀.基于支持向量机的叠前地震反演方法[J].中国石油大学学报:自然科学版,2008,32(1):37-41.YANG Pei-jie,YIN Xing-yao.Prestack seismic inversionmethod based on support vector machine[J].Journal ofChina University of Petroleum(Edition of Natural Sci-ence),2008,32(1):37-41.
[9]徐长航,陈国明,谢静.基于支持向量机和蒙特卡洛的结构可靠性分析方法及应用[J].中国石油大学学报:自然科学版,2008,32(4):103-107.XU Chang-hang,CHEN Guo-ming,XIE Jing.Structuralreliability analysis method based on support vector ma-chines and Monte Carlo and its application[J].Journal ofChina University of Petroleum(Edition of Natural Sci-ence),2008,32(4):103-107.
[10]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.ZHANG Xue-gong.Introduction to statistical learningtheory and support vector machines[J].Acta AutomaticaSinica,2000,26(1):32-42.
[11]王国胜.基于支持向量机的数据挖掘研究[J].计算机工程,2008,34(8):47-49.WANG Guo-sheng.Research on data mining based onsupport vector machine[J].Computer Engineering,2008,34(8):47-49.
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