数据挖掘技术在石油天然气勘探领域的应用探索
|
摘要
基于数据挖掘的概念,详细地阐述了岩石物理数据、测井数据、地震数据和地质数据的特征,并根据其数据特征,确定了岩石物理和测井数据、地震数据和地质数据的三种挖掘思路.用不同的挖掘思路对相应的数据分别展开挖掘,并从挖掘功能的角度分别描述挖掘的成果,即岩石物理数据之间的联系和对储层的预测;测井数据在复杂地质条件下对模糊储层的评价,及有效储层的识别;三维地震数据的空间挖掘成果;地质数据的图表和文本挖掘成果.数据挖掘技术将数据分析方法和对应的数学模型引入勘探领域,从海量的勘探数据中获取潜在信息,用于指导油气的勘探,实现了由数据指导勘探的目的,提出了数据勘探的概念.
The article detailedly describes the features of the petrophysical data, logging data, seismic data and geological data based on the concepts of the data mining. The mining ideas about the petrophysical and logging data, seismic data and geological data are made based on their features. The article uses different mining ways to process the corresponding data, and describes the results from the perspective of the functions of data mining. According to the data mining techniques, the petrophysical data are applied to find the relations and forecast reservoirs; the logging data will be employed to evaluate the fuzzy reservoirs and recognize the effective reservoirs in complicated geological conditions; the space mining results of the 3D seismic data; the charts and text mining results of the geological data. The oil and natural gas data mining in the exploration adopts the methods of data analysis and the corresponding mathematical model to process the exploration data, and get the potential information. It has realized the purpose that the data guide exploration and given the concept of data exploration.
The article detailedly describes the features of the petrophysical data, logging data, seismic data and geological data based on the concepts of the data mining. The mining ideas about the petrophysical and logging data, seismic data and geological data are made based on their features. The article uses different mining ways to process the corresponding data, and describes the results from the perspective of the functions of data mining. According to the data mining techniques, the petrophysical data are applied to find the relations and forecast reservoirs; the logging data will be employed to evaluate the fuzzy reservoirs and recognize the effective reservoirs in complicated geological conditions; the space mining results of the 3D seismic data; the charts and text mining results of the geological data. The oil and natural gas data mining in the exploration adopts the methods of data analysis and the corresponding mathematical model to process the exploration data, and get the potential information. It has realized the purpose that the data guide exploration and given the concept of data exploration.
引文
[1] 瞿辉,赵文智,胡素云.我国油气资源潜力及勘探领域[J].中国石油勘探,2006(4) :1-5． Qu H, Zhao W Z, Hu S Y. Oil & gas resources status and the exploration fields in China[J]. China Petroleum Exploration, 2006(4) :1-5．
[2] 潘继平,金之均.中国油气资源潜力及勘探战略[J].石油学报,2004,25(2) :1-6． Pan J P, Jin Z J. Potentials of petroleum resources and exploration strategy in China[J]. Acta Petrolei Sinica, 2004, 25(2) :1-6．
[3] Alimonti C, Falcone G. Knowledge discovery in databases and multiphase flow metering: the integration of statistics, data mining, neural networks, fuzzy Logic, and ad hoc flow measurements towards well monitoring and diagnosis[R]. SPE 77407, 2002
[4] Stundner M, Al-Thuwaini J S. How data-driven modeling methods like neural networks can help to integrate different types of data into reservoir management[R],SPE68163, 2001．
[5] Clayton V D, Xie Y L, Cullick A S. A rule induction algorithm for application to petrophysical, seismic, geological and reservoir data[R]. SPE68818, 2001．
[6] DeJonge G, Stundner M. How routine reservoir surveillance with neural networks and simplified reservoir models can convert data into information[R]. SPE 78334, 2002
[7] Chen D D, Quirein J, Wiener J. et al. Neural network training-data selection using memory-reduced cluster analysis for field model development[R]. SPE80906, 2003．
[8] Nikravesh M. Soft computing-based computational intelligent for reservoir characterization [J]. Expert Systems With Applications, 2004, 26(1) : 19-38．
[9] Tapias O, Soto C P, Sandoval J. et al. Reservoir engineer and artificial intelligence techniques for data analysis [R], SPE68743, 2001．
[10] Mohaghegh S, Popa A, Gaskari R. et al. Identification of successful practices in hydraulic fracturing using intelligent data mining tools; Application to the codell formation in the DJ-basin[R], SPE 77597, 2002．
[11] Coste J F, Valois J P, Mouret C. et al. Data mining techniques for optimizing fast track re-engineering of mature fields[R], SPE 78333, 2002．
[12] 唐秋华,刘保华,陈永奇,等.结合遗传算法的LVQ神经网络在声学底质分类中的应用[J].地球物理学报,2007,50(1) :313-319． Tang Q H, Liu B H, Chen Y Q, et al. Application of LVQ neural network combined with the genetic algorithm in acoustic seafloor classification [J]. Chinese Journal of Geophysics(in Chinese), 2007, 50(1) : 313-319．
[13] 郑庆生,韩大匡.高阶神经网络在储层分布参数定量预测中的应用[J].地球物理学进展,2007,22(2) :552-555． Zheng Q S, Han D K. Estimation of reservoir distribution parameters using higher-order neural network spproach[J]. Progress in Geophysics (in Chinese) , 2007, 22(2) :552-555．
[14] 陈建江,印兴耀.基于贝叶斯理论的AVO三参数波形反演[J].地球物理学报,2007,50(4) :1251-1260． Chen J J, Yin X Y. Three-parameter AVO waveform inversion based on Bayesian theorem[J]. Chinese Journal of Geophysics(in Chinese), 2007, 50(4) :1251-1260．
[15] 邓小英,李月.Ricker子波核最小二乘支持向量机在地震勘探信号去噪应用中的参数设置研究[J].地球物理学进展,2007,22(3) :953-959． Deng X Y, Li Y. Study of parameters setting for least square support vector machine based on Ricker wavelet kernel in the denoising applications of seismic prospecting signals[J]. Progress in Geophysics (in Chinese), 2007, 22(3) :953-959．
[16] 邹华胜,宁书年,杨峰,等.支持向量机在储层厚度预测和计算中的应用[J].地球物理学进展,2007,22(5) :1597-1601． Zou H S, Ning S N, Yang F, et al. Application of support vector machine to forecasting and calculating reservoir thickness[J]. Progress in Geophysics (in Chinese) , 2007, 22(5) :1597-1601．
[17] 邬世英,王延江,李莉,等.支持向量机在重震联合反演中的应用研究[J].地球物理学进展,2007,22(5) :1611-1616． Wu S Y, Wang Y J, Li L, et al. The application of support vector machine in the joint inversion of gravimetric and seismic data[J]. Progress in Geophysics (in Chinese) , 2007, 22(5) :1611-1616．
[18] Han J W,Kamber M著.数据挖掘概念与技术[M].范明,孟小峰译.北京:机械工业出版社,2007． Han J W, Kamber M. Data mining concepts and techniques, second edition[M]. Beijing: China Machine Press, 2007．
[2] 潘继平,金之均.中国油气资源潜力及勘探战略[J].石油学报,2004,25(2) :1-6． Pan J P, Jin Z J. Potentials of petroleum resources and exploration strategy in China[J]. Acta Petrolei Sinica, 2004, 25(2) :1-6．
[3] Alimonti C, Falcone G. Knowledge discovery in databases and multiphase flow metering: the integration of statistics, data mining, neural networks, fuzzy Logic, and ad hoc flow measurements towards well monitoring and diagnosis[R]. SPE 77407, 2002
[4] Stundner M, Al-Thuwaini J S. How data-driven modeling methods like neural networks can help to integrate different types of data into reservoir management[R],SPE68163, 2001．
[5] Clayton V D, Xie Y L, Cullick A S. A rule induction algorithm for application to petrophysical, seismic, geological and reservoir data[R]. SPE68818, 2001．
[6] DeJonge G, Stundner M. How routine reservoir surveillance with neural networks and simplified reservoir models can convert data into information[R]. SPE 78334, 2002
[7] Chen D D, Quirein J, Wiener J. et al. Neural network training-data selection using memory-reduced cluster analysis for field model development[R]. SPE80906, 2003．
[8] Nikravesh M. Soft computing-based computational intelligent for reservoir characterization [J]. Expert Systems With Applications, 2004, 26(1) : 19-38．
[9] Tapias O, Soto C P, Sandoval J. et al. Reservoir engineer and artificial intelligence techniques for data analysis [R], SPE68743, 2001．
[10] Mohaghegh S, Popa A, Gaskari R. et al. Identification of successful practices in hydraulic fracturing using intelligent data mining tools; Application to the codell formation in the DJ-basin[R], SPE 77597, 2002．
[11] Coste J F, Valois J P, Mouret C. et al. Data mining techniques for optimizing fast track re-engineering of mature fields[R], SPE 78333, 2002．
[12] 唐秋华,刘保华,陈永奇,等.结合遗传算法的LVQ神经网络在声学底质分类中的应用[J].地球物理学报,2007,50(1) :313-319． Tang Q H, Liu B H, Chen Y Q, et al. Application of LVQ neural network combined with the genetic algorithm in acoustic seafloor classification [J]. Chinese Journal of Geophysics(in Chinese), 2007, 50(1) : 313-319．
[13] 郑庆生,韩大匡.高阶神经网络在储层分布参数定量预测中的应用[J].地球物理学进展,2007,22(2) :552-555． Zheng Q S, Han D K. Estimation of reservoir distribution parameters using higher-order neural network spproach[J]. Progress in Geophysics (in Chinese) , 2007, 22(2) :552-555．
[14] 陈建江,印兴耀.基于贝叶斯理论的AVO三参数波形反演[J].地球物理学报,2007,50(4) :1251-1260． Chen J J, Yin X Y. Three-parameter AVO waveform inversion based on Bayesian theorem[J]. Chinese Journal of Geophysics(in Chinese), 2007, 50(4) :1251-1260．
[15] 邓小英,李月.Ricker子波核最小二乘支持向量机在地震勘探信号去噪应用中的参数设置研究[J].地球物理学进展,2007,22(3) :953-959． Deng X Y, Li Y. Study of parameters setting for least square support vector machine based on Ricker wavelet kernel in the denoising applications of seismic prospecting signals[J]. Progress in Geophysics (in Chinese), 2007, 22(3) :953-959．
[16] 邹华胜,宁书年,杨峰,等.支持向量机在储层厚度预测和计算中的应用[J].地球物理学进展,2007,22(5) :1597-1601． Zou H S, Ning S N, Yang F, et al. Application of support vector machine to forecasting and calculating reservoir thickness[J]. Progress in Geophysics (in Chinese) , 2007, 22(5) :1597-1601．
[17] 邬世英,王延江,李莉,等.支持向量机在重震联合反演中的应用研究[J].地球物理学进展,2007,22(5) :1611-1616． Wu S Y, Wang Y J, Li L, et al. The application of support vector machine in the joint inversion of gravimetric and seismic data[J]. Progress in Geophysics (in Chinese) , 2007, 22(5) :1611-1616．
[18] Han J W,Kamber M著.数据挖掘概念与技术[M].范明,孟小峰译.北京:机械工业出版社,2007． Han J W, Kamber M. Data mining concepts and techniques, second edition[M]. Beijing: China Machine Press, 2007．
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