概率神经网络技术在非均质地层岩性反演中的应用
|
摘要
提出了一种由多测井和多地震属性参数组成的概率神经网络方法,来进行非均质性较强的油气储层的预测。介绍了该方法的网络模型构建和地层岩性预测的过程。利用该概率神经网络方法,研究了我国西南某一岩性油气田沙一段湖滩砂及河道砂体。运用测井响应特征、地震属性特征与地质岩性特征的相关性对概率神经网络进行了培训,从而对地层特征进行了预测和识别,并取得了较好的应用效果。
In order to predict the reservoir with strong heterogeneity,a probabilistic neural network technique was developed on the theory of probabilistic density function and trained using known information of sandstone-mudstone reservoir.The probabilistic neural network was used to predict the reservoirs of a lithologic oilfield in the southwest China.The targets in the study area are the beach sandstone and channel sandstone of Sha-1 Member where the reservoir thickness is small and the lateral change of lithology is big.The correlations among the features of logging,seismic attributes and geological lithology were developed to train the probabilistic neural network,and the seismic attributes were transformed by the trained network to identify the lithologic information of reservoirs.The results show that the probabilistic neural network technique has good application effectiveness in the actual data processing.
In order to predict the reservoir with strong heterogeneity,a probabilistic neural network technique was developed on the theory of probabilistic density function and trained using known information of sandstone-mudstone reservoir.The probabilistic neural network was used to predict the reservoirs of a lithologic oilfield in the southwest China.The targets in the study area are the beach sandstone and channel sandstone of Sha-1 Member where the reservoir thickness is small and the lateral change of lithology is big.The correlations among the features of logging,seismic attributes and geological lithology were developed to train the probabilistic neural network,and the seismic attributes were transformed by the trained network to identify the lithologic information of reservoirs.The results show that the probabilistic neural network technique has good application effectiveness in the actual data processing.
引文
[1]杨文采.地球物理反演的理论与方法[M].北京:地质出版社,1997:242-267.Yang Wencai.Theory and methodology on geophysics inversion[M].Beijing:Geological Publishing House,1997:242-267.
[2]Liu Zhengping,Liu Jiaqi.Seismic-controlled nonlinear extrapola-tion of well parameters using neural networks[J].Geophysics,1998,63(6):2035-2041.
[3]de Groot P F M,Bril A H,Floris F J T,et al.Monte Carlo simu-lation of wells[J].Geophysics,1996,61(3):631-638.
[4]Sen W K,Stoffa P L.Nonlinear one-dimensional seismic wave-form inversion using simulated annealing[J].Geophysics,1991,56(10):1624-1638.
[5]McCormack M D.Neural computing in geophysics[J].The Lead-ing Edge,1991,10(1):11-15.
[6]Masters T.Signal and image processing with neural networks[M].New York:John Wiley&Sons Incorporation,1994:1-200.
[7]Specht D F.A general regression neural network[J].IEEETransaction on Neural Networks,1991,2(6):568-576.
[8]徐旺林,庞雄奇,吕淑英,等.动态概率神经网络及油气概率分布预测[J].石油地球物理勘探,2005,40(1):65-70.Xu Wanglin,Pang Xiongqi,LüShuying,et al.Dynamic probabi-listic neural network and predicting probabilistic distribution ofoil/gas[J].Oil Geophysics Prospecting,2005,40(1):65-70.
[9]杨长保,聂兰仕,孙鹏远.改进的模糊神经网络模型在储层产能预测中的应用研究[J].吉林大学学报:地球科学版,2003,33(1):48-50.Yang Changbao,Nie Lanshi,Sun Pengyuan.A study of using im-proved fuzzy neural network to forecast reservoir productivity[J].Journal of Jilin University:Earth Science Edition,2003,33(1):48-50.
[10]赵力民,邹伟宏,郎晓玲,等.利用RM反演方法进行地层岩性油藏研究[J].石油学报,2000,21(2):62-65.Zhao Limin,Zou Weihong,Lang Xiaoling,et al.Lithologic oilreservoir research by means of RM inversion method[J].ActaPetrolei Sinica,2000,21(2):62-65.
[11]邹才能,李明,赵文智,等.松辽南部构造—岩性油气藏识别技术及应用[J].石油学报,2004,23(3):32-36.Zou Caineng,Li Ming,Zhao Wenzhi,et al.Recognition techniqueand application of structure-lithology pool in the south of Songli-ao Basin[J].Acta Petrolei Sinica,2004,23(3):32-36.
[12]张超英,周小鹰,董宁.测井约束的地震反演在鄂尔多斯盆地大牛地气田中的应用[J].地球物理学进展,2004,19(4):909-917.Zhang Chaoying,Zhou Xiaoying,Dong Ning.Seismic inversionconstrained by wells in the Daniu gas-field in Eerduosi Basin[J].Progress in Geophysics,2004,19(4):909-917.
[2]Liu Zhengping,Liu Jiaqi.Seismic-controlled nonlinear extrapola-tion of well parameters using neural networks[J].Geophysics,1998,63(6):2035-2041.
[3]de Groot P F M,Bril A H,Floris F J T,et al.Monte Carlo simu-lation of wells[J].Geophysics,1996,61(3):631-638.
[4]Sen W K,Stoffa P L.Nonlinear one-dimensional seismic wave-form inversion using simulated annealing[J].Geophysics,1991,56(10):1624-1638.
[5]McCormack M D.Neural computing in geophysics[J].The Lead-ing Edge,1991,10(1):11-15.
[6]Masters T.Signal and image processing with neural networks[M].New York:John Wiley&Sons Incorporation,1994:1-200.
[7]Specht D F.A general regression neural network[J].IEEETransaction on Neural Networks,1991,2(6):568-576.
[8]徐旺林,庞雄奇,吕淑英,等.动态概率神经网络及油气概率分布预测[J].石油地球物理勘探,2005,40(1):65-70.Xu Wanglin,Pang Xiongqi,LüShuying,et al.Dynamic probabi-listic neural network and predicting probabilistic distribution ofoil/gas[J].Oil Geophysics Prospecting,2005,40(1):65-70.
[9]杨长保,聂兰仕,孙鹏远.改进的模糊神经网络模型在储层产能预测中的应用研究[J].吉林大学学报:地球科学版,2003,33(1):48-50.Yang Changbao,Nie Lanshi,Sun Pengyuan.A study of using im-proved fuzzy neural network to forecast reservoir productivity[J].Journal of Jilin University:Earth Science Edition,2003,33(1):48-50.
[10]赵力民,邹伟宏,郎晓玲,等.利用RM反演方法进行地层岩性油藏研究[J].石油学报,2000,21(2):62-65.Zhao Limin,Zou Weihong,Lang Xiaoling,et al.Lithologic oilreservoir research by means of RM inversion method[J].ActaPetrolei Sinica,2000,21(2):62-65.
[11]邹才能,李明,赵文智,等.松辽南部构造—岩性油气藏识别技术及应用[J].石油学报,2004,23(3):32-36.Zou Caineng,Li Ming,Zhao Wenzhi,et al.Recognition techniqueand application of structure-lithology pool in the south of Songli-ao Basin[J].Acta Petrolei Sinica,2004,23(3):32-36.
[12]张超英,周小鹰,董宁.测井约束的地震反演在鄂尔多斯盆地大牛地气田中的应用[J].地球物理学进展,2004,19(4):909-917.Zhang Chaoying,Zhou Xiaoying,Dong Ning.Seismic inversionconstrained by wells in the Daniu gas-field in Eerduosi Basin[J].Progress in Geophysics,2004,19(4):909-917.
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