基于模糊神经网络的致密砂岩储层反演——以长岭断陷1号气田登娄库组为例
摘要
模糊神经网络储层反演,能够较好地摈弃不同类型、不同尺度数据的揉合,较好地保留了数据完整性,这既能反映整体的变化趋势,又能刻画局部细致变化特征。针对长岭1号气田登娄库组相变快、砂体横向连续性较差的特点,综合地震、测井、钻井测试分析资料,应用模糊神经网络原理,反演了研究区目的层段砂岩厚度与孔隙度特征。研究结果显示:①长岭1号气田登娄库组各段砂体平面展布变化较大,但厚度较大的区域均集中于长深103—长深1-3—长深1-1井和长深2井附近,向东北呈逐渐减薄趋势,D3岩层段长深103井周围岩石厚度可达33.2 m;②研究区登娄库组主力产油层D3和D4岩层段孔隙度较低,平均仅为5%左右,砂体孔隙度相对较高区域(>9%)仅集中于长深1井附近,整体显示登娄库组岩性较为致密;③反演结果与实际测试数据对比显示,砂体厚度误差控制在2.5 m以内,砂体孔隙度误差在0.49%以下,结果可靠性较好。利用模糊神经网络原理进行储层反演分析,能够很好地展现储集砂体分布规律及储集性能。
Fuzzy neural network reservoir inversion can avoid the integration of data of different types and scales and well preserve the data integrity,making it possible to reveal both the overall variation tendency and the local detailed features.In view of the rapid facies change and poor lateral continuity of the Denglouku Formation sandstone in the Changling1 gas field,we integrated various data including seismic,well logging,drilling and well testing and performed inversion of the sandstone thickness and porosity characters by using the fuzzy neural network theory.The following results were obtained.①The areal distributions of the Denglouku Formation sandstones in the Changling1 gas field varies greatly,with the thicker sandtone occurring mainly in areas along the Changshen 103,Changshen 1-3,Changshen 1-1 wells and the Changshen 2 well.The thickness of sandstone decreases progressively in northeast direction.The thickness of D3 layer near in the Changshen 103 well is up to 33.2m.②The major D3 and D4 pay zones in the Denglouku Formation have a relatively low porosity,averaging at only about 5%.The sandbodies with relatively high porosity(> 9%) only occur in area around the Changshen 1 well.The Denglouku Formation is tight as a whole.③Comparison of the inversion results with the actual test data shows that the error of sandstone thickness is within 2.5 m and the error of the porosity is under 0.49%,indicating a high reliability of the inversion results.It is concluded that fuzzy neural network-based inversion of tight sandstone reservoirs can well reveal sandstone distribution and reservoir properties.
Fuzzy neural network reservoir inversion can avoid the integration of data of different types and scales and well preserve the data integrity,making it possible to reveal both the overall variation tendency and the local detailed features.In view of the rapid facies change and poor lateral continuity of the Denglouku Formation sandstone in the Changling1 gas field,we integrated various data including seismic,well logging,drilling and well testing and performed inversion of the sandstone thickness and porosity characters by using the fuzzy neural network theory.The following results were obtained.①The areal distributions of the Denglouku Formation sandstones in the Changling1 gas field varies greatly,with the thicker sandtone occurring mainly in areas along the Changshen 103,Changshen 1-3,Changshen 1-1 wells and the Changshen 2 well.The thickness of sandstone decreases progressively in northeast direction.The thickness of D3 layer near in the Changshen 103 well is up to 33.2m.②The major D3 and D4 pay zones in the Denglouku Formation have a relatively low porosity,averaging at only about 5%.The sandbodies with relatively high porosity(> 9%) only occur in area around the Changshen 1 well.The Denglouku Formation is tight as a whole.③Comparison of the inversion results with the actual test data shows that the error of sandstone thickness is within 2.5 m and the error of the porosity is under 0.49%,indicating a high reliability of the inversion results.It is concluded that fuzzy neural network-based inversion of tight sandstone reservoirs can well reveal sandstone distribution and reservoir properties.
引文
[1]杨立强.测井约束地震反演综述[J].地球物理学进展,2003,18(3):530-534.Yang Liqiang.A review of well log constrained seismic inversion[J],Progress in Geophysics,2003,18(3):530-534.
[2]Wyllie M R J,Gregory A R,Gardner G H F.An experimental investi-gation of factors affecting elastic wave velocities in porousmedia[J].Geophysics,1958,23:459-493.
[3]Nur A,Mavko G,Dvorkin J,et al.Critical porosity:a key to relatingphysical properties to porosity in rocks[J].The Leading Edge,1998,17:357-362.
[4]马劲风,王学军,钟俊,等.测井资料约束的波阻抗反演中的多解性问题[J].石油与天然气地质,1999,20(1):7-10.Ma Jinfeng,Wang Xuejun,Zhong Jun,et al.Multiple roots in well-re-stricted impedance inversion[J].Oil&Gas Geology,1999,20(1):7-10.
[5]刘振峰,董宁,张永贵,等.致密碎屑岩储层地震反演技术方案及应用[J].石油地球物理勘探,2012,47(2):298-304.Liu Zhenfeng,Dong Ning,Zhang Yonggui,et al.Seismic inversionprogram for tight clastic reservoir and its application[J].Oil Geo-physical Prospecting,2012,47(2):298-304.
[6]Pejman Tahmasebi,Ardeshir Hezarkhani.A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation[J].Computers&Geosciences,2012,42:18-27.
[7]Jang J S R,Sun C T,Mizutani E.Neuro-fuzzy and soft computing:acomputational approach to learning and machine intelligent[M].Prentice-Hall International,1997:614.
[8]Kim J,Kasabov N.HyFIS:adaptive neuro-fuzzy inference systems andtheir application to nonlinear dynamical systems[J].Journal of Neu-ral Network,1999,12:1301-1319.
[9]黄捍东,张如伟,赵迪,等.地震反演与属性耦合检测薄层含气砂岩[J].石油地球物理勘探,2009,44(2):185-189.Huang Handong,Zhang Ruwei,Zhao Di,et al.Seismic inversion anddetection of thin-layer gas bearing sandstone by attributes coupling[J].Oil Geophysical Prospecting,2009,44(2):185-189.
[10]艾宁,张春生,唐永,等.长岭1号气田登娄库组储层成岩作用及储集空间类型[J].新疆石油地质,2008,4(2):34-37.Ai Ning,Zhang Chunsheng,Tang Yong,et al.Research on diagenesisand reservoir characteristic of Denglouku formation in Changling firstgas field[J].Xinjiang Oil&Gas,2008,4(2):34-37.
[11]李君,黄志龙,刘宝柱,等.伸展构造与反转构造对油气分布的控制作用——以松辽盆地东南隆起区为例[J].新疆石油地质,2008,29(1):19-21.Li Jun,Huang Zhilong,Liu Baozhu,et al.Control effects of spreadingstructure and reversal structure on hydrocarbon distribution—an ex-ample from Dongnan uplift in Songliao basin[J].Xinjiang Oil&Gas,2008,29(1):19-21.
[12]马杏垣,刘和甫,王维襄,等.中国东部中、新生代裂陷作用和伸展构造[J].地质学报,1983,1:22-32.Ma Xingyuan,Liu Hefu,Wang Weixiang,et al.Meso-Cenozoictaphrogeny and extensional tectonics in eastern China[J].Acta Geo-logica Sinica,1983,1:22-32.
[13]王键,贾爱林,魏铁军,等.长岭气田登娄库组低渗砂岩储层控制因素分析[J].天然气地球科学,2011,22(5):827-833.Wang Jian,Jia Ailin,Wei Tiejun,et al.Controlling factors of low per-meability sandstone reservoirs in Denglouku formation of Changlinggas field[J].Natural Gas Geoscience,2011,22(5):827-832.
[14]孙学凯,冯世民.地震反演系统中的子波提取方法[J].物探化探计算技术,2010,32(2):120-125.Sun Xuekai,Feng Shimin.Wavelet extraction methods in seismic in-version system[J].Computing Techniques for Geophysical and Geo-chemical Exploration,2010,32(2):120-125.
[15]葛岩,黄志龙,宋立忠,等.松辽盆地南部长岭断陷登娄库组致密砂岩有利储层控制因素[J].中南大学学报(自然科学版),2012,43(7):2691-2699.Ge Yan,Huang Zhilong,Song Lizhong,et al.Controlling factors onhigh quality reservoir of tighe sandstone of Denglouku formation inChangling fault sag,southern part of Songliao basin[J].Journal ofCentral South University(Science and Technology Edition)2012,43(7):2691-2699.
[2]Wyllie M R J,Gregory A R,Gardner G H F.An experimental investi-gation of factors affecting elastic wave velocities in porousmedia[J].Geophysics,1958,23:459-493.
[3]Nur A,Mavko G,Dvorkin J,et al.Critical porosity:a key to relatingphysical properties to porosity in rocks[J].The Leading Edge,1998,17:357-362.
[4]马劲风,王学军,钟俊,等.测井资料约束的波阻抗反演中的多解性问题[J].石油与天然气地质,1999,20(1):7-10.Ma Jinfeng,Wang Xuejun,Zhong Jun,et al.Multiple roots in well-re-stricted impedance inversion[J].Oil&Gas Geology,1999,20(1):7-10.
[5]刘振峰,董宁,张永贵,等.致密碎屑岩储层地震反演技术方案及应用[J].石油地球物理勘探,2012,47(2):298-304.Liu Zhenfeng,Dong Ning,Zhang Yonggui,et al.Seismic inversionprogram for tight clastic reservoir and its application[J].Oil Geo-physical Prospecting,2012,47(2):298-304.
[6]Pejman Tahmasebi,Ardeshir Hezarkhani.A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation[J].Computers&Geosciences,2012,42:18-27.
[7]Jang J S R,Sun C T,Mizutani E.Neuro-fuzzy and soft computing:acomputational approach to learning and machine intelligent[M].Prentice-Hall International,1997:614.
[8]Kim J,Kasabov N.HyFIS:adaptive neuro-fuzzy inference systems andtheir application to nonlinear dynamical systems[J].Journal of Neu-ral Network,1999,12:1301-1319.
[9]黄捍东,张如伟,赵迪,等.地震反演与属性耦合检测薄层含气砂岩[J].石油地球物理勘探,2009,44(2):185-189.Huang Handong,Zhang Ruwei,Zhao Di,et al.Seismic inversion anddetection of thin-layer gas bearing sandstone by attributes coupling[J].Oil Geophysical Prospecting,2009,44(2):185-189.
[10]艾宁,张春生,唐永,等.长岭1号气田登娄库组储层成岩作用及储集空间类型[J].新疆石油地质,2008,4(2):34-37.Ai Ning,Zhang Chunsheng,Tang Yong,et al.Research on diagenesisand reservoir characteristic of Denglouku formation in Changling firstgas field[J].Xinjiang Oil&Gas,2008,4(2):34-37.
[11]李君,黄志龙,刘宝柱,等.伸展构造与反转构造对油气分布的控制作用——以松辽盆地东南隆起区为例[J].新疆石油地质,2008,29(1):19-21.Li Jun,Huang Zhilong,Liu Baozhu,et al.Control effects of spreadingstructure and reversal structure on hydrocarbon distribution—an ex-ample from Dongnan uplift in Songliao basin[J].Xinjiang Oil&Gas,2008,29(1):19-21.
[12]马杏垣,刘和甫,王维襄,等.中国东部中、新生代裂陷作用和伸展构造[J].地质学报,1983,1:22-32.Ma Xingyuan,Liu Hefu,Wang Weixiang,et al.Meso-Cenozoictaphrogeny and extensional tectonics in eastern China[J].Acta Geo-logica Sinica,1983,1:22-32.
[13]王键,贾爱林,魏铁军,等.长岭气田登娄库组低渗砂岩储层控制因素分析[J].天然气地球科学,2011,22(5):827-833.Wang Jian,Jia Ailin,Wei Tiejun,et al.Controlling factors of low per-meability sandstone reservoirs in Denglouku formation of Changlinggas field[J].Natural Gas Geoscience,2011,22(5):827-832.
[14]孙学凯,冯世民.地震反演系统中的子波提取方法[J].物探化探计算技术,2010,32(2):120-125.Sun Xuekai,Feng Shimin.Wavelet extraction methods in seismic in-version system[J].Computing Techniques for Geophysical and Geo-chemical Exploration,2010,32(2):120-125.
[15]葛岩,黄志龙,宋立忠,等.松辽盆地南部长岭断陷登娄库组致密砂岩有利储层控制因素[J].中南大学学报(自然科学版),2012,43(7):2691-2699.Ge Yan,Huang Zhilong,Song Lizhong,et al.Controlling factors onhigh quality reservoir of tighe sandstone of Denglouku formation inChangling fault sag,southern part of Songliao basin[J].Journal ofCentral South University(Science and Technology Edition)2012,43(7):2691-2699.
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