用改进的BP神经网络由地震属性预测测井特性
|
摘要
由地震数据预测测井特性能实现测井曲线的横向外推。分析的数据由一系列与某个地震数据体相连的井的目标测井曲线组成,它利用地震数据体计算一系列基于样点的属性,导出属性的某个子集与目标测井值之间的线性或非线性变换,利用建立的统计关系,由地震属性来预测测井信息。与传统反演方法相比,该方法应用更方便并可以很大地提高分辨率。介绍了一种用改进的多层前馈神经网络由地震属性进行测井特性预测的方法,并应用理论模型和实测数据对该方法进行了验证,结果令人满意。
Predicting log properties from Seismic attributes can extrapolate log cruves in landscape orientation.It establishes linear or non-linear mapping relation between a subset of sample-based seismic attributes and target log curve to predict log properties.This prediction method of easier than traditional inversion method in application and improves resolution greatly.The paper introduced a method of prediction log properties with seismic attributes by optimized BP neural net works,and it had been used to compute a theory model and a real seismic date.The results were good.
Predicting log properties from Seismic attributes can extrapolate log cruves in landscape orientation.It establishes linear or non-linear mapping relation between a subset of sample-based seismic attributes and target log curve to predict log properties.This prediction method of easier than traditional inversion method in application and improves resolution greatly.The paper introduced a method of prediction log properties with seismic attributes by optimized BP neural net works,and it had been used to compute a theory model and a real seismic date.The results were good.
引文
[1]Taner M T,Schuelke J S,O’Doherty R,et al.SeismicAttributes Revisited[C]//64thAnn Intenat Mtg.Soc ExplGeophys,Expanded Abstracts,1994(1):10-1106.
[2]Liu,Z.,and Liu,J.Seismic-controlled nonlinear extrapo-lation of well parameters using neural networks[J].Geo-physics,1998,63:2035-2041.
[3]Masters T.Signal and I mage Processing with Neural Net-work[M].London:John Wiley&Sons,1994:191-210.
[4]Masters T.Advanced Algorithms for Neural Net works[M].London:John Wiley&Sons,1995:111-123.
[5]Daniel P.Hampson.Use of multiattribute transforms topredict log properties from seismic data[J].Geophysics,2001,6(1):220-236.
[6]卢宝坤,等,测井资料与地震属性关系研究综述[J].北京大学学报:自然科学版,2005,41(1):154-160.
[7]Joao B C S,Walter E M,Valeria C F B.Potential fieldin-ver-sion:choosing the appropriate technique to slove a geo-logic problem[J].Geophysics,2001,66(2):511-520.
[8]Leiphart D J,Hart B S.Comparison of linear regressionand aprobabilistic neural net work to predict porosityfrom3-Dseismic attributes in Lower Brushy Canyon chan-neled sandstones,southeast New Mexico[J].Geophysics,2001,66:1349-1358.
[9]Adel Malallah,Ibrahi m Sami Nashawi.Esti mating thefracture gradient coefficient using neural net works for afield in the Middle East[J].Journal of Petroleum Scienceand Engineering,2005,49:193-211.
[10]Schultz,P.S.,Ronen,S.,Hattori,M.Corbett,C.Seismic guided esti mation of log properties[J].The leadingEdge,1997,13:305-310,674-678,770-776.
[11]林自强.地震信息应用的新途径[J].石油地球物理勘探,1996(增刊1):49-58.
[12]李正文,李琼.油气储集层裂缝非线性预测技术及应用研究[J].石油地球物理勘探,2003,38(1):48-52.
[13]吕晓光,等.应用人工神经网络模型进行孔隙度、渗透率预测[J].大庆石油地质与开发,1996,15(3):27-31.
[14]金仁杰.神经网络动量-自适应学习率BP算法与BP算法的性能比较及其应用[J].微型电脑应用,2001,17(7):30-32.
[15]陈敏,刘君.BP网络的改进及其应用[J].湖南文理学院学报:自然科学版,2005,17(2).
[2]Liu,Z.,and Liu,J.Seismic-controlled nonlinear extrapo-lation of well parameters using neural networks[J].Geo-physics,1998,63:2035-2041.
[3]Masters T.Signal and I mage Processing with Neural Net-work[M].London:John Wiley&Sons,1994:191-210.
[4]Masters T.Advanced Algorithms for Neural Net works[M].London:John Wiley&Sons,1995:111-123.
[5]Daniel P.Hampson.Use of multiattribute transforms topredict log properties from seismic data[J].Geophysics,2001,6(1):220-236.
[6]卢宝坤,等,测井资料与地震属性关系研究综述[J].北京大学学报:自然科学版,2005,41(1):154-160.
[7]Joao B C S,Walter E M,Valeria C F B.Potential fieldin-ver-sion:choosing the appropriate technique to slove a geo-logic problem[J].Geophysics,2001,66(2):511-520.
[8]Leiphart D J,Hart B S.Comparison of linear regressionand aprobabilistic neural net work to predict porosityfrom3-Dseismic attributes in Lower Brushy Canyon chan-neled sandstones,southeast New Mexico[J].Geophysics,2001,66:1349-1358.
[9]Adel Malallah,Ibrahi m Sami Nashawi.Esti mating thefracture gradient coefficient using neural net works for afield in the Middle East[J].Journal of Petroleum Scienceand Engineering,2005,49:193-211.
[10]Schultz,P.S.,Ronen,S.,Hattori,M.Corbett,C.Seismic guided esti mation of log properties[J].The leadingEdge,1997,13:305-310,674-678,770-776.
[11]林自强.地震信息应用的新途径[J].石油地球物理勘探,1996(增刊1):49-58.
[12]李正文,李琼.油气储集层裂缝非线性预测技术及应用研究[J].石油地球物理勘探,2003,38(1):48-52.
[13]吕晓光,等.应用人工神经网络模型进行孔隙度、渗透率预测[J].大庆石油地质与开发,1996,15(3):27-31.
[14]金仁杰.神经网络动量-自适应学习率BP算法与BP算法的性能比较及其应用[J].微型电脑应用,2001,17(7):30-32.
[15]陈敏,刘君.BP网络的改进及其应用[J].湖南文理学院学报:自然科学版,2005,17(2).
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