基于粒子群优化的BP网络在地震属性融合技术中的应用
|
摘要
受地震资料品质、岩性、构造等诸多因素的影响,单一地震属性只能在一定程度上提供预测储层的方向,并存在多解性。地震属性融合技术用井孔资料对地震属性进行标定,建立储层含油气性与地震属性之间的关系,采取数学手段融合多种地震属性进行储层含油气性判别,避免了单一地震属性解释储层的多解性问题。BP网络具有良好的非线性拟合能力,但是易陷入局部极小值,不收敛,影响预测精度。针对该问题,采用粒子群优化其网络权值和阈值,再用BP网络对储层、非储层进行模式识别,取得较好成效。
Constrained by factors such as quality of seismic data,lithology and structures,single seismic attribute can only be used to predict reservoirs to a certain extent and there are multiple possibilities.Through calibrating seismic attributes with well data,seismic attribute fusion techniques can correlate oil/gas potential with seismic attributes.For oil/gas potential prediction of reservoirs,mathematics-based multi-attribute fusion can avoid the ambiguity of single-attribute reservoir interpretation.Back propagation(BP)neural network is very good at non-linear fitting,but it is easy to get a local minimum without convergence,influencing the accuracy of prediction.To solve this problem,particle swarm is adopted first to optimize the network weight and threshold,and BP neural network is then used to differentiate reservoirs and non-reservoirs.The results are satisfactory.
Constrained by factors such as quality of seismic data,lithology and structures,single seismic attribute can only be used to predict reservoirs to a certain extent and there are multiple possibilities.Through calibrating seismic attributes with well data,seismic attribute fusion techniques can correlate oil/gas potential with seismic attributes.For oil/gas potential prediction of reservoirs,mathematics-based multi-attribute fusion can avoid the ambiguity of single-attribute reservoir interpretation.Back propagation(BP)neural network is very good at non-linear fitting,but it is easy to get a local minimum without convergence,influencing the accuracy of prediction.To solve this problem,particle swarm is adopted first to optimize the network weight and threshold,and BP neural network is then used to differentiate reservoirs and non-reservoirs.The results are satisfactory.
引文
1曹辉.关于地震属性应用的几点认识[J].勘探地球物理进展,2002,25(5):18～22
2杜世通.地震属性分析[J].油气地球物理,2004,2(4):19～31
3侯伯刚,杨池银,武站国,等.地震属性及其在储层预测中的影响因素[J].石油地球物理勘探,2004,39(5):553～558
4唐建明,杨军,张哨楠.川西坳陷中、浅层气藏储层识别技术[J].石油与天然气地质,2006,27(6):879～893
5石万忠,陈开远,陈新军,等.地震属性参数在胜坨油田气藏预测中的应用[J].石油与天然气地质,2003,24(2):196～198
6孙万军.多种地震属性参数在储层横向预测中的应用[J].石油地球物理勘探,2004,39(5):586～588
7陈波,胡少华,毕建军.地震属性模式聚类预测储层物性参数[J].石油地球物理勘探,2005,40(2):204～208
8赵虎,尹成,朱仕军.多属性融合技术研究[J].勘探地球物理进展,2009,32(2):119～121
9王永刚,曹丹平,朱兆林.神经网络方法烃类预测中的问题探讨[J].石油物探,2004,43(1):94～98
10崔吉峰,乞建勋,杨尚东.基于粒子群改进BP神经网络的组合预测模型及其应用[J].中南大学学报(自然科学版),2009,40(1):190～194
11毕研斌,龙胜祥,郭彤楼,等.应用频率衰减属性预测TNB地区储层含气性[J].石油与天然气地质,2007,28(1):116～121
12Partyka G,Gridley J,Lopez J.Interpretational application of spec-tral decomposition in reservoir characterization[J].The Leading Edge,1999,18(3):353-360
13瞿子易,周文,罗鑫,等.基于粒子群和支持向量机的裂缝识别[J].石油与天然气地质,2009,30(6)350～356
2杜世通.地震属性分析[J].油气地球物理,2004,2(4):19～31
3侯伯刚,杨池银,武站国,等.地震属性及其在储层预测中的影响因素[J].石油地球物理勘探,2004,39(5):553～558
4唐建明,杨军,张哨楠.川西坳陷中、浅层气藏储层识别技术[J].石油与天然气地质,2006,27(6):879～893
5石万忠,陈开远,陈新军,等.地震属性参数在胜坨油田气藏预测中的应用[J].石油与天然气地质,2003,24(2):196～198
6孙万军.多种地震属性参数在储层横向预测中的应用[J].石油地球物理勘探,2004,39(5):586～588
7陈波,胡少华,毕建军.地震属性模式聚类预测储层物性参数[J].石油地球物理勘探,2005,40(2):204～208
8赵虎,尹成,朱仕军.多属性融合技术研究[J].勘探地球物理进展,2009,32(2):119～121
9王永刚,曹丹平,朱兆林.神经网络方法烃类预测中的问题探讨[J].石油物探,2004,43(1):94～98
10崔吉峰,乞建勋,杨尚东.基于粒子群改进BP神经网络的组合预测模型及其应用[J].中南大学学报(自然科学版),2009,40(1):190～194
11毕研斌,龙胜祥,郭彤楼,等.应用频率衰减属性预测TNB地区储层含气性[J].石油与天然气地质,2007,28(1):116～121
12Partyka G,Gridley J,Lopez J.Interpretational application of spec-tral decomposition in reservoir characterization[J].The Leading Edge,1999,18(3):353-360
13瞿子易,周文,罗鑫,等.基于粒子群和支持向量机的裂缝识别[J].石油与天然气地质,2009,30(6)350～356
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