一种模糊神经网络技术及其在储层预测中的应用
|
摘要
大庆外围油田的葡萄花油层主要为砂泥岩薄互层,储层砂体横向变化大,这给井位设计带来了很大的难度。近几年地震属性分析技术虽然得到了较快的发展,但地震属性与储层地质参数之间的关系较模糊,难以用地震特征参数直接预测储层的砂岩厚度。为此,研究了一种模糊神经网络预测砂岩技术,它将人工神经网络理论与模糊逻辑分析相结合,在地震属性分析的基础上,以井旁地震道主分量参数为输入,以井孔地质参数为期望输出,建立模糊神经网络,并对网络进行训练,当网络收敛且网络整体方差达到要求的精度时,便完成了网络训练。该技术应用于大庆太平屯地区储层预测中,通过4口后验井检验,预测厚度与钻井厚度吻合较好,平均绝对误差为0.21m。
It is hard to estimate the sandstone thickness in reservoir intervals because there is lack of direct relationship between seismic attributes and reservoir parameters. This paper presents a fuzzy neural network technique for sandstone prediction. The technique combines artificial neural network theory with fuzzy logic analysis. Based on seismic attribute analysis, a fuzzy neural network was established which used the principal components of traces nearby wells as input and wellbore geologic parameters as output. The network was then be trained until it converged such that its overall variance was less than the predefined precision. This technique has been applied in the reservoir prediction in Taipingtun region of Daqing. Verifications in four wells showed that the average absolute thickness error is 0. 21 m.
It is hard to estimate the sandstone thickness in reservoir intervals because there is lack of direct relationship between seismic attributes and reservoir parameters. This paper presents a fuzzy neural network technique for sandstone prediction. The technique combines artificial neural network theory with fuzzy logic analysis. Based on seismic attribute analysis, a fuzzy neural network was established which used the principal components of traces nearby wells as input and wellbore geologic parameters as output. The network was then be trained until it converged such that its overall variance was less than the predefined precision. This technique has been applied in the reservoir prediction in Taipingtun region of Daqing. Verifications in four wells showed that the average absolute thickness error is 0. 21 m.
引文
1 焦李成.神经网络的应用与实现[M].陕西西安:西安电子科技大学出版社,1995． 218-259
2 张学庆,刘燕,肖慈珣,等.在测井中用一种组合优化神经网络识别油水层[J].石油物探,2001,40(4) :119-124
3 宋维琪,韩宏伟.2D地震小波变换和自组织神经网络联合边界检测[J].石油物探,2003,42(4) :473-476
4 靳蕃,范俊波,谭永东.神经网络与神经计算机[M].四川成都:西南交通大学出版社,1991． 55-267
5 杨德义,王赟,王妙月,等.一种改进的多层感知器神经网络技术[J].石油物探,2000,39(2) :107-116
6 王大力,陈云英.前馈神经网络用于压裂效果预测[J].石油物探,2000,39(3) :121-126
7 焦李成.神经网络系统理论[M].陕西西安:西安电子科技大学出版社,1990． 80-350
8 赵振宇.模糊理论和神经网络的基础与应用[M].北京:清华大学出版社,1996． 46-188
9 胡守仁.神经网络应用技术[M].湖南长沙:国防科技大学出版社,1993． 156-310
10 王士同.模糊推理理论与模糊专家系统[M].上海:上海科学技术文献出版社,1995． 270-390
11 刘文岭,牛彦良,李刚,等.多信息储层预测地震属性提取与有效性分析方法[J].石油物探,2002,41(41) :100-106
12 刘其,赵永勤,窦慧媛,等.利用地震波主参数预测岩性和油气[J].石油物探,2003,42(1) :77-81
13 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
14 陈念贻.模式识别优化技术及其应用[M].北京:中国石化出版社,1997． 55-186
2 张学庆,刘燕,肖慈珣,等.在测井中用一种组合优化神经网络识别油水层[J].石油物探,2001,40(4) :119-124
3 宋维琪,韩宏伟.2D地震小波变换和自组织神经网络联合边界检测[J].石油物探,2003,42(4) :473-476
4 靳蕃,范俊波,谭永东.神经网络与神经计算机[M].四川成都:西南交通大学出版社,1991． 55-267
5 杨德义,王赟,王妙月,等.一种改进的多层感知器神经网络技术[J].石油物探,2000,39(2) :107-116
6 王大力,陈云英.前馈神经网络用于压裂效果预测[J].石油物探,2000,39(3) :121-126
7 焦李成.神经网络系统理论[M].陕西西安:西安电子科技大学出版社,1990． 80-350
8 赵振宇.模糊理论和神经网络的基础与应用[M].北京:清华大学出版社,1996． 46-188
9 胡守仁.神经网络应用技术[M].湖南长沙:国防科技大学出版社,1993． 156-310
10 王士同.模糊推理理论与模糊专家系统[M].上海:上海科学技术文献出版社,1995． 270-390
11 刘文岭,牛彦良,李刚,等.多信息储层预测地震属性提取与有效性分析方法[J].石油物探,2002,41(41) :100-106
12 刘其,赵永勤,窦慧媛,等.利用地震波主参数预测岩性和油气[J].石油物探,2003,42(1) :77-81
13 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
14 陈念贻.模式识别优化技术及其应用[M].北京:中国石化出版社,1997． 55-186
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