基于三维地震的地震相分析技术研究
|
摘要
随着油气勘探开发对象复杂程度的增加和地震解释技术的日趋成熟,地震油气预测技术正朝着精细和实用的方向发展。为了提高油气预测的准确率,地震相的划分是尤为重要的一步,地震相划分的准确性将直接影响油气勘探结果的可靠性。
本文研究了地震属性提取及地震属性优选,从三维地震资料中提取出分析地震相的属性特征,针对这些复杂的地震属性特征进行优选,选出有用的属性特征信息。
为解决三维地震数据中输入变量过多的问题,文中使用了主成分分析法。它将原来较大的输入变量组利用线性变换后,得到一组个数较少彼此不相关的输入变量,并且所得到的一组输入变量包含原输入变量群的大部分信息,然后再用这些个数较少的新输入变量作为BP神经网络和SOFM神经网络的数据输入部分。
划分地震相的方法是本文研究的重点,本文着重研究了利用波形分析与BP神经网络划分地震相的方法和SOFM神经网络划分地震相的方法,并对BP神经网络算法和SOFM神经网络算法进行了改进。通过地震数据的实验,证明了应用本文提出的BP神经网络改进算法和SOFM神经网络改进算法划分地震相,不但分类的速度快而且预测的精度高。文中给出了这两种算法的详细步骤,并分别用实验说明了这两种算法的训练和预测过程。
以地震属性特征提取和两种神经网络划分地震相方法为理论基础,以VC++ 6.0、MatLab以及OpenGL为开发工具开发出一套适合于三维地震解释要求的基于三维地震的地震相分析系统,实现了地震相的二维和三维显示。在开发本系统过程中以面向对象技术作为指导,把系统分为若干模块,实现了各模块的功能并给出了模拟结果,并对文中不足之处进行了分析,对未来的工作提出了要求。
Along with object complex degree of oil-gas exploratory development increasing and seismic interpretation technology being more and more mature day by day, seismic oil-gas forecasting technology develops toward fine and the practical direction. In order to enhance the rate of accuracy of the oil-gas forecasting, division of the seismic facies is especially one important step, accuracy of division of the seismic facies influences the reliability of result of oil-gas exploration.
This thesis has study the seismic attribute extraction and seismic attribute optimization, seismic attribute property is withdrawn from the three dimensional seismic data, attribute optimization is carried on view of these complex seismic attribute property, the useful attribute property information is selected.
In order to solve the question of many excessive input variables in three dimensional seismic data,the principal component analysis method is used in this thesis.After the principal component analysis method transforms the originally bigger group of input variables by using linear transformation,it can obtain a group of new irrelvant input variables,which include majority of information of the original group of input variables. Then these few new input variables are used as the data input of the BP neural network and the SOFM neural network.
The method of division of seismic facies is the key point in this thesis.This thesis has studied emphatically the method of BP neural network algorithm using the waveform analysis which divides the seismic facies and the method of SOFM neural network algorithm which divides the seismic facies, And some improvements to the BP neural network algorithm using the waveform analysis and the SOFM network algorithm are made. The experiment of seismic data has proven that the improving algorithm of BP and the improving algorithm of SOFM which divide seismic facies in this thesis, which not only has a faster speed of classification ,but also has a higher precision of prediction.The detailed steps of two algorithms are given in this thesis,the two algorithms` processes of training and forcasting are explained by two experiments separately.
The extraction of seismic attribute property and two methods of neural network which divide seismic facies are taken as the base of theory, VC++ 6.0, MatLab as well as OpenGL are taken as the development kit,then a suit of system of analysis of seismic facies based on three-dimensional seismism has been achieved,which conforms to the conventionality of 3D seismic data interpretation,it realizes the display of two-dimensional seismic facies and two-dimensional seismic facies.The system is divided into several modules by using object-oriented programming technology as a guide during the process of development.The function of every module are implemented, and imitative results are presented. What is more, shortcomings of the thesis are analyzed, and some requests are put forward in the future.
本文研究了地震属性提取及地震属性优选,从三维地震资料中提取出分析地震相的属性特征,针对这些复杂的地震属性特征进行优选,选出有用的属性特征信息。
为解决三维地震数据中输入变量过多的问题,文中使用了主成分分析法。它将原来较大的输入变量组利用线性变换后,得到一组个数较少彼此不相关的输入变量,并且所得到的一组输入变量包含原输入变量群的大部分信息,然后再用这些个数较少的新输入变量作为BP神经网络和SOFM神经网络的数据输入部分。
划分地震相的方法是本文研究的重点,本文着重研究了利用波形分析与BP神经网络划分地震相的方法和SOFM神经网络划分地震相的方法,并对BP神经网络算法和SOFM神经网络算法进行了改进。通过地震数据的实验,证明了应用本文提出的BP神经网络改进算法和SOFM神经网络改进算法划分地震相,不但分类的速度快而且预测的精度高。文中给出了这两种算法的详细步骤,并分别用实验说明了这两种算法的训练和预测过程。
以地震属性特征提取和两种神经网络划分地震相方法为理论基础,以VC++ 6.0、MatLab以及OpenGL为开发工具开发出一套适合于三维地震解释要求的基于三维地震的地震相分析系统,实现了地震相的二维和三维显示。在开发本系统过程中以面向对象技术作为指导,把系统分为若干模块,实现了各模块的功能并给出了模拟结果,并对文中不足之处进行了分析,对未来的工作提出了要求。
Along with object complex degree of oil-gas exploratory development increasing and seismic interpretation technology being more and more mature day by day, seismic oil-gas forecasting technology develops toward fine and the practical direction. In order to enhance the rate of accuracy of the oil-gas forecasting, division of the seismic facies is especially one important step, accuracy of division of the seismic facies influences the reliability of result of oil-gas exploration.
This thesis has study the seismic attribute extraction and seismic attribute optimization, seismic attribute property is withdrawn from the three dimensional seismic data, attribute optimization is carried on view of these complex seismic attribute property, the useful attribute property information is selected.
In order to solve the question of many excessive input variables in three dimensional seismic data,the principal component analysis method is used in this thesis.After the principal component analysis method transforms the originally bigger group of input variables by using linear transformation,it can obtain a group of new irrelvant input variables,which include majority of information of the original group of input variables. Then these few new input variables are used as the data input of the BP neural network and the SOFM neural network.
The method of division of seismic facies is the key point in this thesis.This thesis has studied emphatically the method of BP neural network algorithm using the waveform analysis which divides the seismic facies and the method of SOFM neural network algorithm which divides the seismic facies, And some improvements to the BP neural network algorithm using the waveform analysis and the SOFM network algorithm are made. The experiment of seismic data has proven that the improving algorithm of BP and the improving algorithm of SOFM which divide seismic facies in this thesis, which not only has a faster speed of classification ,but also has a higher precision of prediction.The detailed steps of two algorithms are given in this thesis,the two algorithms` processes of training and forcasting are explained by two experiments separately.
The extraction of seismic attribute property and two methods of neural network which divide seismic facies are taken as the base of theory, VC++ 6.0, MatLab as well as OpenGL are taken as the development kit,then a suit of system of analysis of seismic facies based on three-dimensional seismism has been achieved,which conforms to the conventionality of 3D seismic data interpretation,it realizes the display of two-dimensional seismic facies and two-dimensional seismic facies.The system is divided into several modules by using object-oriented programming technology as a guide during the process of development.The function of every module are implemented, and imitative results are presented. What is more, shortcomings of the thesis are analyzed, and some requests are put forward in the future.
引文
[1]刘葵,赵文津.地震相分析在深反射地震勘探资料解释中的应用[J].地质力学学报,2005,11(2):129-134
[2]段玉顺,李芳.地震相的自动识别方法及应用.石油地球物理勘探[J], 2004,39(2):158-162
[3]沈守文,彭大钧,颜其彬,黄先律,李志军,胡军. SB 地区西山窑组上部地震相与沉积相分析[J]. 西南石油学院学报, 1999,21(3):32-36
[4]袁全社,乐友喜.用神经网络与构造属性进行交互地震相分析[J].勘探地球物理进展,2004,27(2):93-98
[5]West B P,May S R,Eastwood J E,et al. Interactive seismic facies classification using textu- ral attributes and neural networks[J].The Leading Edge, 2002, 21(10):1042-1050
[6]柏冠军.三维地震资料微机管理及可视化解释系统研究与开发[D]:[学位论文].西安:西北大学,2006:36-38
[7]许慧华,王志高. 地震属性分析及其在胜利探区的应用[J].石油仪器,2002,16(5):21-24
[8]Randen T,Monsen E, Signer C,et al. Three-dimensional texture attributes for seismic data analysis[C].Expanded Abstracts of 70 Annual Internat SEG Mtg,2000,668-671
[9]Geoffrey A D,et al.Modern 3D seismic interpretation[J].The Leading Edge,1998,(8):1262- 1272
[10]Barnes A R.Seismic attributes and their classification. [J]The Leading Edge,2001,66(1): 47-48
[11]王龙军,张群会,叶琴.关于地震属性技术的研究和分析[J].科技信息,2008,3(251):592
[12]Hart B S.Validating seismic attribute studies: beyond statistics[J].The Leading Edge, 2002 ,21(10):1016-1021.
[13]Rankey E C,Mitchell J C.Impact of horizon uncertainty on seismic attribute analysis[J]. The Leading Edge,2003,22(9):820-828
[14]陈遵德.储层地震属性优化方法[M].北京:石油工业出版社,1998:93-100
[15]Brown, A. R.Understanding seismic attributes[J].Geophysics, 2001, 66(1), 46-48
[16]吴大奎.利用 K-L 变换提高模式识别的精度[J].石油地球物理勘探,1995 ,30(2):272-277
[17]赵力民,郎晓玲,金凤鸣,曹兰柱.波形分类技术在隐蔽油藏预测中的应用[J].石油勘探与开发,2001,28(6):53-55
[18]Dutta R K,Paul S.Applicability of The Modified Back-Propagation Algorithm in Tool Co- dition Monitoring for Faster Convergence[J].Journal of Materials Processing Technology, 2000,(98):299~309
[19]徐勇,荆涛译.神经网络模式识别及其实现[J].北京:电子工业出版社,1999,(6):3~15
[20]何耀华,夏志忠. BP 网络的快速自适应学习算法[J].系统工程理论与实践,2000,(1):93-98
[21]Beigy H,Meybodi M R.Adaptation of parameters of BP algorithm using learning automa- ta[C].Proceedings Sixth Brazilian Symposium on Neural Networks,2000,24-31
[22]Widyanto R M,NobuharaH.Improving Recognition and Generalization Capability of Back -Propagation NN Using a Self-Organized Network Inspired by Immune Algorithm[J].Ap- pplied Soft Computing.2005,(6):72~84
[23]徐勇,荆涛译.神经网络模式识别及其实现[M].北京:电子工业出版社,1999,(6):3~15
[24]李望晨.BP 神经网络改进及其在手写数字识别中的应用[C]:[学位论文]. 哈尔滨:哈尔滨工业大学,2006:9-12
[25]Cheng C,Tang Y C.To improve the training time of BP neural networks[C].Info-tech and Info-net 2001 International Conference on,2001,3:473-479
[26]王淑红,李英龙,戈保梁,刘墨.主成分分析法与神经网络在选矿建模中的应用.有色矿冶[J],2001,17(6):25-28
[27]王立德,郭其一.基于波形识别的机车电气设备在线故障诊断.电工技术学报[J],2000,- 15(3):225-228
[28]师永民,祁军,张成学,肖荣阁,王斌婷.应用地震波形分析技术预测裂缝的方法探讨[J].石油物探,2005,44(2):128-130
[29]唐大海,谢继容. Stratimagic地震相分析技术在川中GSM油气勘探中的应用.四川地质学报[J],24(3):185-189
[30]Gao J H, et al.On the choice of wavelet functions for seismic data processing[J].Chinese - Geophysics(in Chinese),1996,39(3):389-397
[31]Kohonen T.The self-organizing map[J].Neurocomputing,1998,21:1-6
[32]Zhao Z,Rowden C.Use of Kohonen self-organizing feature maps for HMM parameter sm- ooothing in speech recognition[C].IEEE Proceedings-F,1992,139(6):385-390
[33]Pal N R,Bezdek J C,Tsao E C K.Generalized clustering networks and Kohonen self-orga- nizing scheme[J].IEEE Trans. NN,1993,4(4):549-557
[34]刘纯平.基于 Kohonen 神经网络聚类方法在遥感分类中的比较[J].计算机应用,2000,26 (7):1744-1750
[35]张友水,冯学智,阮仁宗.Kohonen神经网络在遥感影像分类中的应用研究[J].遥感学报, 2004,8(2):17818
[36]涂晓之,颜学峰,钱峰.自组织映射网络及其在化学化工领域中的应用进展[J].计算机与应用化学,2005,22(9):737-740
[37]吴海桥,刘毅等.SOM人工神经网络在客机零部件故障诊断中的应用研究[J].南京航空航天大学学报,2002,34(l):31-34
[38]何术.SOM神经网络在树叶形状分类中的应用[J].电脑开发与应用,2003,(2):23-25
[39]潘爱民,张丽译.C++Primer 第三版[M].北京:中国电力出版社,2004:23-26
[40]David J.ruglinski 著.潘爱民,王国印译.Visual C++技术内幕(第四版)[M].北京:清华大学出版社,1999:280-290
[41]尚涛,石端伟,安宁,张李义.工程计算可视化与 MATLAB 实现[M].武汉:武汉大学出版 社,2002:180-186
[42]和平鸽工作室.OpenGL三维图形系统开发与实用技术[M].北京:清华大学出版社,2003 :25-29
[43]Richard S Wright,Michael Sweet J,潇湘工作室译.OpenGL 超级宝典(第二版)[M].北京: 人民邮电出版社,2001:220-228
[2]段玉顺,李芳.地震相的自动识别方法及应用.石油地球物理勘探[J], 2004,39(2):158-162
[3]沈守文,彭大钧,颜其彬,黄先律,李志军,胡军. SB 地区西山窑组上部地震相与沉积相分析[J]. 西南石油学院学报, 1999,21(3):32-36
[4]袁全社,乐友喜.用神经网络与构造属性进行交互地震相分析[J].勘探地球物理进展,2004,27(2):93-98
[5]West B P,May S R,Eastwood J E,et al. Interactive seismic facies classification using textu- ral attributes and neural networks[J].The Leading Edge, 2002, 21(10):1042-1050
[6]柏冠军.三维地震资料微机管理及可视化解释系统研究与开发[D]:[学位论文].西安:西北大学,2006:36-38
[7]许慧华,王志高. 地震属性分析及其在胜利探区的应用[J].石油仪器,2002,16(5):21-24
[8]Randen T,Monsen E, Signer C,et al. Three-dimensional texture attributes for seismic data analysis[C].Expanded Abstracts of 70 Annual Internat SEG Mtg,2000,668-671
[9]Geoffrey A D,et al.Modern 3D seismic interpretation[J].The Leading Edge,1998,(8):1262- 1272
[10]Barnes A R.Seismic attributes and their classification. [J]The Leading Edge,2001,66(1): 47-48
[11]王龙军,张群会,叶琴.关于地震属性技术的研究和分析[J].科技信息,2008,3(251):592
[12]Hart B S.Validating seismic attribute studies: beyond statistics[J].The Leading Edge, 2002 ,21(10):1016-1021.
[13]Rankey E C,Mitchell J C.Impact of horizon uncertainty on seismic attribute analysis[J]. The Leading Edge,2003,22(9):820-828
[14]陈遵德.储层地震属性优化方法[M].北京:石油工业出版社,1998:93-100
[15]Brown, A. R.Understanding seismic attributes[J].Geophysics, 2001, 66(1), 46-48
[16]吴大奎.利用 K-L 变换提高模式识别的精度[J].石油地球物理勘探,1995 ,30(2):272-277
[17]赵力民,郎晓玲,金凤鸣,曹兰柱.波形分类技术在隐蔽油藏预测中的应用[J].石油勘探与开发,2001,28(6):53-55
[18]Dutta R K,Paul S.Applicability of The Modified Back-Propagation Algorithm in Tool Co- dition Monitoring for Faster Convergence[J].Journal of Materials Processing Technology, 2000,(98):299~309
[19]徐勇,荆涛译.神经网络模式识别及其实现[J].北京:电子工业出版社,1999,(6):3~15
[20]何耀华,夏志忠. BP 网络的快速自适应学习算法[J].系统工程理论与实践,2000,(1):93-98
[21]Beigy H,Meybodi M R.Adaptation of parameters of BP algorithm using learning automa- ta[C].Proceedings Sixth Brazilian Symposium on Neural Networks,2000,24-31
[22]Widyanto R M,NobuharaH.Improving Recognition and Generalization Capability of Back -Propagation NN Using a Self-Organized Network Inspired by Immune Algorithm[J].Ap- pplied Soft Computing.2005,(6):72~84
[23]徐勇,荆涛译.神经网络模式识别及其实现[M].北京:电子工业出版社,1999,(6):3~15
[24]李望晨.BP 神经网络改进及其在手写数字识别中的应用[C]:[学位论文]. 哈尔滨:哈尔滨工业大学,2006:9-12
[25]Cheng C,Tang Y C.To improve the training time of BP neural networks[C].Info-tech and Info-net 2001 International Conference on,2001,3:473-479
[26]王淑红,李英龙,戈保梁,刘墨.主成分分析法与神经网络在选矿建模中的应用.有色矿冶[J],2001,17(6):25-28
[27]王立德,郭其一.基于波形识别的机车电气设备在线故障诊断.电工技术学报[J],2000,- 15(3):225-228
[28]师永民,祁军,张成学,肖荣阁,王斌婷.应用地震波形分析技术预测裂缝的方法探讨[J].石油物探,2005,44(2):128-130
[29]唐大海,谢继容. Stratimagic地震相分析技术在川中GSM油气勘探中的应用.四川地质学报[J],24(3):185-189
[30]Gao J H, et al.On the choice of wavelet functions for seismic data processing[J].Chinese - Geophysics(in Chinese),1996,39(3):389-397
[31]Kohonen T.The self-organizing map[J].Neurocomputing,1998,21:1-6
[32]Zhao Z,Rowden C.Use of Kohonen self-organizing feature maps for HMM parameter sm- ooothing in speech recognition[C].IEEE Proceedings-F,1992,139(6):385-390
[33]Pal N R,Bezdek J C,Tsao E C K.Generalized clustering networks and Kohonen self-orga- nizing scheme[J].IEEE Trans. NN,1993,4(4):549-557
[34]刘纯平.基于 Kohonen 神经网络聚类方法在遥感分类中的比较[J].计算机应用,2000,26 (7):1744-1750
[35]张友水,冯学智,阮仁宗.Kohonen神经网络在遥感影像分类中的应用研究[J].遥感学报, 2004,8(2):17818
[36]涂晓之,颜学峰,钱峰.自组织映射网络及其在化学化工领域中的应用进展[J].计算机与应用化学,2005,22(9):737-740
[37]吴海桥,刘毅等.SOM人工神经网络在客机零部件故障诊断中的应用研究[J].南京航空航天大学学报,2002,34(l):31-34
[38]何术.SOM神经网络在树叶形状分类中的应用[J].电脑开发与应用,2003,(2):23-25
[39]潘爱民,张丽译.C++Primer 第三版[M].北京:中国电力出版社,2004:23-26
[40]David J.ruglinski 著.潘爱民,王国印译.Visual C++技术内幕(第四版)[M].北京:清华大学出版社,1999:280-290
[41]尚涛,石端伟,安宁,张李义.工程计算可视化与 MATLAB 实现[M].武汉:武汉大学出版 社,2002:180-186
[42]和平鸽工作室.OpenGL三维图形系统开发与实用技术[M].北京:清华大学出版社,2003 :25-29
[43]Richard S Wright,Michael Sweet J,潇湘工作室译.OpenGL 超级宝典(第二版)[M].北京: 人民邮电出版社,2001:220-228
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |