基于核空间的模糊聚类方法在储层预测中的应用
|
摘要
基于核空间的模糊C均值聚类方法是一种模式识别的新方法。在地震属性聚类处理时常常会遇到非超球体数据以及非线性类间边界等问题,而传统的模糊C均值聚类方法无法行之有效地解决。将核空间方法引入传统的模糊C均值聚类方法中,并应用于储层预测。针对地震属性聚类问题中不同属性对于储层的敏感性不同,将特征权重和模糊指数等参数加以优化,提高新的模糊聚类方法的储层预测效果。对实际资料的计算与分析结果表明,新的基于核空间的模糊C均值聚类方法可以更准确地刻画碳酸盐岩含气储层边界。
The kernel fuzzy C-means(FCM) method is a novel method for pattern recognition.The problems such as non-hyperspherical data and non-linear inter-class boundary are prevalent during seismic attributes clustering process,which could not be resolved effectively by traditional FCM method.The kernel function was introduced into traditional FCM method for these problems in reservoir prediction.The parameters including feature weights and fuzzy coefficient were optimized for different sensibility of seismic attributes,which could improve the effectiveness of this new kernel FCM method for reservoir prediction.The results of experiments on the artificial and real data show that the new kernel FCM method can describe the boundaries of gas-bearing carbonate reservoir more accurately.
The kernel fuzzy C-means(FCM) method is a novel method for pattern recognition.The problems such as non-hyperspherical data and non-linear inter-class boundary are prevalent during seismic attributes clustering process,which could not be resolved effectively by traditional FCM method.The kernel function was introduced into traditional FCM method for these problems in reservoir prediction.The parameters including feature weights and fuzzy coefficient were optimized for different sensibility of seismic attributes,which could improve the effectiveness of this new kernel FCM method for reservoir prediction.The results of experiments on the artificial and real data show that the new kernel FCM method can describe the boundaries of gas-bearing carbonate reservoir more accurately.
引文
[1]QUINCY Chen,STEVE Sidney.Seismic attribute tech-nology for reservoir forecasting and monitoring[J].TheLeading Edge,1997,16(5):445-456.
[2]印兴耀,周静毅.地震属性优化方法综述[J].石油地球物理勘探,2005,40(4):482-489.YIN Xing-yao,ZHOU Jing-yi.Summary of optimummethods of seismic attributes[J].Oil Geophysical Pros-pecting,2005,40(4):482-489.
[3]印兴耀,孔国英,张广智.基于核主成分分析的地震属性优化方法及应用[J].石油地球物理勘探,2008,43(2):179-183.YIN Xing-yao,KONG Guo-ying,ZHANG Guang-zhi.Seismic attributes optimization based on kernel principalcomponent analysis(KPCA)and application[J].OilGeophysical Prospecting,2008,43(2):179-183.
[4]杨培杰,印兴耀,张广智.模糊C均值地震属性聚类分析[J].石油地球物理勘探,2007,42(3):322-324,347.YANG Pei-jie,YIN Xing-yao,ZHANG Guang-zhi.Clus-ter analysis of seismic attributes by fuzzy C-mean algo-rithm[J].Oil Geophysical Prospecting,2007,42(3):322-324,347.
[5]叶端南,印兴耀,张广智.地震属性转换中褶积算子的应用研究[C]//中国地球物理协会.中国地球物理年会论文集.合肥:中国科学技术大学出版社,2009:150.
[6]何碧竹,周杰,汪功怀.利用多元地震属性预测储层信息[J].石油地球物理勘探,2003,38(3):258-262.HE Bi-zhu,ZHOU Jie,WANG Gong-huai.Using multi-variate seismic attributions to predict reservoir information[J].Oil Geophysical Prospecting,2003,38(3):258-262.
[7]BEZDEK J C.Pattern recognition with fuzzy objectivefunction algorithms[M].New York:Plenum Press,1981.
[8]HATHAWAY R J,BEZDEK J C,TUCKER W T.Con-vergence results for the fuzzy c-means clustering:counterexamples and repairs[J].IEEE Trans PAMI,1987,17(5):873-877.
[9]伍忠东,高新波,谢维信.基于核方法的模糊聚类算法[J].西安电子科技大学学报:自然科学版,2004,31(4):533-537.WU Zhong-dong,GAO Xin-bo,XIE Wei-xin.A study ofa new fuzzy clustering algorithm based on the kernelmethod[J].Journal of Xidian University,2004,31(4):533-537.
[10]孔攀,邓辉文,江欢,等.改进的基于核函数的模糊聚类算法[J].计算机应用,2008,28(9):2338-2340.KONG Pan,DENG Hui-wen,JIANG Huan,et al.Im-proved kernel-based fuzzy clustering algorithm[J].Journal of Computer Applications,2008,28(9):2338-2340.
[11]普运伟,金炜东,朱明,等.核模糊C均值算法的聚类有效性研究[J].计算机科学,2007,34(2):207-210,229.PU Yun-wei,JIN Wei-dong,ZHU Ming,et al.Oncluster validity for kernelized fuzzy C-mean algorithm[J].Computer Science,2007,34(2):207-210,229.
[12]高新波,裴继红,谢维信.模糊C-均值聚类算法中加权指数m的研究[J].电子学报,2000,28(4):80-83.GAO Xin-bo,PEI Ji-hong,XIE Wei-xin.A study ofweighting exponent m in a fuzzy C-means algorithm[J].Acta electronica Sinica,2000,28(4):80-83.
[13]宫改云,高新波,伍忠东.FCM聚类算法中模糊加权指数m的优选方法[J].模糊系统与数学,2005,19(1):143-148.GONG Gai-yun,GAO Xin-bo,WU Zhong-dong.An op-timal choice method of parameter m in FCM clusteringalgorithm[J].Fuzzy Systems and Mathematics,2005,19(1):143-148.
[14]肖满生,阳娣兰,张居武,等.基于模糊相关度的模糊C均值聚类加权指数研究[J].计算机应用,2010,30(12):3388-3390.XIAO Man-sheng,YANG Di-lan,ZHANG Ju-wu,etal.Research of weighting exponent of fuzzy C-means al-gorithm based on fuzzy relevance[J].Journal of Com-puter Applications,2010,30(12):3388-3390.
[15]曹辉.地震参数解释的模式识别法[J].石油地球物理勘探,1994,29(2):140-146.CAO Hui.A pattern recognition method for seismic pa-rameter interpretation[J].Oil Geophysical Prospecting,1994,29(2):140-146.
[2]印兴耀,周静毅.地震属性优化方法综述[J].石油地球物理勘探,2005,40(4):482-489.YIN Xing-yao,ZHOU Jing-yi.Summary of optimummethods of seismic attributes[J].Oil Geophysical Pros-pecting,2005,40(4):482-489.
[3]印兴耀,孔国英,张广智.基于核主成分分析的地震属性优化方法及应用[J].石油地球物理勘探,2008,43(2):179-183.YIN Xing-yao,KONG Guo-ying,ZHANG Guang-zhi.Seismic attributes optimization based on kernel principalcomponent analysis(KPCA)and application[J].OilGeophysical Prospecting,2008,43(2):179-183.
[4]杨培杰,印兴耀,张广智.模糊C均值地震属性聚类分析[J].石油地球物理勘探,2007,42(3):322-324,347.YANG Pei-jie,YIN Xing-yao,ZHANG Guang-zhi.Clus-ter analysis of seismic attributes by fuzzy C-mean algo-rithm[J].Oil Geophysical Prospecting,2007,42(3):322-324,347.
[5]叶端南,印兴耀,张广智.地震属性转换中褶积算子的应用研究[C]//中国地球物理协会.中国地球物理年会论文集.合肥:中国科学技术大学出版社,2009:150.
[6]何碧竹,周杰,汪功怀.利用多元地震属性预测储层信息[J].石油地球物理勘探,2003,38(3):258-262.HE Bi-zhu,ZHOU Jie,WANG Gong-huai.Using multi-variate seismic attributions to predict reservoir information[J].Oil Geophysical Prospecting,2003,38(3):258-262.
[7]BEZDEK J C.Pattern recognition with fuzzy objectivefunction algorithms[M].New York:Plenum Press,1981.
[8]HATHAWAY R J,BEZDEK J C,TUCKER W T.Con-vergence results for the fuzzy c-means clustering:counterexamples and repairs[J].IEEE Trans PAMI,1987,17(5):873-877.
[9]伍忠东,高新波,谢维信.基于核方法的模糊聚类算法[J].西安电子科技大学学报:自然科学版,2004,31(4):533-537.WU Zhong-dong,GAO Xin-bo,XIE Wei-xin.A study ofa new fuzzy clustering algorithm based on the kernelmethod[J].Journal of Xidian University,2004,31(4):533-537.
[10]孔攀,邓辉文,江欢,等.改进的基于核函数的模糊聚类算法[J].计算机应用,2008,28(9):2338-2340.KONG Pan,DENG Hui-wen,JIANG Huan,et al.Im-proved kernel-based fuzzy clustering algorithm[J].Journal of Computer Applications,2008,28(9):2338-2340.
[11]普运伟,金炜东,朱明,等.核模糊C均值算法的聚类有效性研究[J].计算机科学,2007,34(2):207-210,229.PU Yun-wei,JIN Wei-dong,ZHU Ming,et al.Oncluster validity for kernelized fuzzy C-mean algorithm[J].Computer Science,2007,34(2):207-210,229.
[12]高新波,裴继红,谢维信.模糊C-均值聚类算法中加权指数m的研究[J].电子学报,2000,28(4):80-83.GAO Xin-bo,PEI Ji-hong,XIE Wei-xin.A study ofweighting exponent m in a fuzzy C-means algorithm[J].Acta electronica Sinica,2000,28(4):80-83.
[13]宫改云,高新波,伍忠东.FCM聚类算法中模糊加权指数m的优选方法[J].模糊系统与数学,2005,19(1):143-148.GONG Gai-yun,GAO Xin-bo,WU Zhong-dong.An op-timal choice method of parameter m in FCM clusteringalgorithm[J].Fuzzy Systems and Mathematics,2005,19(1):143-148.
[14]肖满生,阳娣兰,张居武,等.基于模糊相关度的模糊C均值聚类加权指数研究[J].计算机应用,2010,30(12):3388-3390.XIAO Man-sheng,YANG Di-lan,ZHANG Ju-wu,etal.Research of weighting exponent of fuzzy C-means al-gorithm based on fuzzy relevance[J].Journal of Com-puter Applications,2010,30(12):3388-3390.
[15]曹辉.地震参数解释的模式识别法[J].石油地球物理勘探,1994,29(2):140-146.CAO Hui.A pattern recognition method for seismic pa-rameter interpretation[J].Oil Geophysical Prospecting,1994,29(2):140-146.
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