基于核空间的模糊聚类方法在储层预中的应用.PDFVIP

-吨多， e 2012 年第36 卷 中国石油大学学报(自然科学版) Vo 1. 36 No.l 第 1 期 Joumal of China University of Petroleum Feb.2012 文章编号: 1673-5005 (2012) 01 -0053 -07 基于核空间的模糊聚类方法在储层预 中的应用 印兴耀，叶端南，张广智 (中国石油大学地球科学与技术学院，山东青岛 266555 ) 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。将核空间方法引人传统的 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。 关键词:核空间;模糊聚类;地震属性;储层预测 中国分类号:P 63 1. 49 文献标志码:A doi: 10. 3969/j. issn. 1673-5005.2012.01. 009 Application of kernel fuzzy C-means method to reservoir prediction YIN Xing-yao , YE Duan-nan , ZHANG Guang-zhi ( College 0/ Geosciences in China University 0/ Petroleum , Qingdao 266555 , China) Abstract: The kemel fuzzy C-means (FCM) method is a novel method for pattem recognition. The problems such as non- hyperspherical data and non-linear inter-class boundalγare prevalent during seismic attributes clustering process , which could not be resolved effectively by traditional FCM method. The kemel 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 kemel FCM method for reservoir prediction. The results of experiments on the artificial and real data show that