摘要
针对火山岩储层,从岩石化学成分分类和岩石结构分类两个角度出发,提出了一种利用测井资料识别火山岩岩性的方法。基于取芯薄片鉴定资料获得对应井段的常规测井数据,利用统计学习理论中的支持向量机方法对其处理,得到地质上按岩石化学成分分类的火山岩岩性类别。建立地层微电阻率成像测井图像与不同结构火山岩岩性之间的对应关系,归纳出典型的微电阻率图像模式,从而得到地质上按岩石结构分类的火山岩岩性类别,结合上述两者结论确定最终岩性,实现了运用支持向量机算法处理常规测井资料与微电阻率图像模式相结合的火山岩岩性测井识别新方法。
From the viewpoint of chemical composition categorization and structure classification of rocks, an effective method was proposed to identify the fithology of volcanic rocks by using logging data. On the one hand, the conventional logging data could be obtained by core wafer identification. Thus, after processing the data with Support Vector Machines ( SVM ) method of statistical theory, we could get the lithologic type of the volcanic rocks, which are classified according to the chemical composition of rocks. On the other hand, the volcanic rocks can be classified as volcanic lava, pyroclastic lava and pyroclastic rock according to the rock structure. Typi- cal formation micro-resistivity imaging logging (FMI) image mode can be concluded by establishing the corresponding relationship be- tween FMI images and lithology of volcanic rocks with different structures. As a result, the lithologic type of the volcanic rock classified by rock structure can be determined. Finally, by combining these two kinds of litbology, the ultimate rock lithology can be determined, too. In this paper, the authors presented a novel method to identify the lithology of volcanic rocks by combining SVM processed logging data and FMI image mode.
出处
《物探与化探》
CAS
CSCD
北大核心
2011年第5期634-638,642,共6页
Geophysical and Geochemical Exploration
关键词
支持向量机
地层微电阻率成像测井
火山岩岩性识别
Support Vector Machines
formation micro-resistivity imaging logging
lithologic identification of volcanic rock