聚类和判别分析在测井岩性识别中的应用  

The Application of Cluster and Discriminant Analyses in Logging Lithology Recognition

作　　者：寻知锋[1] 余继峰[1] 

机构地区：[1]山东科技大学地质科学与工程学院,山东青岛266510

出　　处：《山东科技大学学报（自然科学版）》2008年第5期10-13,共4页Journal of Shandong University of Science and Technology(Natural Science)

基　　金：教育部留学回国人员科研启动基金项目(2006331);中国博士后科研基金项目(第41批)

摘　　要：应用多元统计方法和计算机技术对测井数据进行岩性识别。以济阳坳陷中的某钻井测井资料为例,首先进行了层次聚类和k-means聚类分析,然后根据聚类分析结果进行判别分析,两种统计方法相结合识别钻井岩性,得出了预测岩性剖面和录井剖面基本吻合的综合柱状图。结果说明,聚类分析和判别分析相结合的定量方法在测井岩性识别方面具有实用价值。The multivariate statistical method and the computer technology are used in the paper to identify lithology of the logging data. The logging data in Jiyang Depression are selected for case study. The hierarchical clustering and k-means clustering are firstly adopted in determining the proper number of clusters, then, based on the cluster analy- sis resuh,diseriminant analysis methods are used for forecasting lithology. The lithology profile recognized by the combination of these two methods coincides well with the lithology column provided by logging company. This quan- titative method has proved to be of good value in identifying lithology with logging data.

关 键 词：多元统计 聚类分析 判别分析 岩性识别 测井资料 定量方法 

分 类 号：P631.84[天文地球—地质矿产勘探]