| 摘要: |
| 针对传统储层流体识别方法识别精度低、运算量大、过于依赖个人经验的缺点,提出基于密度聚类的K近邻法,根据待测层段测井数据的空间分布规律,将样本按相对密度聚类成数据簇,并利用K近邻投票获得各簇所属类别。将该方法应用在某油田奥陶系鹰山组碳酸盐岩储层识别中。结果表明,较之其他常用识别方法,该算法识别精度高,泛化性和鲁棒性强,在处理大数据分类问题时具有明显优势,且在识别常规方法难以识别的油水同层时取得了较好的效果,具有良好的应用前景,为利用数据挖掘方法解决油田勘探开发中的复杂问题提供了新思路。 |
| 关键词: 测井解释 流体识别 K近邻法 相对密度聚类 数据挖掘 |
| DOI：10.3969/j.issn.1673-5005.2015.05.009 |
| 分类号::P 631.84; TE 122.2 |
| 基金项目:国家“十二五”重大专项(2011ZX05049-001-001) |
|
| Application of density clustering based K-nearest neighbor method for fluid identification |
|
ZHAO Jun1, LU Yifan1, LI Zongjie2, LIU Jianhua2
|
|
(1.School of Geoscience and Technology, Southwest Petroleum University,Chengdu 610500, China;2.Sinopec Northwest Oilfield Branch, Urumqi 830013, China)
|
| Abstract: |
| Reservoir fluid identification is an indispensable link in logging interpretation.In order to remove the defects of traditional approaches, such as unsatisfying accuracy, excessive computation, undue dependence on personal experience, a density clustering based K-nearest neighbor method was proposed. According to the spatial distribution of the interval logging data under test, data clusters are formed based on relative density. And then with K-nearest neighbor voting method, the categories of all clusters become available. Comparing with other commonly used identification methods, tested on the carbonate reservoir of Ordovician Yingshan Formation in an oil field, this approach shows a high accuracy, strong generalization and robustness, as well as better effects on oil-water layer identification which is usually difficult for the compared methods. The method has a good application prospect and provides a new thought on solving complex problems in oilfield exploration and development with data mining methods. |
| Key words: logging interpretation fluid identification K-nearest neighbor method relative density clustering data mining |
