Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Well Logging Technology》 2010-01
Add to Favorite Get Latest Update

Lithology Identification of Conglomerate Reservoir Based on Decision Tree Method

LI Hongqi1,2,TAN Fengqi1,2,XU Changfu3,YAO Zhenhua3,PENG Shouchang3(1.Faculty of Natural Resource and Information Technology,China University of Petroleum,Beijing 102249,China;2.State Key Laboratory of Petroleum Resource and Prospecting,China University of Petroleum,Beijing 102249,China;3.Research Institute of Petroleum Exploration and Development,Xinjiang Oilfield Company,PetroChina,Karamay,Xinjiang 834000,China)  
The characteristics of conglomerate reservoir are complicated reservoir lithology and logging response without changes in regularity because of the special depositional environment of close source,multistreams and rapid changing,and accurate identification of lithology becomes focus and difficult in development of conglomerate reservoir.Studied is Kexia Group conglomerate reservoir of the Sixth District in Karamay Oilfield with Decision Tree method,and analyzed is the logging curve sensitivity of eight kinds of conglomerate reservoir lithologies combined with sealed coring data.Optimized are three logging response values such as original formation resistivity,acoustic travel time and natural gamma as characteristic parameters of conglomerate lithology identification.Finally,established are the lithology identification models of the Decision Tree with integrated identification accuracy rate reaching 96.97%,their effect is good in the second adjustment development of oilfield and evaluation of water flooded layers.Based on analysis results of the Decision Tree,completed is the identification plate of conglomerate reservoir lithology with geophysical methods.The effective combination of data mining methods and geophysical methods provides a new thinking and a new method to solve complex questions in oilfield exploration and development.
【CateGory Index】: P618.13
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved