2017年12月第36卷第6期
大庆石油地质与开发
Petroleum Geology and Oilfield Development in Daqing
DOI:10.19597/J.ISSN.1000-3754.201703072
Dee.，2017 Vel. 36 No. 6
基于粗糙集一随机森林算法的复杂岩性识别
张占松1,2张超谟"2聂昕1,2朱林奇1,2
周雪晴1,2张
（1.长江大学油气资源与勘探技术教育部重点实验室，湖北武汉430100： 2.长江大学非常规油气湖北省协同创新中心，湖北武汉430100）
张宏悦1,2
摘要：针对复杂岩性碳酸盐岩储层原有岩性识别方法精度较低、泛化能力不足、结果不稳定等问题，提出基于粗楚集-随机森林算法的复杂岩性识别方法。利用邻域粗糙集的属性约简选取岩性敏感曲线，在不影响岩性识别基础上将不必要曲线翻除，能有效去除元余信息；其次将筛选出的曲线作为随机森林模型输人，建立粗髓集-随机森林算法的性识别模型。通过对某区块502块岩心数据处理，该模型岩性判别率稳定到88.3%，比Fisher判别、Bayes判别等方法精度高，且实现简单，有较强泛化能力。该方法可作为复杂岩性储层岩性识别方法，为复杂岩性储层的勘探开发提供帮助。
关键调：复杂岩性储层；碳酸盐岩；岩性识别：邻域粗糙集；随机森林
中图分类号：P631.8
文献标识码：A
文章编号：1000-3754（2017）06-0127-07
COMPLEXLITHOLOGICIDENTIFICATIONBASEDON
ROUGHSET-RANDOMFORESTALGORISM
ZHOU Xueqing'-2, ZHANG Zhansong'-2, ZHANG Chaomo-2, NIE Xin'-2, ZHU Linqi'-2, ZHANG Hongyue'-2
(1, MOE Key Laboratory of Exploration Technologies for Oil and Gas Resources, Yangtze University， Wuhan 430100, China; 2. Hubei Cooperatine Innotation Center of Unconventional Oil and Gas,
Yangtze University, Wuhan 430100, China)
Abstract: In view of the problems of the low precision of the original identifying methods, insufficient generalized ability, unstable results and so on for the complex-lithology carbonate reservoir, the identifying method for the com-plex lithology was proposed based on rough set-random forest algorism. With the help of the atributes of the neigh-borhood rough set, the lithology sensitive curves were reduced and chosen, on the basis of the non-effects on the li-thology identification, the unnecessary curves were cut out to effectively delete the redundant information; and then the chosen curves were input into the random forest model and the lithology identifying model for the rough set- ran-dom forest algorism was established. Through the core data processing of 502 samples in a block , the identified ratio of the lithology for the model has been stabilized to 88. 3% i. e. is significantly higher than other discriminating methods (Fisher and Bayes) and furthermore the task is easy to realized and the model possesses much stronger ca
改回日期：2017-10-30
收稿日期：2017-03-25
基金项目：国家自然科学基金项目“页岩油储层岩石物理特性数值模拟研究”（41504094）、"致密气储层岩石导电机理
（）究与应用”（2017ZX05032003-005）。
作者篇介：周雪靖，女，1993年生，在读硕士，从事地球物理测并解释与评价研究。
E-mail: 201571239@ yangtzeu, edu. cn
万方数据