主成分分析与模糊识别在岩性识别中的应用

doi:10.3969/j.issn.1673-8926.2017.05.015

岩性油气藏 ›› 2017, Vol. 29 ›› Issue (5): 127–133.doi: 10.3969/j.issn.1673-8926.2017.05.015

主成分分析与模糊识别在岩性识别中的应用

马峥¹, 张春雷², 高世臣¹

1. 中国地质大学(北京)数理学院, 北京 100083;
2. 北京中地润德石油科技有限公司, 北京 100083

收稿日期:2017-04-30 修回日期:2017-07-14 出版日期:2017-09-21 发布日期:2017-09-21
通讯作者: 高世臣(1965-),男,博士,教授,主要从事油气田开发地质方面的教学和研究工作。Email:gsc2039@163.com。 E-mail:gsc2039@163.com
作者简介:马峥(1993-),女,中国地质大学(北京)在读硕士研究生,研究方向为数据挖掘。地址:(100083)北京市海淀区学院路29号中国地质大学(北京)。Email:545308598@qq.com。
基金资助:
国家自然科学基金项目“基于正交匹配追踪算法的相敏关联层析研究”（编号：29932016006）与“异常高压致密砂砾岩油藏衰竭式开采渗流规律研究”（编号：51674227）联合资助

Lithology identification based on principal component analysis and fuzzy recognition

MAZheng¹, ZHANG Chunlei², GAO Shichen¹

1. School of Science, China University of Geosciences, Beijing 100083, China;
2. Beijing Zhongdirunde Petroleum Technology Co. Ltd, Beijing 100083, China

Received:2017-04-30 Revised:2017-07-14 Online:2017-09-21 Published:2017-09-21

摘要/Abstract

摘要： 表征复杂岩性的测井曲线之间的相似度较高，在岩性识别过程中存在着大量信息冗余，造成测井曲线具有一定的模糊性与相关性，干扰识别过程，导致识别效果不理想。以苏里格气田苏东41-33区块马家沟组五段碳酸盐岩测井数据为例，采用一种基于主成分分析与模糊识别相结合的方法解决了这一难题。该方法首先提取声波时差（AC）、自然伽马（GR）、光电吸收截面指数（P_e）、补偿中子（CNL）、补偿密度（DEN）、深侧向电阻率（R_LLD）等对岩性变化反映比较敏感的测井曲线参数，通过主成分分析构建出3个综合变量Y₁，Y₂和Y₃，再采用模糊识别方法对研究区的岩性进行识别。与传统识别方法相比，主成分分析与模糊识别相结合的岩性识别方法能有效消除特征曲线间的模糊性与相关性，并使岩性识别的正确率达到86%，是一种实用且有效的识别复杂岩性的方法，具有一定的推广和应用价值。

关键词: 模糊识别, 主成分分析, 岩性识别, 测井参数, 苏里格气田

Abstract: It is not ideal that characterization the complex lithology is disturbed by logging curves,which are redundancies in high similarity logging parameters. Based on principal component analysis(PCA) and fuzzy recognition, to solve this problem,a method was adopt to identify the complex lithology,and verified by carbonate rocks logging data of from fifth member of Majiagou Formation in Sudong 41-33 blocks of Sulige gasfileld. The complex lithology identification methods chose six logging curves of AC,GR,Pe,CNL,DEN,R_LLD firstly,which are sensitive to lithology change,then construct three comprehensive variables Y₁,Y₂,Y₃ by principal component analysis,and finally identify lithology by fuzzy recognition method. Compared with traditional identification methods,the method eliminate the fuzziness and correlation effectively,and the accuracy rate is reached up to 86%. It is a practical and effective method of complex lithology identification,and has certain popularization and application value.

Key words: fuzzy recognition, principal component analysis, lithology identification, well logging curve, Sulige gasfilelds

中图分类号:

P618.13

马峥, 张春雷, 高世臣. 主成分分析与模糊识别在岩性识别中的应用[J]. 岩性油气藏, 2017, 29(5): 127–133.

MAZheng, ZHANG Chunlei, GAO Shichen. Lithology identification based on principal component analysis and fuzzy recognition[J]. Lithologic Reservoirs, 2017, 29(5): 127–133.

参考文献

[1] 佘刚,马丽娟,徐永发,等. 油砂储层特征及测井评价方法研究——以柴达木盆地干柴沟地区为例. 岩性油气藏,2015,27(6):119-124. SHE G,MA L J,XU Y F,et al. Reservoir characteristics of oil sands and logging evaluation methods:a case study from Ganchaigouarea, Qaidam Basin. Lithologic Rservoirs,2015,27(6):119-124.
[2] 包强,张婷,张晓东,等. 岩石相测井识别技术在阿姆河右岸A区的应用.天然气工业,2013,33(11):51-55. BAO Q,ZHANG T,ZHANG X D,et al. Application of logging lithofacies identification technology in block A of the Right Bank of the Amu-Darya River. Natural Gas Industry, 2013,33(11):51-55.
[3] 张大权,邹妞妞,姜杨,等. 火山岩岩性测井识别方法研究——以准噶尔盆地火山岩为例. 岩性油气藏,2015,27(1):108-114. ZHANG D Q,ZOU N N,JIANG Y,et al. Logging identification method of volcanic rock lithology:a case study from volcanic rock in Junggar Basin. Lithologic Rservoirs,2015,27(1):108-114.
[4] 王庆如,李敬功. 碳酸盐岩气藏储量参数测井评价方法. 岩性油气藏,2013,25(6):98-102. WANG Q R,LI J G. Logging evaluation method of reserve parameters of carbonate gas reservoir. Lithologic Rservoirs,2013, 25(6):98-102.
[5] BALDWIN J L,BATEMAN R M,WHEATLEY C L. Application of a neural network to the problem of mineral identification from well logs. Log Analyst,1990,3(5):279-293.
[6] 单敬福,陈欣欣,赵忠军,等. 利用BP神经网络法对致密砂岩气藏储集层复杂岩性的识别. 地球物理学进展,2015,30(3):1257-1263. SHAN J F,CHEN X X,ZHAO Z J,et al. Identification of complex lithology for tight sandstone gas reservoirs sase on BP neural net. Progress in Geophysics,2015,30(3):1257-1263.
[7] 张国英,王娜娜,张润生. 基于主成分分析的BP神经网络在岩性识别中的应用. 北京石油化工学院学报,2008,16(3):43-46. ZHANG G Y,WANG N N,ZHANG R S. Application of principal component analysis and BP neural network in identifying lithology. Journal of Beijing Institute of Petro-chemical Technology, 2008,16(3):43-46.
[8] AL-ANAZI A,GATES I D. On the capability of support vector machines to classify lithology from well logs. Natural Resources Research,2010,19(2):125-139.
[9] 于代国,孙建孟,王焕增,等. 测井识别岩性新方法——支持向量机方法.大庆石油地质与开发,2005,24(5):93-95. YU D G,SUN J M,WANG H Z,et al. A new method for logging lithology identification-SVM. Petroleum Geology & Oilfield Development in Daqing,2005,24(5):93-95.
[10] 胡红,曾恒英,梁海波,等. 基于主成分分析和学习矢量化的神经网络岩性识别方法.测井技术,2015,39(5):586-590. HU H,ZENG H Y,LIANG H B,et al. Lithology identification based on principal component analysis and learning vector quantization neural network. Well Logging Technology,2015, 39(5):586-590.
[11] 杨兆栓,林畅松,尹宏,等. 主成分分析在塔中地区奥陶系鹰山组碳酸盐岩岩性识别中的应用. 天然气地球科学,2015,26(1):54-59. YANG Z S,LIN C S,YIN H,et al. Application of principal component analysis in carbonate lithology identification of the Ordovician Yingshan formation in Tazhong area. Natural Gas Geoscience,2015,26(1):54-59.
[12] 刘璐,吴成茂. 模糊局部均值聚类分割法改进及其应用. 计算机工程与设计,2015,36(12):3365-3369. LIU L,WU C M. Improvement and application of fuzzy local mean clustering segmentation method.Computer Engineering and Design,2015,36(12):3365-3369.
[13] 李洁,高新波,焦李成. 基于特征加权的模糊聚类新算法. 电子学报,2006,34(1):89-92. LI J,GAO X B,JIAO L C. A new feature weighted fuzzy clustering algorithm. Chinese Journal of Electronics,2006,34(1):89-92.
[14] PROVOROVA I,PARSHUTIN S,PROVOROVS S. Usin genetic algorithm to optimize weights in data mining task. Scientific Journal of Riga Technical University,Computer Sciences,2009, 40(1):123-128.
[15] 张涛,莫修文. 基于交会图与模糊聚类算法的复杂岩性识别. 吉林大学学报(地球科学版),2007,37(增刊1):109-113. ZHANG T,MO X W. Complex lithologic identification based on cross plot and fuzzy clustering algorithm. Journal of Jilin University(Earth Science Edition),2007,37(Suppl 1):109-113.
[16] DUBOIS M K,BOHLING G C,CHAKRABARTI S. Comparison of four approaches to a rock facies classification problem. Computers and Geosciences,2007,33(5):599-617.
[17] 王瑞,朱筱敏,王礼常. 用数据挖掘方法识别碳酸盐岩岩性. 测井技术,2012,36(2):197-201. WANG R,ZHU X M,WANG L C. Using data mining to identify carbonate lithology. Well Logging Technology,2012,36(2):197-201.
[18] HSIE B Z,LEWIS C,LIN Z S. Lithology identification of aquifers from geophysical well logs and fuzzy logic analysis:Shuilin area,Taiwan. Computers & Geosciences,2005,31(3):263-275.
[19] DONG S,WANG Z,ZENG L. Lithology identification using kernel Fisher discriminant analysis with well logs. Journal of Petroleum Science and Engineering,2016,143:95-102.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

主成分分析与模糊识别在岩性识别中的应用

Lithology identification based on principal component analysis and fuzzy recognition

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	杨占伟, 姜振学, 梁志凯, 吴伟, 王军霞, 宫厚健, 李维邦, 苏展飞, 郝绵柱. 基于2种机器学习方法的页岩TOC含量评价——以川南五峰组—龙马溪组为例[J]. 岩性油气藏, 2022, 34(1): 130-138.
[2]	叶涛, 牛成民, 王清斌, 高坤顺, 孙哲, 陈安清. 用“成分-结构”分类法识别古潜山变质岩岩性——以渤海海域太古界为例[J]. 岩性油气藏, 2021, 33(6): 156-164.
[3]	李志远, 杨仁超, 张吉, 王一, 杨特波, 董亮. 天然气扩散散失率定量评价——以苏里格气田苏X区块为例[J]. 岩性油气藏, 2021, 33(4): 76-84.
[4]	马乔雨, 张欣, 张春雷, 周恒, 武中原. 基于一维卷积神经网络的横波速度预测[J]. 岩性油气藏, 2021, 33(4): 111-120.
[5]	武中原, 张欣, 张春雷, 王海英. 基于LSTM循环神经网络的岩性识别方法[J]. 岩性油气藏, 2021, 33(3): 120-128.
[6]	龙盛芳, 王玉善, 李国良, 段传丽, 邵映明, 何咏梅, 陈凌云, 焦煦. 苏里格气田苏49区块盒8下亚段致密储层非均质性特征[J]. 岩性油气藏, 2021, 33(2): 59-69.
[7]	李树博, 郭旭光, 郑孟林, 王泽胜, 刘新龙. 准噶尔盆地东部西泉地区石炭系火山岩岩性识别[J]. 岩性油气藏, 2021, 33(1): 258-266.
[8]	孙予舒, 黄芸, 梁婷, 季汉成, 向鹏飞, 徐新蓉. 基于XGBoost算法的复杂碳酸盐岩岩性测井识别[J]. 岩性油气藏, 2020, 32(4): 98-106.
[9]	侯科锋, 李进步, 张吉, 王龙, 田敏. 苏里格致密砂岩气藏未动用储量评价及开发对策[J]. 岩性油气藏, 2020, 32(4): 115-125.
[10]	田清华, 刘俊, 张晨, 王文胜, 黄丹. 苏里格气田下古生界储层特征及主控因素[J]. 岩性油气藏, 2020, 32(2): 33-42.
[11]	柳娜, 周兆华, 任大忠, 南珺祥, 刘登科, 杜堃. 致密砂岩气藏可动流体分布特征及其控制因素——以苏里格气田西区盒8段与山1段为例[J]. 岩性油气藏, 2019, 31(6): 14-25.
[12]	仲鸿儒, 成育红, 林孟雄, 高世臣, 仲婷婷. 基于SOM和模糊识别的复杂碳酸盐岩岩性识别[J]. 岩性油气藏, 2019, 31(5): 84-91.
[13]	冯强汉, 阳生国, 熊哲, 高航, 张佳超, 杨懿, 杨振. 苏里格气田西部S48区气水分布特征[J]. 岩性油气藏, 2019, 31(5): 61-69.
[14]	刘跃杰, 刘书强, 马强, 姚宗森, 佘家朝. BP神经网络法在三塘湖盆地芦草沟组页岩岩相识别中的应用[J]. 岩性油气藏, 2019, 31(4): 101-111.
[15]	崔连可, 单敬福, 李浮萍, 崔璐, 种健. 基于稀疏井网条件下的古辫状河道心滩砂体估算——以苏里格气田苏X区块为例[J]. 岩性油气藏, 2018, 30(1): 155-164.