岩性油气藏 ›› 2019, Vol. 31 ›› Issue (5): 84–91.doi: 10.12108/yxyqc.20190509

• 勘探技术 • 上一篇    下一篇

基于SOM和模糊识别的复杂碳酸盐岩岩性识别

仲鸿儒1, 成育红2, 林孟雄2, 高世臣3, 仲婷婷3   

  1. 1. 中国地质大学(北京)信息工程学院, 北京 100083;
    2. 中国石油长庆油田分公司 第五采气厂, 西安 710016;
    3. 中国地质大学(北京)数理学院, 北京 100083
  • 收稿日期:2019-04-13 修回日期:2019-05-20 出版日期:2019-09-21 发布日期:2019-09-16
  • 第一作者:仲鸿儒(1993-),男,中国地质大学(北京)在读硕士研究生,研究方向为机器学习、地质和遥感。地址:(100083)北京市海淀区学院路38号中国地质大学信息工程学院。Email:2004170017@cugb.edu.cn。
  • 基金资助:
    国家科技重大专项“鄂尔多斯盆地大型岩性地层油气藏勘探开发示范工程”（编号：2016ZX05050）资助

Lithology identification of complex carbonate based on SOM and fuzzy recognition

ZHONG Hongru1, CHENG Yuhong2, LIN Mengxiong2, GAO Shichen3, ZHONG Tingting3   

  1. 1. School of Information Engineering, China University of Geosciences, Beijing 100083, China;
    2. No.5 Gas Production Plant, PetroChinaChangqing Oilfield Company, Xi'an 710016, China;
    3. School of Science, China University of Geosciences, Beijing 100083, China
  • Received:2019-04-13 Revised:2019-05-20 Online:2019-09-21 Published:2019-09-16

PDF (PC)

333

摘要： 碳酸盐岩储层受构造、沉积、古地貌等因素的影响，储层岩性复杂多样，基于测井资料开展岩性的识别在储层评价过程中具有重要意义。针对岩性识别方法存在泛化能力差，难以和地质经验相结合等问题，以苏里格气田苏东41-33区块下古碳酸盐岩储层为例，提出一种基于自组织映射（Self-OrganizingMap，SOM）和模糊识别相结合的岩性识别方法。对岩性较为敏感的声波时差、补偿中子、密度等6种测井参数，采用自组织映射以无监督形式挖掘测井参数的关系信息和拓扑结构，并采用模糊识别方法对自组织映射模型进行局部校正。实际应用结果显示：该方法岩性识别正确率比传统模糊识别方法提高了7.3%，为岩性识别提供了新思路。

关键词: 岩性识别, 自组织映射, 模糊系统, 碳酸盐岩储层

Abstract: Carbonate reservoir is influenced by structure,sedimentation,ancient landform and other factors, which make it become complex and diverse. Therefore,it is significant to identify lithology based on logging data in the process of reservoir assessment. Aim to the problems of the current methods of lithology identification, such as poor generalization ability and the obstacle in combining with geological experience,taking the lower carbonate reservoir in block Sudong 41-33 of Sulige Gas Field as an example,a lithology identification method based on self-organizing map(SOM) and fuzzy recognition was proposed. The SOM was used in unsupervised form to unearth the relationship information and topological structure of six well logging parameters,such as acoustic travel time,compensated neuron and density,which are sensitive to the lithology,and then the SOM model was locally corrected by using fuzzy recognition method. The practical application results show that the lithology identification accuracy of this method was 7.3% higher than that of traditional fuzzy recognition method. It provides a new idea for lithologic identification.

Key words: lithology identification, self-organizing map, fuzzy system, carbonate reservoir

中图分类号: 

  • P618.13
[1] 袁照威,段正军,张春雨,等. 基于马尔科夫概率模型的碳酸盐岩储集层测井岩性解释. 新疆石油地质,2017,38(1):96-102. YUAN Z W,DUAN Z J,ZHANG C Y,et al. Interpretation of logging lithology in carbonate reservoirs based on Markov Chain probability model. Xinjiang Petroleum Geology,2017, 38(1):96-102.
[2] 吴磊,徐怀民,季汉成. 基于交会图和多元统计法的神经网络技术在火山岩识别中的应用. 石油地球物理勘探,2006,41(1):81-86. WU L,XU H M,JI H C. Application of neural network based on crossplot and multivariate statistical method in identification of volcanic rocks. Oil Geophysical Prospecting,2006,41(1):81-86.
[3] 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. 岩性油气藏,2017,29(5):127-133. MA Z,ZHANG C L,GAO S C. Lithology identification based on principal component analysis and fuzzy recognition. Lithologic Reservoirs,2017,29(5):127-133.
[4] MA Y Z. Lithofacies clustering using principal component analysis and neural network:Applications to wireline logs. Mathematical Geosciences,2011,43(4):401-419.
[5] WANG G C,CARR T R,JU Y W,et al. Identifying organicrich marcellus shale lithofacies by support vector machine classifier in the Appalachian Basin. Computers & Geosciences, 2014,64(3):52-60.
[6] CHANG H C,KOPASKA-MERKEL D C,CHEN H C,et al. Lithofacies identification using multiple adaptive resonance theory neural networks and group decision expert system. Computers & Geosciences,2000,26(5):591-601.
[7] 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.
[8] VILALMANN T.Topology preservation in self-organizing maps. Kohonen Maps,1999,27(2):279-292.
[9] FRASER S J,DICKSON B L. A new method for data integration and integrated data interpretation:Self-organizing maps? MILKEREIT B. Proceedings of exploration 07:Fifth decennial international conference on mineral exploration. Torouto:Decennial Mineral Exploration Conference Publisher,2007:907-910.
[10] 许少华,何新贵,李盼池. 自组织过程神经网络及其应用研究. 计算机研究与发展,2003,40(11):1612-1615. XU S H,HE X G,LI P C. Research and applications of self-organization process neural networks. Journal of Computer Research and Development,2003,40(11):1612-1615.
[11] KOHONEN T. Self-organized formation of topologically correct feature maps. Biological Cybernetics,1982,43(1):59-69.
[12] ROY A,MATOS M,MARFURT K J. Automatic seismic facies classification with Kohonen self organizing maps-a tutorial. Geohorizons,2010,1(1):6-14.
[13] 韩波,何治亮,任娜娜. 四川盆地东缘龙王庙组碳酸盐岩储层特征及主控因素. 岩性油气藏,2018,30(1):75-85. HAN B,HE Z L,REN N N. Characteristics and main controlling factors of carbonate reservoirs of Longwangmiao Formation in eastern Sichuan Basin. Lithologic Reservoirs,2018,30(1):75-85.
[14] 田亮,李佳玲,焦保雷. 塔河油田12区奥陶系油藏溶洞充填机理及挖潜方向. 岩性油气藏,2018,30(3):52-60. TIAN L,LI J L,JIAO B L. Filling mechanism and potential tapping direction of Ordovician karst reservoirs in block-12 of Tahe Oilfield. Lithologic Reservoirs,2018,30(3):52-60.
[15] 张䶮,郑晓东,李劲松,等. 基于SOM和PSO的非监督地震相分析技术. 地球物理学报,2015,58(9):3412-3423. ZHANG Y,ZHENG X D,LI J S,et al. Unsupervised seismic facies analysis technology based on SOM and PSO. Chinese Hournal of Geophysics,2015,58(9):3412-3423.
[16] 段林娣,张春雷,王利田,等.储层建模新技术、新方法研究:基于模糊系统的储层建模方法.内蒙古石油化工,2007,32(4):76-79. DUAN L D,ZHANG C L,WANG L T,et al. Research on reservoir model ing based on fuzzy system. Inner Mongolia Petrochemical Industry,2007,32(4):76-79.
[17] RITTER H,MARTINETZ T,SCHULTEN K,et al. Neural computation and self-organizing maps:an introduction. Boston:Addison-Wesley,1993:243-244.
[18] KOSKO B. Fuzzy engineering. Upper Saddle River,NJ:Prentice Hall,1996:35-75.
[19] VESANTO J,AHOLA J. Hunting for correlations in data using the self-organizing map//ROCHESTER N Y. Proceedings of the international ICSC congress on Computational Intelligence Methods and Applications(CIMA'99). Switzerland:ICSC Academic Press,1999:279-285.
[20] 袁照威. 基于机器学习与多信息融合的致密砂岩储层井震解释方法研究.北京:中国地质大学(北京),2017. YUAN Z W. Interpretation methods of tseight sandstone reservoir with seismic data and welllogs based on machine learning method and multi-information fusion. Beijing:China University of Geosciences(Beijing),2017.
[1] 张天择, 王红军, 张良杰, 张文起, 谢明贤, 雷明, 郭强, 张雪锐. 射线域弹性阻抗反演在阿姆河右岸碳酸盐岩气藏储层预测中的应用[J]. 岩性油气藏, 2024, 36(6): 56-65.
[2] 陈叔阳, 何云峰, 王立鑫, 尚浩杰, 杨昕睿, 尹艳树. 塔里木盆地顺北1号断裂带奥陶系碳酸盐岩储层结构表征及三维地质建模[J]. 岩性油气藏, 2024, 36(2): 124-135.
[3] 王亚, 刘宗宾, 路研, 王永平, 刘超. 基于SSOM的流动单元划分方法及生产应用——以渤海湾盆地F油田古近系沙三中亚段湖底浊积水道为例[J]. 岩性油气藏, 2024, 36(2): 160-169.
[4] 宋兴国, 陈石, 杨明慧, 谢舟, 康鹏飞, 李婷, 陈九洲, 彭梓俊. 塔里木盆地富满油田FⅠ16断裂发育特征及其对油气分布的影响[J]. 岩性油气藏, 2023, 35(3): 99-109.
[5] 倪新锋, 沈安江, 乔占峰, 郑剑锋, 郑兴平, 杨钊. 塔里木盆地奥陶系缝洞型碳酸盐岩岩溶储层成因及勘探启示[J]. 岩性油气藏, 2023, 35(2): 144-158.
[6] 宋传真, 马翠玉. 塔河油田奥陶系缝洞型油藏油水流动规律[J]. 岩性油气藏, 2022, 34(4): 150-158.
[7] 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.
[8] 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.
[9] 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.
[10] 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.
[11] 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.
[12] 张大权,邹妞妞,姜 杨,马崇尧,张顺存,杜社宽 . 火山岩岩性测井识别方法研究——以准噶尔盆地火山岩为例[J]. 岩性油气藏, 2015, 27(1): 108-114.
[13] 司马立强,李 清，杨 毅,陈 强 . 用 J 函数法求取碳酸盐岩储层饱和度方法探讨[J]. 岩性油气藏, 2014, 26(6): 106-110.
[14] 石战战，庞溯，唐湘蓉，贺振华. 基于匹配追踪算法的碳酸盐岩储层低频伴影识别方法研究[J]. 岩性油气藏, 2014, 26(3): 114-118.
[15] 王庆如，李敬功. 碳酸盐岩气藏储量参数测井评价方法[J]. 岩性油气藏, 2013, 25(6): 98-102.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 黄思静,黄培培,王庆东,刘昊年,吴　萌,邹明亮. 胶结作用在深埋藏砂岩孔隙保存中的意义[J]. 岩性油气藏, 2007, 19(3): 7 -13 .
[2] 刘震, 陈艳鹏, 赵阳,, 郝奇, 许晓明, 常迈. 陆相断陷盆地油气藏形成控制因素及分布规律概述[J]. 岩性油气藏, 2007, 19(2): 121 -127 .
[3] 丁超，郭兰，闫继福. 子长油田安定地区延长组长6 油层成藏条件分析[J]. 岩性油气藏, 2009, 21(1): 46 -50 .
[4] 李彦山，张占松，张超谟，陈鹏. 应用压汞资料对长庆地区长6 段储层进行分类研究[J]. 岩性油气藏, 2009, 21(2): 91 -93 .
[5] 罗 鹏,李国蓉,施泽进,周大志,汤鸿伟,张德明. 川东南地区茅口组层序地层及沉积相浅析[J]. 岩性油气藏, 2010, 22(2): 74 -78 .
[6] 左国平，屠小龙，夏九峰. 苏北探区火山岩油气藏类型研究[J]. 岩性油气藏, 2012, 24(2): 37 -41 .
[7] 王飞宇. 提高热采水平井动用程度的方法与应用[J]. 岩性油气藏, 2010, 22(Z1): 100 -103 .
[8] 袁云峰，才业，樊佐春，姜懿洋，秦启荣，蒋庆平. 准噶尔盆地红车断裂带石炭系火山岩储层裂缝特征[J]. 岩性油气藏, 2011, 23(1): 47 -51 .
[9] 袁剑英，付锁堂，曹正林，阎存凤，张水昌，马达德. 柴达木盆地高原复合油气系统多源生烃和复式成藏[J]. 岩性油气藏, 2011, 23(3): 7 -14 .
[10] 耿燕飞，张春生，韩校锋，杨大超. 安岳—合川地区低阻气层形成机理研究[J]. 岩性油气藏, 2011, 23(3): 70 -74 .

陇ICP备17006252号
版权所有© 2018 中国石油集团西北地质研究所有限公司《岩性油气藏》编辑部

地址：甘肃省兰州市城关区雁儿湾路535号(陇ICP备17006252号)    电话：0931-8686158;8686058;8686288    邮箱：yxyqc@petrochina.com.cn

甘公网安备 62010202002827号

本系统由北京玛格泰克科技发展有限公司设计开发