基于支持向量机的浊积扇低渗透储层流动单元研究

doi:10.13278/j.cnki.jjuese.20170168

吉林大学学报(地球科学版) ›› 2018, Vol. 48 ›› Issue (5): 1330-1341.doi: 10.13278/j.cnki.jjuese.20170168

基于支持向量机的浊积扇低渗透储层流动单元研究

徐守余^1,2, 路研^1,2, 王亚^1,2

1. 中国石油大学(华东)地球科学与技术学院, 山东青岛 266580;
2. 海洋国家实验室海洋矿产资源评价与探测技术功能实验室, 山东青岛 266071

收稿日期:2018-01-19 出版日期:2018-09-26 发布日期:2018-11-20
通讯作者: 路研(1992-),女,博士研究生,主要从事油气储层地质学及油藏描述研究,E-mail:wangyayifan@163.com E-mail:wangyayifan@163.com
作者简介:徐守余(1968-),男,教授,博士生导师,主要从事油气储层地质学及油藏描述研究,E-mail:xushouyu@upc.edu.cn
基金资助:
国家科技重大专项（2017ZX05009001）；国家自然科学基金面上项目（41772138）

Study on Flow Units of Turbidite Fan Low Permeability Reservoir Based on Support Vector Machine

Xu Shouyu^1,2, Lu Yan^1,2, Wang Ya^1,2

1. School of Geosciences, China University of Petroleum(East China), Qingdao 266580, China;
2. Laboratory for Marine Mineral Resources, Qingdao National Laboratory for Marine Science and Technology, Qingdao 266071, Shandong, China

Received:2018-01-19 Online:2018-09-26 Published:2018-11-20
Supported by:
Supported by National Science and Technology Major Project (2017ZX05009001) and National Natural Science Foundation of China(41772138)

摘要/Abstract

摘要： 由于浊积扇储层成因机制的复杂性，本文通过因子分析从反映储层岩石物理特征、微观孔隙结构特征、储层沉积特征及储层非均质特征的13个储层参数中提取了5个主因子，并以此作为预测模型的输入，采用支持向量机的算法来建立流动单元预测模型。应用该模型对大芦湖油田樊29块10口关键井的预测样本进行检验，正判率达90.38%。运用建立的预测模型对研究区4^4¹单砂层流动单元进行划分，将预测结果与定性分析结果对比，具有较高的吻合度。平面上，流动单元划分结果与沉积微相展布具有较高的对应关系：Ⅰ类、Ⅱ类流动单元储层质量最好，仅在浊积水道及朵叶体微相发育；Ⅲ类流动单元分布广泛，在浊积水道、水道侧缘及中扇侧缘微相均有分布；Ⅳ类流动单元主要分布在浊积扇外缘的扇缘亚相。结果表明，建立的流动单元模型能够较为系统地反映多种地质因素与流动性能之间的复杂映射规律。

关键词: 浊积扇, 流动单元, 因子分析, 支持向量机, 储层, 大芦湖油田

Abstract: Due to the complexity of the formation mechanism of the turbidite reservoir, five principal factors were extracted through analysis on 13 parameters for reflecting the petrophysical, microscopic pore structural, sedimentary and heterogeneity characteristics of the reservoir. Then using the five principal factors as the input,the flow unit prediction model was established based on the support vector machine method. The model was used to test the predicting samples in Fan 29 block of Daluhu oilfield,and the accuracy rate of the results reached 90.38%.With the established prediction model, the flow unit of the single sand bed 4^4¹ in the study area was classified and evaluated, the prediction results were highly consistent with the qualitative analysis results. The flow unit classification well corresponded to the distribution of the sedimentary microfacies as the follows:the I-type and Ⅱ-type flow-units are the best quality reservoirs,that are developed only in the turbidity channel and lobe;the flow-unit of Ⅲ-type is widely distributed in the turbidity channel, channel edge,and the edge of middle fan;and the flow-unit IV is distributed in the edge of the fan. The studies suggest that the prediction model of flow units can be more comprehensive in consideration with the complex mapping relationship between the various geological factors and the flow units.

Key words: turbidite fan, flow units, factor analysis, support vector machine, reservoir, Daluhu oilfield

中图分类号:

TE122.2

徐守余, 路研, 王亚. 基于支持向量机的浊积扇低渗透储层流动单元研究[J]. 吉林大学学报(地球科学版), 2018, 48(5): 1330-1341.

Xu Shouyu, Lu Yan, Wang Ya. Study on Flow Units of Turbidite Fan Low Permeability Reservoir Based on Support Vector Machine[J]. Journal of Jilin University(Earth Science Edition), 2018, 48(5): 1330-1341.

参考文献

[1] 宁正福,赵洋,程林松. 基于因子分析的流动单元研究[J]. 中国石油大学学报:自然科学版,2012,36(4):107-111,117. Ning Zhengfu, Zhao Yang, Cheng Linsong. Study on Flow Units Based on Factor Analysis[J]. Journal of China University of Petroleum, 2012, 36(4):107-111, 117.
[2] 熊文涛,师永民,刘新菊,等. 致密砂岩储层流动单元研究:以鄂尔多斯盆地延长组长6¹油层为例[J].北京大学学报(自然科学版),2014,50(2):288-294. Xiong Wentao, Shi Yongmin, Liu Xinju, et al. Study on Flow Unit of Tight Sandstone Reservoir:A Case of Yanchang Formation Chang-6¹ Resrvoir in Erdos Basin[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2014, 50(2):288-294.
[3] 王亚,杨少春,路研,等. 基于测井岩石物理相识别的低渗透储层评价方法:以东营凹陷高青地区蒙阴组上段为例[J]. 中国矿业大学学报,2018,47(6):1388-1399. Wang Ya, Yang Shaochun, Lu Yan, et al. Evaluation Method of Low Permeability Reservoirs Based on Logging Petrophysical Facies Identification:A Case Study of the Upper Member of Mengyin Formation in Gaoqing Area, Dongying Depression[J]. Journal of China University of Mining & Technology, 2018, 47(6):1388-1399.
[4] Yin T J, Zhang C M, Zhang S F, et al. Estimation of Reservoir and Remaining Oil Prediction Based on Flow Unit Analysis[J]. Earth Science, 2009, 52(Sup. I):120-127.
[5] 范子菲,李孔绸,李建新,等. 基于流动单元的碳酸盐岩油藏剩余油分布规律[J].石油勘探与开发,2014,41(5):578-584. Fan Zifei, Li Kongchou, Li Jianxin, et al. A Study on Remaining Oil Distribution in a Carbonate Oil Reservoir Based on Reservoir Flow Units[J]. Petroleum Exploration and Development, 2014, 41(5):578-584.
[6] 苗长盛,董清水,张旗,等. 储层流动单元研究在油田老区挖潜中的应用:以吉林油田乾146区块开发为例[J]. 吉林大学学报(地球科学版),2011,41(1):39-45. Miao Changsheng, Dong Qingshui, Zhang Qi, et al. Application of Reservoir Flow Unit in Potential Finding of Developed Reservoir:A Case Study on Exploitation of Block Qian-146 in Jilin Oil Field, NE China[J]. Journal of Jilin University (Earth Science Edition), 2011, 41(1):39-45.
[7] Hearn C L, Ebanks W J, Tye R S, et al. Geological Factors Influencing Reservoir Performance of the Hartzog Draw Field[J]. Wyoming JPT, 1984, 36(9):1335-1344.
[8] Ebanks W J Jr. Flow Unit Concept Integrated App-roach to Reservoir Description for Engineering Projects[J]. AAPG Bulletin, 1987, 71(5):551-552.
[9] Rodriguez A. Facies Modeling and the Flow Unit Concept as a Sedimentological Tool in Reservoir Description:A Case Study[C]//SPE Annual Technical Conference and Exhibition. Houston:Society of Petroleum Engineers of AIME, 1988:465-472.
[10] Mahjour S K, Al-Askari M K G, Masihi M. Iden-tification of Flow Units Using Methods of Testerman Statistical Zonation, Flow Zone Index, and Cluster Analysis in Tabnaak Gas Field[J]. Journal of Petroleum Exploration & Production Technology, 2016, 6(4):577-592.
[11] 朱怡翔,石广仁. 火山岩岩性的支持向量机识别[J].石油学报,2013,34(2):312-322. Zhu Yixiang, Shi Guangren. Identification of Lithologic Characteristics of Volcanic Rocks by Support Vector Machine[J]. Acta Petrolei Sinica, 2013, 34(2):312-322.
[12] 牟丹,王祝文,黄玉龙,等. 基于最小二乘支持向量机测井识别火山岩类型:以辽河盆地中基性火山岩为例[J].吉林大学学报(地球科学版),2015,45(2):639-648. Mou Dan, Wang Zhuwen, Huang Yulong, et al. Application of Least Squares Support Vector Machine to Lithology Identification:Taking Intermediate/Basaltic Rocks of Liaohe Basin as an Example[J]. Journal of Jilin University (Earth Science Edition),2015,45(2):639-648.
[13] 王常明,田书文,王翊虹,等. 泥石流危险性评价:模糊c均值聚类-支持向量机法[J]. 吉林大学学报(地球科学版),2016,46(4):1168-1175. Wang Changming, Tian Shuwen, Wang Yihong, et al. Risk Assessment of Debris Flow:A Method of SVM Based on FCM[J]. Journal of Jilin University (Earth Science Edition), 2016, 46(4):1168-1175.
[14] 韩祥磊,王文林,孙红蕾. 博兴洼陷沙三段沉积体系探讨[J]. 油气地质与采收率,2003,8(10):7-18. Han Xianglei, Wang Wenlin, Sun Honglei. Discussion on Sedimentary System of the Es₃ Formation in Boxing Sag[J]. Petroleum Geology and Recovery Efficiency, 2003, 8(10):7-18.
[15] 王志章,何刚. 储层流动单元划分方法与应用[J]. 天然气地球科学,2010,21(3):362-366. Wang Zhizhang, He Gang. The Classification Method and Application of Reservoir Flow Units[J]. Natural Gas Geoscience, 2010, 21(3):362-366.
[16] 郑香伟,吴健,何胜林,等. 基于流动单元的砂砾岩储层渗透率测井精细评价[J]. 吉林大学学报(地球科学版),2016,46(1):286-294. Zheng Xiangwei, Wu Jian, He Shenglin, et al. Fine Evaluation of Permeability of Conglomerate Reservoir Based on Flow Unit[J]. Journal of Jilin University (Earth Science Edition), 2016, 46(1):286-294.
[17] Davis J C. Statistical and Data Analysis in Geology[M]. 2nd ed. New York:John Wiley & Sons, 1986:646.
[18] 赵少卿,魏俊浩,高翔,等. 因子分析在地球化学分区中的应用:以内蒙古石板井地区1:5万岩屑地球化学测量数据为例[J].地质科技情报,2012,31(2):27-34. Zhao Shaoqing, Wei Junhao, Gao Xiang, et al. Factor Analysis in the Geochemical Subdivisions:Taking 1:50000 Debris Geochemical Survey in the Shibanjing Area of Inner Mongolia as an Example[J]. Geological Science and Technology Information, 2012, 31(2):27-34.
[19] Vapnik V N. 统计学习理论的本质[M]. 张学工,译. 北京:清华大学出版社,2000:85-205. Vapnik V N. The Nature of Statistical Learning Theory[M]. Translated by Zhang Xuegong. Beijing:Tsinghua University Press, 2000:85-205.
[20] 卢文喜,郭家园,董海彪,等. 改进的支持向量机方法在矿山地质环境质量评价中的应用[J]. 吉林大学学报(地球科学版),2016,46(5):1511-1519. Lu Wenxi, Guo Jiayuan, Dong Haibiao, et al. Evaluating Mine Geology Environmental Quality Using Improved SVM Method[J]. Journal of Jilin University (Earth Science Edition), 2016, 46(5):1511-1519.
[21] 陈科贵,吴刘磊,陈愿愿,等. 基于支持向量机的川中杂卤石分类识别研究[J]. 地球科学进展,2016,31(10):1041-1046. Chen Kegui, Wu Liulei, Chen Yuanyuan, et al. Classification and Recognition of Polyhalite in Chuanzhong Based on Support Vector Machine[J]. Advances in Earth Science, 2016, 31(10):1041-1046.
[22] 孙致学,姚军,孙治雷,等. 基于神经网络的聚类分析在储层流动单元划分中的应用[J]. 物探与化探,2011, 35(3):249-353. Sun Zhixue, Yao Jun, Sun Zhilei, et al. The Application of Clustering Analysis Based on Neural Network Technology in Reservoir Flow Unit Classification[J]. Geophysical & Geochemical Exploration, 2011, 35(3):249-353.
[23] 万琼华,吴胜和,王石,等. 深水浊积水道储层多参数流动单元划分方法及其分布规律研究[J]. 高校地质学报,2014,20(2):317-323. Wan Qionghua, Wu Shenghe, Wang Shi, et al. Multi-Parameter Technology on the Study of Flow Units Division and Their Distribution in Deep-Water Turbidity Channel Reservoir[J]. Geological Journal of China Universities, 2014, 20(2):317-323.
[24] 吴小斌, 侯加根, 孙卫, 等. 基于层次分析方法对姬塬地区流动单元的研究[J]. 吉林大学学报(地球科学版), 2011, 41(4):1013-1019. Wu Xiaobin, Hou Jiagen, Sun Wei, et al. Study on Flow-Units Based on Hierarchical Analysis in Jiyuan Area, Ordos Basins[J]. Journal of Jilin University (Earth Science Edition), 2011, 41(4):1013-1019.
[25] 唐民安,李建明,孙宝玲,等. 鄂尔多斯盆地红河油田长8油层组储层流动单元研究[J]. 地质科技情报,2014,33(6):83-87. Tang Min'an, Li Jianming, Sun Baoling, et al. Reservoir Flow Units of Chang-8 Oil-Bearing Formation in Honghe Oilfield, Ordos Basin[J]. Geological Science and Technology Information, 2014, 33(6):83-87.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于支持向量机的浊积扇低渗透储层流动单元研究

Study on Flow Units of Turbidite Fan Low Permeability Reservoir Based on Support Vector Machine

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]	唐华风, 张亚东, 邹明倬, 陆国超, 户景松, 张津铭, 卞海越. 渤海湾盆地莱州湾凹陷K油田中生界火山岩储层定量评价[J]. 吉林大学学报(地球科学版), 2026, 56(3): 739-753.
[2]	李冠, 何文祥, 文志刚, 胡勇, 高小洋, 肖娜. 鄂尔多斯盆地陇东地区长71-2亚段不同源储组合的页岩油富集机理及富集模式[J]. 吉林大学学报(地球科学版), 2026, 56(3): 768-787.
[3]	陈泽熙, 徐志明, 李斌, 钟笠, 彭军, 张昆, 魏祥峰, 郝景宇. 基质型页岩甜点特征及评价方法：以四川盆地涪陵地区中侏罗统凉高山组陆相页岩为例[J]. 吉林大学学报(地球科学版), 2026, 56(3): 788-803.
[4]	王蓓东, 杨胜来 , 赵帅 , 邓惠 , 张钰祥 , 白浩言, 李沁怡, 姜艺. 高磨地区震旦系灯影组四段台内储层储集空间类型及其孔喉结构特征[J]. 吉林大学学报(地球科学版), 2026, 56(3): 804-817.
[5]	夏英杰, 陈华斌, 陈健, 姚明宇, 杨海. 不同施工参数下深层页岩水力压裂数值模拟[J]. 吉林大学学报(地球科学版), 2026, 56(3): 924-936.
[6]	张恩威, 孟庆涛, 唐佰强, 胡菲, 党微. 基于机器学习的TOC测井预测方法：以松辽盆地南部青山口组一段为例[J]. 吉林大学学报(地球科学版), 2026, 56(3): 1062-1075.
[7]	丁梦颜, 冯晅, 刘财. 裂缝对岩石非线性弹性特征的影响[J]. 吉林大学学报(地球科学版), 2026, 56(3): 1051-1061.
[8]	刘涛, 刘宗堡, 张可佳, 张岩, 张瑞雪, 刘晓文, 徐翠云. 基于深度学习的致密砂岩储层薄片图像生成与识别方法 [J]. 吉林大学学报(地球科学版), 2026, 56(2): 724-738.
[9]	周三栋, 张伟鑫, 成巧耘, 魏佳成, 周国栋, . 深部煤储层中煤层水可动性评价方法及动力学机制研究进展[J]. 吉林大学学报(地球科学版), 2026, 56(2): 397-412.
[10]	王健, 张媛瑗, 吴楠, 徐清海, 崔子岳, 刘显凤, 付清萌. 鄂尔多斯盆地志靖—安塞地区长7段夹层型页岩油储层特征及分类评价[J]. 吉林大学学报(地球科学版), 2026, 56(2): 453-468.
[11]	王振军. 油气储层裂缝预测进展[J]. 吉林大学学报(地球科学版), 2026, 56(2): 469-482.
[12]	黄玉龙, 张皓, 郭强, 陈昌. 低阻玄武岩的矿物学特征及其油气地质意义——以辽河坳陷古近系为例 [J]. 吉林大学学报(地球科学版), 2026, 56(2): 511-521.
[13]	唐华风, 付琦, 尹永康, 高有峰, 户景松, 武海超, 田志文. 花岗岩潜山储层地质研究回顾[J]. 吉林大学学报(地球科学版), 2025, 55(6): 1806-1836.
[14]	杨兰, 王运, 邹勇军, 胡宝群, 李满根, 张安, 朱满怀. 基于机器学习的富硒土壤预测模型的构建与比较——以江西省信丰县油山地区为例[J]. 吉林大学学报(地球科学版), 2025, 55(5): 1629-1643.
[15]	王伟明, 胡美硕, 焦立新, 杨斌, 苗长盛, 孙宏亮, 周志超, 曲希玉, . 三塘湖盆地下石炭统新层系石油地质条件及勘探潜力 [J]. 吉林大学学报(地球科学版), 2025, 55(5): 1401-1419.