鄂尔多斯盆地西缘中段长8油藏低阻成因及人工智能油水识别方法研究与应用

doi:10.3969/j.issn.1672-7703.2025.05.013

摘要/Abstract

摘要： 位于鄂尔多斯盆地西缘的环江—洪德—演武地区普遍发育着中生界延长组长8油藏，该油藏储量巨大，是围绕该区域勘探增储较好的后备潜力资源。但该区长8油层电阻率普遍分布在3～15Ω·m之间、油水层电阻率比小于2，对比度低、识别难度较大，常规测井解释方法识别准确度较低，无法满足高效增储建产的需求。本文结合大量钻井、岩心、三维地震和测井曲线对比分析等资料，从构造演化、矿化特征等，对研究区长8油藏低阻成因进行研究。研究认为鄂尔多斯西缘盆地长8 储层低阻成因主要是高地层水矿化度和高束缚水饱和度。通过采用以人工神经网络模型为基础，以6类关键测井参数为变量，构建了QRw和PC1两项敏感参数，建立机器学习模型，绘制QRw与PC1交会图版，油层、油水同层、水层呈现出良好的分区性，储层流体类型识别精度提高至88.9%。

关键词: 鄂尔多斯盆地；低阻油层；高地层水矿化度；人工神经网络

Abstract: In Huanjiang–Hongde–Yanwu area in the western margin of Ordos Basin, oil reservoirs were widely developed in the eighth member of the Mesozoic Yanchang Formation (Chang 8 member), with huge reserve amount, which is a favorable replacement resource for further exploration and increasing reserves in the region. However, the electrical resistivity of Chang 8 member oil reservoir generally ranges in 3.0–15.0 Ω·m, and the resistivity ratio between oil layer and water layer is lower than 2, showing low contrast ratio, and leading to great difficulty in oil layer identification. The conventional logging interpretation method has a low accuracy, which is unable to meet the needs of high-efficiency reserve increase and capacity construction. Based on a large amount of well drilling, core data, 3D seismic data, and comparative analysis of logging curves, the genesis of Chang 8 member low-resistivity oil reservoir has been studied from the perspectives of structural evolution and mineralization characteristics. The study results indicate that Chang 8 member low-resistivity oil reservoir in the western margin of Ordos Basin was mainly due to high salinity of formation water and high saturation of bound water. By using an artificial neural network model and variables of six key logging parameters, two sensitive parameters have been introduced, i.e., QRw and PC1, and a machine learning model has been established to prepare a cross plot between them, obtaining good distinguishment results among oil layer, oil–water layer, and water layer, with an accuracy of reservoir fluid type recognition improved to 88.9%.

Key words: Ordos Basin; low-resistivity oil layer; high salinity of formation water; artificial neural network

中图分类号:

TE319

杨晨,时建超,陈小东,景文平,张宝娟,谢启超,石坚. 鄂尔多斯盆地西缘中段长8油藏低阻成因及人工智能油水识别方法研究与应用[J]. 中国石油勘探, 2025, 30(5): 171-184.

Yang Chen,Shi Jianchao,hen Xiaodong,Jing Wenping,Zhang Baojuan,Xie Qichao,Shi Jian. Genesis of low-resistivity oil reservoir in the eighth member of Yanchang Formation and research and application of artificial intelligence oil–water identification method in the middle section of the western margin of Ordos Basin[J]. China Petroleum Exploration, 2025, 30(5): 171-184.

参考文献

[1] 付金华，郭正权，邓秀芹. 鄂尔多斯盆地西南地区上三叠统延长组沉积相及石油地质意义[J]. 古地理学报，2005,(1):34-44.
Fu Jinhua, Guo Zhengquan, Deng Xiuqin. Sedimentary facies of the Yanchang Formation of Upper Triassic and petroleum geological implication in southwestern Ordos Basin [J]. Journal of Paleogeography, 2005,(1):34-44.
[2] 杨华，梁晓伟，牛小兵，等. 陆相致密油形成地质条件及富集主控因素：以鄂尔多斯盆地三叠系延长组7 段为例[J]. 石油勘探与开发，2017,44(1):12-20.
Yang Hua, Liang Xiaowei, Niu Xiaobing, et al . Geological conditions and main controlling factors for the formation and enrichment of terrestrial tight oil: taking the 7th member of the Triassic Yanchang Formation in the Ordos Basin as an example [J]. Petroleum Exploration and Development, 2017,44(1):12-20.
[3] 杨华，田景春，夏青松，等. 短期基准面旋回叠加样式与储层物性变化模式关系研究：以陇东地区三叠系延长组长6—长8 油层组为例[J].成都理工大学学报( 自然科学版)，2004(5):478-483.
Yang Hua, Tian Jingchun, Xia Qingsong, et al . Research on the relationship between short term base level cycle overlay patterns and reservoir physical property change patterns: a case study of the Chang 6-Chang 8 oil layers in the Triassic Yanchang Formation of Longdong Area [J]. Journal of Chengdu University of Technology (Science & Technology Edition), 2004(5):478-483.
[4] 赵红格，刘池洋，王峰，等. 鄂尔多斯盆地西缘构造分区及其特征[J].石油与天然气地质，2006(2):173-179.
Zhao Hongge, Liu Chiyang, Wang Feng, et al . Structural zoning and characteristics of the western margin of the Ordos Basin [J]. Oil & Gas Geology, 2006(2):173-179.
[5] 席胜利，李文厚，李荣西. 烃源岩生烃期次与油气成藏：以鄂尔多斯盆地西缘马家滩地区长7 烃源岩为例[J]. 石油勘探与开发，2008,35(6):657-663.
Xi Shengli, Li Wenhou, Li Rongxi. The hydrocarbon generation stages of source rocks and the formation of oil and gas reservoirs: a case study of Chang-7 source rocks in the Majiatan area of the western margin of the Ordos Basin[J]. Petroleum Exploration and Development, 2008,35(6):657-663.
[6] 孙建孟，陈钢花，杨玉征，等. 低阻油气层评价方法[J]. 石油学报，1998(3):95-100.
Sun Jianmeng, Chen Ganghua, Yang Yuzheng, et al . Evaluation method for low resistance oil and gas reservoirs [J]. Acta Petrolei Sinica, 1998 (3): 95-100.
[7] 张冲，毛志强，张超，等. 低阻油层的成因机理及测井识别方法研究[J]. 工程地球物理学报，2008(1):48-53.
Zhang Chong, Mao Zhiqiang, Zhang Chao, et al . Research on the genesis mechanism and logging identification method of low resistivity oil reservoirs [J]. Chinese Journal of Engineering Geophysics, 2008(1):48-53.
[8] 刘威，刘尚，白润才，等. 互学习神经网络训练方法研究[J]. 计算机学报，2017,40(6):1291-1308.
Liu Wei, Liu Shang, Bai Runcai, et al . Research of mutual learning neural networks training method [J]. Chinese Journal of Computers, 2017,40(6):1291-1308.
[9] 刘合. 油气勘探开发数字化转型：人工智能应用大势所趋[J]. 石油科技论坛, 2023, 42(3): 1-9.
Liu He. Digital transformation of oil and gas exploration and development; unstoppable artificial intelligence application[J]. Petroleum Science and Technology Forum, 2023, 42(3): 1-9.
[10]Li Fei , Song Haolan,Wang Yifan . Drilling dynamics measurement of drilling motors and its application in recognition of motor operation states through machine learning[J]. Petroleum, 2024.10(4): 608-619.
[11] 孙龙祥，韩宏伟，冯德永，等. 基于人工智能的测井地层划分方法研究现状与展望[J]. 油气地质与采收率，2023，30（3）：49-58.
Sun Longxiang，Han Hongwei，Feng Deyong，et al. Research status and outlook of logging stratigraphic division methods based on artificial intelligence[J].Petroleum Geology and Recovery Efficiency，2023，30（3）：49-58.
[12]Anand D Kulkarni, Pratiksha D Khurpade, Somnath Nandi. Estimation of SARA composition of crudes purely from density and viscosity using machine learning based models[J]. Petroleum, 2024.10(4): 620-630.
[13] 杨华，付金华，欧阳征健，等. 鄂尔多斯盆地西缘晚三叠世构造—沉积环境分析[J]. 沉积学报，2011,29(3):427-439.
Yang Hua, Fu Jinhua, Ouyang Zhengjian, et al . Analysis of late Triassic structures and sedimentary environment in the western margin of the Ordos Basin [J]. Acta Sedimentologica Sinica, 2011,29(3):427-439.
[14] 王祝文，刘菁华，任莉. 基于K 均值动态聚类分析的地球物理测井岩性分类方法[J]. 东华理工大学学报( 自然科学版)，2009,32(2):152-156.
Wang Zhuwen, Liu Jinghua, Ren Li. Geophysical logging lithology classification method based on K-means dynamic clustering analysis [J]. Journal of East China University of Technology (Natural Science), 2009,32(2):152-156.
[15] 王赛英，赵冠军，张萍，等. 低阻油层形成机理及测井识别方法研究[J]. 特种油气藏，2010,17(4):10-14,120.
Wang Saiying, Zhao Guanjun, Zhang Ping, et al . Research on the Formation Mechanism and Logging Identification Method of Low Resistance Oil Layers [J]. Special Oil & Gas Reservoirs,2010,17(4):10-14,120.
[16] 左银卿，郝以岭，安霞，等. 高束缚水饱和度低阻油层测井解释技术[J]. 西南石油学院学报，2000(2):27-31.
Zuo Yinqing, Hao Yiling, An Xia, et al . Logging interpretation technology for low resistivity oil reservoirs with high bound water saturation [J]. Journal of Southwest Petroleum Institute, 2000(2):27-31.
[17] 赵虹, 党犇, 姚泾利，等. 鄂尔多斯盆地姬塬地区延长组长2 低阻油层成因机理[J]. 石油实验地质，2009,31(6):588-592.
Zhao Hong, Dang Ben, Yao Jingli, et al . The genesis mechanism of the Chang 2 low resistivity oil reservoir in the Jiyuan area of the Ordos Basin [J]. Petroleum Geology & Experiment, 2009,31(6):588-592.
[18] 李国欣，欧阳健，周灿灿，等. 中国石油低阻油层岩石物理研究与测井识别评价技术进展[J]. 中国石油勘探，2006(2):43-50,72.
Li Guoxin, Ouyang Jian, Zhou Cancan, et al . Progress in rock physics research and logging identification and evaluation technology for low resistivity oil reservoirs in China Petroleum[J]. China Petroleum Exploration, 2006(2):43-50,72.
[19] 赵军龙，李甘，朱广社，等. 低阻油层成因机理及测井评价方法综述[J]. 地球物理学进展，2011,26(4):1334-1342.
Zhao Junlong, Li Gan, Zhu Guangshe, et al . A review of the genesis mechanism and logging evaluation methods of low resistivity oil reservoirs [J]. Progress in Geophysics, 2011,26(4):1334-1342.
[20] 印森林，陈旭，杨毅，等. 细粒沉积岩典型低阻油层成因及甜点分布[J]. 石油与天然气地质，2023,44(4):946-961.
Yin Senlin, Chen Xu, Yang Yi, et al . The genesis and sweet spot distribution of typical low resistivity oil reservoirs in finegrained sedimentary rocks [J]. Oil & Gas Geology, 2023,44(4):946-961.
[21] 翟利华，林艳波，秦智，等. 鄂尔多斯盆地姬塬地区延长组长4+5 低阻油层成因及识别方法[J]. 油气地质与采收率，2018,25(2):50-57.
Zhai Lihua, Lin Yanbo, Qin Zhi, et al . Genetic mechanism and identification methods of low resistivity oil reservoirs in Chang4+5 member of Yanchang Formation in Jiyuan area，Ordos Basin [J]. Petroleum Geology and Recovery Efficiency,2018,25(2):50-57.
[22] 王海更，张博文，张俊.L 油田低阻油层成因分析及挖潜研究[J]. 石化技术，2024,31(12):220-222.
Wang Haigeng, Zhang Bowen, Zhang Jun. Genetic analysis and potential research of low resistance oil reservoirs in Bohai L oilfield [J]. Petrochemical Industry Technology, 2024,31(12):220-222.
[23] 李晓峰，刘光中. 人工神经网络BP 算法的改进及其应用[J]. 四川大学学报( 工程科学版)，2000(2):105-109.
Li Xiaofeng, Liu Guangzhong. Improvement and application of artificial neural network BP algorithm [J]. Journal of Sichuan University (Engineering Science Edition), 2000(2):105-109.
[24] 杨庆军，邓春呈，杨永利，等. 人工神经网络在低阻油层识别上的应用[J]. 特种油气藏，2001(2):8-10,104.
Yang Qingjun, Deng Chuncheng, Yang Yongli, e t a l . Application of artificial neural networks in identification of low resistance oil layers [J]. Special Oil & Gas Reservoirs,2001(2):8-10,104.
[25] 于红岩，李洪奇，郭兵，等. 基于成因机理的低阻油层精细评价方法[J]. 吉林大学学报( 地球科学版)，2012,42(2):335-343.
Yu Hongyan, Li Hongqi, Guo Bing, et al . Fine evaluation method for low resistivity oil reservoirs based on genesis mechanism [J]. Journal of Jilin University (Earth Science Edition), 2012,42(2):335-343.