岩性油气藏 ›› 2026, Vol. 38 ›› Issue (2): 153–161.doi: 10.12108/yxyqc.20260214

• 地质勘探 • 上一篇    下一篇

基于白鲸算法的致密砂砾岩储层测井最优化评价

庞志超1(), 张奔2(), 党宛笛2, 高明1, 毛晨飞2, 陈国军1   

  1. 1 中国石油新疆油田公司 勘探开发研究院， 乌鲁木齐 830013
    2 中国石油集团测井有限公司 地质研究院， 西安 710021
  • 收稿日期:2024-11-21 修回日期:2024-12-21 出版日期:2026-03-01 发布日期:2025-12-03
  • 第一作者:庞志超（1985—），男，硕士，高级工程师，主要从事石油地质综合研究工作。地址：（830013）新疆维吾尔自治区乌鲁木齐市新市区北京北路397号。Email:pzhichao@petrochina.com.cn。
  • 通信作者: 张奔（1995—），男，硕士，工程师，主要从事复杂储层测井解释及评价工作。Email:zhben105@126.com。
  • 基金资助:
    中国石油天然气股份有限公司重大科技专项“致密砾岩储层分类评价及甜点区预测技术研究”(2023ZZ24YJ02)

Optimized logging interpretation for tight glutenite reservoir based on beluga whale algorithm

PANG Zhichao1(), ZHANG Ben2(), DANG Wandi2, GAO Ming1, MAO Chenfei2, CHEN Guojun1   

  1. 1 Research Institute of Exploration and Development, Xinjiang Oilfield Company, PetroChina, Urumqi 830013, China
    2 Geological Research Institute, China National Logging Company, Xi’an 710021, China
  • Received:2024-11-21 Revised:2024-12-21 Online:2026-03-01 Published:2025-12-03

RichHTML

0

PDF (PC)

9

摘要：

为了解决深层砂砾岩储层矿物组分含量和孔隙度计算难度大的问题，以准噶尔盆地南缘白垩系清水河组致密砂砾岩储层为例，提出了一种基于白鲸智能算法（BWO）的测井最优化解释方法，该方法的计算结果与岩心的实验室分析数据吻合度更高。研究结果表明：①基于BWO的储层测井最优化评价的思路为，综合岩心资料、岩石薄片资料及扫描电镜资料，建立研究区多组分体积物理模型；基于常规测井资料建立测井响应方程，并以BWO进行求解；以最小二乘法为基础理论，结合多组体积物理模型和测井响应方程建立最优化测井目标函数。②该方法具有优异的全局和局部搜索能力，收敛速度快，计算精度高，可扩展性大；测试模拟结果显示，该方法反演测井曲线时，目标函数在迭代40次左右时趋于平稳，计算的各组分含量与构造的对应组分含量相关性较好，平均绝对误差都低于1.50%，平均相对误差都低于11.50%。③准噶尔盆地南缘深层砂砾岩储层矿物成分主要为石英、长石、方解石、白云石和黏土，基于BWO的测井最优化解释方法计算出的各矿物组分含量与实测岩心数据的绝对误差都小于3.00%，孔隙度绝对误差为0.26%，预测效果明显优于常规方法。

关键词: 白鲸算法, 致密砂砾岩储层, 多矿物体积物理模型, 最优化测井解释, 地球物理反演, 清水河组, 白垩系, 准噶尔盆地南缘

Abstract:

To address the challenges of determining mineral composition and improving porosity estimation in deep glutenite reservoirs, taking the tight glutenite reservoirs of Cretaceous Qingshuihe Formation in the southern margin of Junggar Basin as an example, an optimized logging interpretation method based on the beluga whale optimization (BWO) algorithm was proposed, and the computational results of this method demonstrate higher consistency with the laboratory analysis data of core samples. The results show that: （1） The process of BWO-based optimized logging interpretation for reservoirs is as follows: By integrating data of core, thin section, and scanning electron microscopy, a multi-composition volumetric physical model of the study area is established; based on conventional logging data, a logging response equation is established and then solve it with BWO algorithm; with the least squares method as the basic theory, an optimized logging objective function is established by combining multiple volumetric physical model and logging response equation. （2） The proposed method demonstrates excellent global and local search capabilities, fast convergence, high computational accuracy, and strong scalability. Test simulations showed that the objective function stabilizes after approximately 40 iterations during logging curve inversion. The calculated mineral contents show good correlation with actual data, with mean absolute errors below 1.50% and mean relative errors below 11.50%. （3） The primary minerals of deep glutenite reservoir in the southern margin of Junggar Basin are quartz, feldspar, calcite, dolomite, and clay. The absolute errors for mineral content and porosity calculated by the BWO-based optimized logging interpretation method and the measured core data are less than 3.00% and 0.26%, respectively, significantly outperforming conventional methods.

Key words: beluga whale optimization algorithm, tight glutenite reservoir, multi-mineral volumetric physical model, optimal logging interpretation, geophysical inversion, Qingshuihe Formation, Cretaceous, southern margin of Junggar Basin

中图分类号: 

  • TE122

图1

准噶尔盆地南缘白垩系清水河组砂砾岩储层岩性特征 （a） 粉砂岩，GHW001井，5 823.1 m；（b） 中细砂岩，H102井，7 430.3 m；（c） 细砾岩，GQ5井，6 051.3 m；（d） 中砾岩，GHW001井，5 829.0 m；（e） 粒间孔、粒内溶孔和泥质中微孔的体积占比分别为80%，15%和5%，G101井，6 022.1 m；（f） 粒间片状伊利石与似蜂巢状伊蒙混层矿物，GQ5井，6 060.1 m；（g） 复成分砂质细砾岩，G101井，6 196.3 m；（h） 复成分砂质细—中砾岩，GQ101井，6 017.7 m；（i） 复成分砂质细砾岩，GQ101井，6 019.4 m。"

图2

准噶尔盆地南缘白垩系清水河组砂砾岩储层岩石组分饼状图"

图3

准噶尔盆地南缘白垩系清水河组砂砾岩储层黏土矿物组分含量直方图"

图4

准噶尔盆地南缘白垩系清水河组砂砾岩储层多组分体积物理模型"

图5

应用BWO处理时目标函数随迭代次数变化曲线"

图6

基于BWO的测井最优化解释方法反演的参数与构造的参数交会结果 注：ϕ(矿物成分)反演和ϕ(矿物成分)构造分别为反演计算和构造的矿物成分体积分数，%；POR反演和POR构造分别为反演计算和构造的孔隙度，%。"

表1

基于BWO的测井最优化解释方法反演的储层参数误差统计"

储层参数 ϕ(石英) ϕ(长石) ϕ(方解石) ϕ(白云石) ϕ(黏土) 孔隙度
平均绝对
误差/%		 1.41 0.91 0.68 0.51 0.55 0.56
平均相对
误差/%		 3.08 2.32 9.81 6.09 7.87 11.42

图7

基于BWO的测井最优化解释方法流程 注：①.探索阶段；②.开发阶段；③.鲸落阶段。"

表2

准噶尔盆地南缘清水河组致密砂砾岩储层矿物骨架成分和孔隙流体测井响应特征值"

储层组分 GR/API DEN/(g·cm-3) AC/(μs·m-1) CNL/%
石英 12.0 2.65 182 -2
长石 56.8 2.55 200 -3
方解石 10.0 2.71 155 0
白云石 15.0 2.88 142 2
黏土 260.0 2.50 328 36
孔隙 0 1.00 620 100

图8

准噶尔盆地南缘G1井清水河组致密砂砾岩储层基于BWO的最优化测井解释成果"

表3

准噶尔盆地南缘G1井清水河组致密砂砾岩储层基于BWO与传统最优化方法计算储层参数效果对比"

最优化方法 绝对误差/%
ϕ(石英) ϕ(长石) ϕ(白云石) ϕ(方解石) ϕ(黏土) 孔隙度
BWO
最优化		 2.31 2.94 0.18 1.18 0.72 0.26
常规
最优化		 5.54 6.12 1.98 3.29 4.83 1.13

图9

准噶尔盆地南缘G2井白垩系清水河组致密砂砾岩储层基于BWO的测井最优化解释成果"

[1] 卞保力, 刘海磊, 蒋文龙, 等. 准噶尔盆地盆1井西凹陷石炭系火山岩凝析气藏的发现与勘探启示[J]. 岩性油气藏, 2024, 36(3):96-105.
doi: 10.12108/yxyqc.20240309
BIAN Baoli, LIU Hailei, JIANG Wenlong, et al. Discovery and exploration enlightenment of Carboniferous volcanic condensate gas reservoirs in western well Pen-1 Sag,Junggar Basin[J]. Lithologic Reservoirs, 2024, 36(3):96-105.
doi: 10.12108/yxyqc.20240309
[2] 赵军, 李勇, 文晓峰, 等. 基于斑马算法优化支持向量回归机模型预测页岩地层压力[J]. 岩性油气藏, 2024, 36(6):12-22.
doi: 10.12108/yxyqc.20240602
ZHAO Jun, LI Yong, WEN Xiaofeng, et al. Prediction of shale formation pore pressure based on Zebra Optimization Algorithm-optimized support vector regression[J]. Lithologic Reservoirs, 2024, 36(6):12-22.
[3] 雍世和, 孙建孟. 测井数字处理中最优化方法的选择[J]. 中国石油大学学报, 1988, 12(增刊1):11-26.
YONG Shihe, SUN Jianmeng. Selection of optimization methods in digital logging processing[J]. Journal of China University of Petroleum, 1988, 12 (Suppl 1):11-26.
[4] 李宁, 徐彬森, 武宏亮, 等. 人工智能在测井地层评价中的应用现状及前景[J]. 石油学报, 2021, 42(4):508-522.
doi: 10.7623/syxb202104008
LI Ning, XU Binsen, WU Hongliang, et al. Application status and prospects of artificial intelligence in well logging and formation evaluation[J]. Acta Petrolei Sinica, 2021, 42(4):508-522.
doi: 10.7623/syxb202104008
[5] 陈康, 戴隽成, 魏玮, 等. 致密砂岩AVO属性的贝叶斯岩相划分方法:以川中侏罗系沙溪庙组沙一段为例[J]. 岩性油气藏, 2024, 36(5):111-121.
doi: 10.12108/yxyqc.20240511
CHEN Kang, DAI Juncheng, WEI Wei, et al. Lithofacies classification of tight sandstone based on Bayesian Facies-AVO attributes:A case study of the first member of Jurassic Shaximiao Formation in central Sichuan Basin[J]. Lithologic Reservoirs, 2024, 36(5):111-121.
doi: 10.12108/yxyqc.20240511
[6] 韩雪, 潘保芝, 张意, 等. 遗传最优化算法在砂砾岩储层测井评价中的应用[J]. 测井技术, 2012, 36(4):392-396.
HAN Xue, PAN Baozhi, ZHANG Yi, et al. GA-Optimal log interpretation applied in glutenite reservoir evaluation[J]. Well Logging Technology, 2012, 36(4):392-396.
[7] 徐苗苗, 印兴耀, 宗兆云. 基于复合蛙跳算法的火山岩最优化测井解释方法[J]. 石油物探, 2020, 59(1):122-130.
doi: 10.3969/j.issn.1000-1441.2020.01.014
XU Miaomiao, YIN Xingyao, ZONG Zhaoyun. Logging interpretation optimization of volcanic rocks using the complex frog-leaping algorithm[J]. Geophysical Prospecting for Petroleum, 2020, 59(1):122-130.
doi: 10.3969/j.issn.1000-1441.2020.01.014
[8] 孙茹雪, 潘保芝, 石玉江, 等. 人工蜂群最优化测井解释方法在致密砂岩储层评价中的应用[J]. 测井技术, 2017, 41(3):320-324.
SUN Ruxue, PAN Baozhi, SHI Yujiang, et al. Application of artificial bee colony optimization log interpretation method to tight sandstone reservoir evaluation[J]. Well Logging Technology, 2017, 41(3):320-324.
[9] 陈愿愿, 杨晓, 邓小江, 等. 海鸥优化算法在四川盆地渝西区块H井区页岩气储层最优化测井解释中的应用[J]. 地球科学进展, 2020, 35(7):761-768.
doi: 10.11867/j.issn.1001-8166.2020.046
CHEN Yuanyuan, YANG Xiao, DENG Xiaojiang, et al. Application of seagull optimization algorithm log interpretation to shale gas reservoir of Well H in Sichuan Basin Yuxi Block[J]. Advances in Earth Science, 2020, 35(7):761-768.
doi: 10.11867/j.issn.1001-8166.2020.046
[10] ZHONG Changting, LI Gang, MENG Zeng. Beluga whale optimization:A novel nature-inspired metaheuristic algorithm[J]. Knowledge-Based Systems, 2022, 251:109215.
doi: 10.1016/j.knosys.2022.109215
[11] HASSAN M H, KAMEL S, JURADO F, et al. Economic load dispatch solution of large-scale power systems using an enhanced beluga whale optimizer[J]. Alexandria Engineering, 2023, 72:573-591.
[12] 孟冠军, 黄江涛, 魏亚博. 混合白鲸优化算法求解柔性作业车间调度问题[J]. 计算机工程与应用, 2024, 60(12):325-333.
doi: 10.3778/j.issn.1002-8331.2307-0216
MENG Guanjun, HUANG Jiangtao, WEI Yabo. Hybrid beluga whale optimization algorithm for flexible job shop scheduling problem[J]. Computer Engineering and Applications, 2024, 60(12):325-333.
doi: 10.3778/j.issn.1002-8331.2307-0216
[13] 蔡海良, 胡凯, 李军, 等. 基于BWO-ELM算法与VR-GIS技术的电力光缆故障诊断及定位研究[J]. 计算机测量与控制, 2022, 30(12):98-104.
CAI Hailiang, HU Kai, LI Jun, et al. Research on fault diagnosis and location of power optical cable based on BWO-ELM algorithm and VR-GIS technology[J]. Computer Measurement and Control, 2022, 30(12):98-104.
[14] 朱菊香, 谷卫, 钱炜, 等. 基于IF-SVMD-BWO-LSTM的空气质量预测建模[J]. 中国测试, 2024, 50(11):173-184.
ZHU Juxiang, GU Wei, QIAN Wei, et al. Modeling of air quality prediction based on IF-SVMD-BWO-LSTM[J]. China Measurement & Test, 2024, 50(11):173-184.
[15] 胡心玲, 荣焕青, 杨伟, 等. 东营凹陷八面河地区古近系沙四段湖相白云岩测井识别及应用[J]. 岩性油气藏, 2025, 37(1):13-23.
doi: 10.12108/yxyqc.20250102
HU Xinling, RONG Huanqing, YANG Wei, et al. Logging identification and application of lacustrine dolomite in the fourth member of the Shahejie Formation in the Bamianhe area of Dongying Sag[J]. Lithologic Reservoirs, 2025, 37(1):13-23.
doi: 10.12108/yxyqc.20250102
[16] 朱博远, 张超谟, 张占松, 等. 渤中19-6太古界潜山复杂岩性储层矿物组分反演[J]. 岩性油气藏, 2020, 32(4):107-114.
doi: 10.12108/yxyqc.20200411
ZHU Boyuan, ZHANG Chaomo, ZHANG Zhansong, et al. Mineral component inversion of complex lithologic reservoirs in Bozhong 19-6 Archean buried hill[J]. Lithologic Reservoirs, 2020, 32(4):107-114.
doi: 10.12108/yxyqc.20200411
[17] 庞志超, 肖华, 毛晨飞, 等. 准噶尔盆地南缘地区含膏质地层岩性特征及测井识别方法[J]. 吉林大学学报(地球科学版), 2024, 54(4):1419-1431.
PANG Zhichao, XIAO Hua, MAO Chenfei, et al. Lithological characteristics and logging identification methods of gypsum-bearing strata in southern margin area of Junggar Basin[J]. Journal of Jilin University (Earth Science Edition), 2024, 54(4):1419-1431.
[18] 乔桐, 刘成林, 杨海波, 等. 准噶尔盆地盆1井西凹陷侏罗系三工河组凝析气藏特征及成因机制[J]. 岩性油气藏, 2024, 36(6):169-180.
doi: 10.12108/yxyqc.20240616
QIAO Tong, LIU Chenglin, YANG Haibo, et al. Characteristics and genetic mechanism of condensate oil and gas of the Jurassic Sangonghe Formation in western well Pen-1 Sag,Junggar Basin[J]. Lithologic Reservoirs, 2024, 36(6):169-180.
doi: 10.12108/yxyqc.20240616
[19] 谢伟彪, 殷秋丽, 刘迪仁, 等. 基于多矿物分析的砂砾岩稠油储层测井评价[J]. 岩性油气藏, 2013, 25(3):102-105.
XIE Weibiao, YIN Qiuli, LIU Diren, et al. Evaluation of glute-nite heavy oil reservoir based on multi-mineral log interpretation method[J]. Lithologic Reservoirs, 2013, 25(3):102-105.
[20] QIN Zhen, WANG Gang, ZHANG Yuehua, et al. A novel evaluation scheme of resistivity anisotropy in near-tight sandstones using conventional geophysical logs:A case study of the Triassic Chang 8 oil layer,Zhenjing area,Ordos Basin[J]. Journal of Applied Geophysics, 2023, 213:1-10.
[21] 江梦雅, 王江涛, 刘龙松, 等. 准噶尔盆地盆1井西凹陷石炭系—二叠系天然气特征及成藏主控因素[J]. 岩性油气藏, 2023, 35(3):138-151.
doi: 10.12108/yxyqc.20230312
JIANG Mengya, WANG Jiangtao, LIU Longsong, et al. Characteristics and main controlling factors of natural gas of Carboni-ferous-Permian in western well Pen-1 Sag,Junggar Basin[J]. Lithologic Reservoirs, 2023, 35(3):138-151.
doi: 10.12108/yxyqc.20230312
[22] QIN Zhen, WU Dong, LUO Shaocheng, et al. A novel method to obtain permeability in a dual-pore system using geophysical logs:A case study of an Upper Triassic Formation,southwest Ordos Basin,China[J]. Natural Resources Research, 2020, 29(4):2619-2634.
doi: 10.1007/s11053-019-09612-3
[23] 杨占伟, 姜振学, 梁志凯, 等. 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.
doi: 10.12108/yxyqc.20220113
YANG Zhanwei, JIANG Zhenxue, LIANG Zhikai, et al. Evaluation of shale TOC content based on two machine learning methods:A case study of Wufeng-Longmaxi Formation in southern Sichuan Basin[J]. Lithologic Reservoirs, 2022, 34(1):130-138.
doi: 10.12108/yxyqc.20220113
[24] 雍世和, 张超谟. 最优化测井解释[M]. 东营: 石油大学出版社,1996:65-74.
YONG Shihe, ZHANG Chaomo. Optimal logging interpretation[M]. Dongying: Petroleum University Press,1996:65-74.
[25] 王飞, 边会媛, 韩雪, 等. 基于细菌觅食算法的砂砾岩岩性识别方法[J]. 地球科学与环境学报, 2016, 38(2):277-284.
WANG Fei, BIAN Huiyuan, HAN Xue, et al. Identification method of sandy-conglomerate lithology based on bacterial foraging algorithm[J]. Journal of Earth Sciences and Environment, 2016, 38(2):277-284.
[26] 刘明明, 王全, 马收, 等. 基于混合粒子群算法的煤层气井位优化方法[J]. 岩性油气藏, 2020, 32(6):164-171.
doi: 10.12108/yxyqc.20200616
LIU Mingming, WANG Quan, MA Shou, et al. Well placement optimization of coalbed methane based on hybrid particle swarm optimization algorithm[J]. Lithologic Reservoirs, 2020, 32(6):164-171.
doi: 10.12108/yxyqc.20200616
[27] 斯伦贝谢公司. 测井解释常用岩石矿物手册[M]. 吴庆岩,张爱军,译. 北京: 石油工业出版社,1998:151-159.
SCHLUMBERGER. Manual of normal rock and mineral in log interpreting[M]. WU Qingyan,ZHANG Aijun,trans. Beijing: Petroleum Industry Press,1998:151-159.
[1] 户昶昊, 裴家学, 杨雪, 蔡国钢, 范家铭, 李丽. 开鲁盆地奈曼凹陷白垩系义县组天然碱矿地质特征及成矿条件[J]. 岩性油气藏, 2026, 38(1): 1-12.
[2] 肖萌, 周勇, 王柯, 闫璟驰, 张粤杰. 松辽盆地南部梨树断陷白垩系沙河子组古地貌特征及控砂机制[J]. 岩性油气藏, 2026, 38(1): 146-161.
[3] 张云峰, 史晓东, 刘宗堡, 杨雪微, 王鸿军, 郝彬. 松辽盆地龙虎泡油田白垩系构造-岩性圈闭类型及成藏主控因素[J]. 岩性油气藏, 2025, 37(5): 111-121.
[4] 刘丽娟, 李军辉, 付秀丽, 白月, 郑强. 松辽盆地北部中央坳陷区白垩系青山口组火山灰特征及其地质意义[J]. 岩性油气藏, 2025, 37(5): 145-154.
[5] 徐思慧, 赵军, 赵新建, 汪峻宇, 李兆平, 林宗鹏. 库车山前克拉苏构造带白垩系亚格列木组致密储层裂缝有效性评价[J]. 岩性油气藏, 2025, 37(5): 155-165.
[6] 户昶昊, 裴家学, 蔡国钢. 开鲁盆地陆东凹陷白垩系九佛堂组油气连续成藏条件[J]. 岩性油气藏, 2025, 37(3): 1-12.
[7] 冉逸轩, 杜长鹏, 张晶晶. 松辽盆地北部葡萄花油田白垩系泉四段源下型致密油成藏条件[J]. 岩性油气藏, 2025, 37(3): 47-58.
[8] 何星, 金玮, 张帆, 霍秋立, 李跃, 鲍俊驰, 刘璐, 曾庆兵. 海拉尔盆地乌尔逊凹陷白垩系铜钵庙组原油地球化学特征及来源[J]. 岩性油气藏, 2025, 37(1): 41-52.
[9] 陈红果, 张凤奇, 江青春, 刘红艳, 孙立东, 刘刚. 松辽盆地徐家围子断陷白垩系沙河子组超压形成机制及其演化特征[J]. 岩性油气藏, 2025, 37(1): 102-114.
[10] 卫欢, 单长安, 朱松柏, 黄钟新, 刘汉广, 朱兵, 吴长涛. 库车坳陷克深地区白垩系巴什基奇克组致密砂岩裂缝发育特征及地质意义[J]. 岩性油气藏, 2025, 37(1): 149-160.
[11] 屈卫华, 田野, 董常春, 郭小波, 李立立, 林斯雅, 薛松, 杨世和. 松辽盆地德惠断陷白垩系烃源岩特征及其控藏作用[J]. 岩性油气藏, 2024, 36(6): 122-134.
[12] 肖博雅. 二连盆地阿南凹陷白垩系凝灰岩类储层特征及有利区分布[J]. 岩性油气藏, 2024, 36(6): 135-148.
[13] 王洪星, 韩诗文, 胡佳, 潘志浩. 松辽盆地德惠断陷白垩系火石岭组凝灰岩储层预测及成藏主控因素[J]. 岩性油气藏, 2024, 36(5): 35-45.
[14] 杨为华. 松辽盆地双城断陷白垩系营城组四段致密油成藏主控因素及模式[J]. 岩性油气藏, 2024, 36(4): 25-34.
[15] 周洪锋, 吴海红, 杨禹希, 向红英, 高吉宏, 贺昊文, 赵旭. 二连盆地巴音都兰凹陷B51井区白垩系阿四段扇三角洲前缘沉积特征[J]. 岩性油气藏, 2024, 36(4): 85-97.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!

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