乍得Bongor盆地花岗岩潜山裂缝型储层有效渗透率计算方法

doi:10.12108/yxyqc.20230613

岩性油气藏 ›› 2023, Vol. 35 ›› Issue (6): 117–126.doi: 10.12108/yxyqc.20230613

乍得Bongor盆地花岗岩潜山裂缝型储层有效渗透率计算方法

郭海峰¹, 肖坤叶², 程晓东¹, 杜业波², 杜旭东¹, 倪国辉¹, 李贤兵², 计然¹

1. 中国石油集团测井有限公司国际公司, 北京 102206;
2. 中国石油集团科学技术研究院有限公司, 北京 100083

收稿日期:2023-04-17 修回日期:2023-06-27 出版日期:2023-11-01 发布日期:2023-11-07
第一作者:郭海峰(1976—),男,博士,高级工程师,主要从事测井资料处理与解释工作。地址:(102206)北京市昌平区沙河镇中石油科技园A12地块C座520室。Email:guohaifeng.cnlc@cnpc.com.cn。
基金资助:
中国石油集团科研项目“乍得花岗岩潜山油藏高效开发关键技术研究”(编号:2018D-4407)与中国石油集团测井有限公司科研项目“海外稳油控水技术体系研究”(编号:CNLC2022-10D02)联合资助

Determination of effective permeability of granitic buried-hill fractured reservoirs in Bongor Basin,Chad

GUO Haifeng¹, XIAO Kunye², CHENG Xiaodong¹, DU Yebo², DU Xudong¹, NI Guohui¹, LI Xianbing², JI Ran¹

1. International Branch, China National Logging Corporation, Beijing 102206, China;
2. Research Institute of Science and Technology Co., Ltd., CNPC, Beijing 100083, China

Received:2023-04-17 Revised:2023-06-27 Online:2023-11-01 Published:2023-11-07

摘要/Abstract

摘要： 基于乍得Bongor盆地花岗岩潜山油藏的钻录井、测井和试油资料,提出了一种新的储层有效渗透率计算方法,将试油结果转换为视有效渗透率来作为样本库的标签数据;以领域知识和机理模型驱动为主,机器学习为辅,建立特征曲线;采用XGBoost+KNN作为双重预测模型参与视有效渗透率计算,并利用SHAP值对模型进行了可解释性分析。研究结果表明:①将储层的测井视波阻抗和孔隙度作为渗透率指示曲线,分别与生产指数进行交会,从建模数据一致性指示交会图中挑选出19口井共26个有效井段,将试油结果转换为视渗透率(0.01~1 601.50 m D),共建立了51 348个深度点数据,14条输入曲线,基本覆盖主要潜山带,包含了不同岩性、不同储层品质和不同试油产量井段,使得整个样本库具有足够的代表性。②XGBoost模型充分利用了测井视波阻抗曲线、辅助表征潜山储层纵向分带特性的归一化垂深曲线、密度曲线、自然伽马窗口均值曲线、声波时差曲线、补偿中子测井曲线、视中子-密度孔隙度差窗口均值曲线、深浅电阻率曲线和自然伽马窗口标准差曲线信息,其计算结果与潜山储层品质的定性认识一致,预测精度较KNN模型更高。③乍得Bongor盆地花岗岩潜山油藏中有效渗透率大于1.00 mD的储层为有效储层,有效渗透率大于50.00 mD的储层为好储层,该方法的计算结果与试油结果一致。

关键词: 花岗岩潜山, 裂缝型储层, 视有效渗透率, 机器学习, 样本库构建, XGBoost, 储层参数建模, Bongor盆地

Abstract: A new effective permeability calculation method was proposed for the granitic buried-hill reservoirs in Bongor Basin of Chad based on drilling,logging,and oil testing data. Apparent effective permeability was derived from well testing results,serving as labeled data for the sample dataset. The method relies primarily on domain knowledge and mechanism-driven models,and is supplemented by machine learning to establish feature logs. The dual-prediction model XGBoost+KNN was employed to calculate apparent effective permeability,with SHAP values used for model interpretability analysis. The results show that:（1）Permeability indicator logs,namely apparent acoustic impedance and porosity,were utilized to select 26 effective testing intervals from19 wells,based on their intersection with production index. The well testing results were converted into apparent permeability values,ranging from 0.01 to 1 601.50 m D,resulting in a dataset comprising 51 348 depth data points and 14 input logs. The sample dataset adequately covers the main buried hill zones and incorporates input log response characteristics from diverse lithologies,reservoir qualities,and well testing production performance,thus achieving sufficient representativeness.（2）The XGBoost model effectively uses various logs,inclu-ding the apparent acoustic impedance log,normalized depth log representing the vertical zoning characteristics of buried-hill reservoirs,density log,window average of natural gamma ray log,acoustic log,neutron log,window average of neutron-density porosity difference log,deep and shallow resistivity log,and window standard deviation of natural gamma ray log. The model’s predictions exhibit consistency with qualitative understanding of buried-hill reservoir quality and demonstrate higher accuracy compared to the KNN model.（3）The granitic buried-hill reservoirs of Bongor Basin,Chad,with effective permeability greater than 1.00 m D,are classified as effective reservoirs,while those exceeding 50.00 mD are considered good reservoirs. The calculated results using the proposed method are consistent with the well testing results.

Key words: granitic buried hill, fractured reservoir, apparent effective permeability, machine learning, sample dataset building, XGBoost, reservoir parameter modeling, Bongor Basin

中图分类号:

TE122

郭海峰, 肖坤叶, 程晓东, 杜业波, 杜旭东, 倪国辉, 李贤兵, 计然. 乍得Bongor盆地花岗岩潜山裂缝型储层有效渗透率计算方法[J]. 岩性油气藏, 2023, 35(6): 117–126.

GUO Haifeng, XIAO Kunye, CHENG Xiaodong, DU Yebo, DU Xudong, NI Guohui, LI Xianbing, JI Ran. Determination of effective permeability of granitic buried-hill fractured reservoirs in Bongor Basin,Chad[J]. Lithologic Reservoirs, 2023, 35(6): 117–126.

参考文献

[1] 王楠.乍得Bongor盆地潜山岩性识别及储层测井综合评价[J].科学技术与工程,2019,19(27):66-73.WANG Nan. Lithology identification and well-logging comprehensive evaluation of basement reservoir in Bongor Basin,Chad[J]. Science Technology and Engineering,2019,19(27):66-73.
[2] 汪文湛,文光耀,程维营,等. Bongor盆地花岗岩潜山流体性质识别[J].石化技术,2019,26(6):138-141.WANG Wenzhan,WEN Guangyao,CHENG Weiying,et al.Identification of granitic buried-hill reservoir fluid properties in Bongor Basin[J]. Petrochemical Industry Technology,2019,26(6):138-141.
[3] 孙建孟,闫国亮.渗透率模型研究进展[J].测井技术,2012,36(4):329-335.SUN Jianmeng,YAN Guoliang. Review on absolute permeability model[J]. Well Logging Technology,2012,36(4):329-335.
[4] 任杰.碳酸盐岩裂缝性储层常规测井评价方法[J].岩性油气藏,2020,32(6):129-137.REN Jie. Conventional logging evaluation method for carbonate fractured reservoir[J]. Lithologic Reservoirs,2020,32(6):129-137.
[5] 吴伟,邵广辉,桂鹏飞,等.基于电成像资料的裂缝有效性评价和储集层品质分类:以鸭儿峡油田白垩系为例[J].岩性油气藏,2019,31(6):102-108.WU Wei,SHAO Guanghui,GUI Pengfei,et al. Fracture effectiveness evaluation and reservoir quality classification based on electrical imaging data:A case study of Cretaceous in Ya’erxia Oilfield[J]. Lithologic Reservoirs,2019,31(6):102-108.
[6] 严伟,张冲,胡挺,等.利用斯通利波估算火成岩地层渗透率[J].岩性油气藏,2013,25(1):107-110.YAN Wei,ZHANG Chong,HU Ting,et al. Calculation of permeability in igneous rock formation based on Stoneley wave[J]. Lithologic Reservoirs,2013,25(1):107-110.
[7] 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.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.
[8] 匡立春,刘合,任义丽,等.人工智能在石油勘探开发领域的应用现状与发展趋势[J].石油勘探与开发,2021,48(1):1-11.KUANG Lichun,LIU He,REN Yili,et al. Application and development trend of artificial intelligence in petroleum exploration and development[J]. Petroleum Exploration and Development,2021,48(1):1-11.
[9] 王华,张雨顺.测井资料人工智能处理解释的现状及展望[J].测井技术,2021,45(4):345-356.WANG Hua,ZHANG Yushun. Research status and prospect of artificial intelligence in logging data processing and interpretation[J]. Well Logging Technology,2021,45(4):345-356.
[10] 孙予舒,黄芸,梁婷,等.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.SUN Yushu,HUANG Yun,LIANG Ting,et al. Identification of complex carbonate lithology by logging based on XGBoost algorithm[J]. Lithologic Reservoirs,2020,32(4):98-106.
[11] 武中原,张欣,张春雷,等.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.WU Zhongyuan,ZHANG Xin,ZHANG Chunlei,et al. Lithology identification based on LTSM recurrent neural network[J]. Lithologic Reservoirs,2021,33(3):120-128.
[12] 窦立荣,魏小东,王景春,等.乍得Bongor盆地花岗质基岩潜山储层特征[J].石油学报,2015,36(8):897-904.DOU Lirong,WEI Xiaodong,WANG Jingchun,et al. Characteristics of granitic basement rock buried hill reservoir in Bongor Basin,Chad[J]. Acta Petrolei Sinica,2015,36(8):897-904.
[13] 余朝华,杜业波,肖坤叶,等.乍得Bongor盆地基岩潜山储层特征与影响因素研究[J].岩石学报,2019,35(4):1279-1290.YU Zhaohua,DU Yebo,XIAO Kunye,et al. Characteristics and influence factors of basement buried-hill reservoir in Bongor Basin,Chad[J]. Acta Petrologica Sinica,2019,35(4):1279-1290.
[14] SINGH A,THAKUR N,SHARMA A. A review of supervised machine learning algorithms[R]. New Delhi,India:2016 The3rd International Conference on Computing for Sustainable Global Development(INDIACom),2016.
[15] 刘能强.实用现代试井解释方法[M].5版.北京:石油工业出版社,2008:29-31.LIU Nengqiang. The utility of modern well test interpretation method[M]. 5th ed. Beijing:Petroleum Industry Press,2008:29-31.
[16] 肖立志.机器学习数据驱动与机理模型融合及可解释性问题[J].石油物探,2022,61(2):205-212.XIAO Lizhi. The fusion of data-driven machine learning with mechanism models and interpretability issues[J]. Geophysical Prospecting for Petroleum,2022,61(2):205-212.
[17] LIANG Lin,LEI Ting. Machine learning-enabled automatic sonic shear processing[J]. Petrophysics,2021,62(3):282-295.
[18] LI Hongqi,GUO Haifeng,GUO Haimin,et al. Data mining techniques for complex formation evaluation in petroleum exploration and production:A comparison of feature selection and classification methods[R]. Wuhan,China:2008 IEEE PacificAsia Workshop on Computational Intelligence and Industrial Application,2008.
[19] ZHENG A,CASARI A. Feature engineering for machine learning:Principles and techniques for data scientists[M]. Sebastopol,California:O’Reilly Media,Inc.,2018.
[20] Aspen Tech. Aspen Geolog[EB/OL].[2023-07-20]. https://www.aspentech.com/en/products/sse/aspen-geolog.
[21] YE Shinju,RABILLER P. A new tool for electro-facies analysis:Multi-resolution graph-based clustering[R]. Dallas,Texas,USA:SPWLA 41st Annual Logging Symposium,2000.
[22] GRINSZTAJN L,OYALLON E,VAROQUAUX G. Why do tree-based models still outperform deep learning on tabular data?[DB/OL].(2022-07-18)[2023-07-20]. https://arxiv.org/abs/2207.08815.
[23] SHWARTZ-ZIV R,ARMON A. Tabular data:Deep learning is not all you need[J]. Information Fusion,2022,81:84-90.
[24] GORISHNIY Y,RUBACHEV I,KHRULKOV V,et al. Revisiting deep learning models for tabular data[DB/OL].(2021-11-10)[2023-07-20]. https://arxiv.org/abs/2106.11959.
[25] FIX E,HODGES J L. Discriminatory analysis—Nonparametric discrimination:Consistency properties[J]. International Statistical Review/Revue Internationale de Statistique,1989,57(3):238-247.
[26] CORTES C,VAPNIK V. Support-vector networks[J]. Machine Learning,1995,20(3):273-297.
[27] KE Guolin,MENG Qi,FINLEY T,et al. LightGBM:A highly efficient gradient boosting decision tree[M]//GUYON I,VON L U,BENGIO S,et al. 31st Advances in neural information processing systems 30(NIPS 2017). Massachusetts,USA:MIT Press,2017.
[28] CHEN Tianqi,GUESTRIN C. XGBoost:A scalable tree boosting system[C]//KRISHNAPURAM B,SHAH M,SMOLA A,et al. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. New York:Association for Computing Machinery,2016.
[29] Microsoft Corporation. Parameters tuning—Light GBM 4.0.0.99documentation. html[EB/OL].[2023-07-20]. https://lightgbm.readthedocs.io/en/latest/Parameters-Tuning.html.
[30] SNOEK J,LAROCHELLE H,ADAMS R P. Practical bayesian optimization of machine learning algorithms[DB/OL].(2012-08-29)[2023-07-20]. https://arxiv.org/abs/1206.2944.
[31] PEDREGOSA F,VAROQUAUX G,GRAMFORT A,et al.Scikit-Learn:Machine learning in python[J]. Journal of Machine Learning Research,2011,12(85):2825-2830.
[32] HEAD T,KUMAR M,NAHRSTAEDT H,et al. Scikit-optimize/scikit-optimize[DB/OL].(2022-04-12)[2023-07-20]. https://zenodo.org/record/6451894.
[33] WANG Chi,WU Qingyun,WEIMER M,et al. FLAML:A fast and lightweight Auto ML library[DB/OL].(2021-05-19)[2023-07-20]. https://arxiv.org/abs/1911.04706.
[34] LUNDBERG S M,LEE S I. A unified approach to interpreting model predictions[C]//Advances in Neural Information Processing Systems 30(NIPS 2017). Long Beach,California,USA:Neural Information Processing Systems Foundation,Inc.(NeurIPS),2018.
[35] LUNDBERG S M,ERION G,CHEN H,et al. From local explanations to global understanding with explainable AI for trees[J]. Nature Machine Intelligence,2020,2(1):56-67.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

乍得Bongor盆地花岗岩潜山裂缝型储层有效渗透率计算方法

Determination of effective permeability of granitic buried-hill fractured reservoirs in Bongor Basin,Chad

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

Metrics

本文评价

推荐阅读 10

[1]	赵军, 李勇, 文晓峰, 徐文远, 焦世祥. 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.
[2]	桂金咏, 李胜军, 高建虎, 刘炳杨, 郭欣. 基于特征变量扩展的含气饱和度随机森林预测方法[J]. 岩性油气藏, 2024, 36(2): 65-75.
[3]	杨午阳, 魏新建, 李海山. 智能物探技术的过去、现在与未来[J]. 岩性油气藏, 2024, 36(2): 170-188.
[4]	唐昱哲, 柴辉, 王红军, 张良杰, 陈鹏羽, 张文起, 蒋凌志, 潘兴明. 中亚阿姆河右岸东部地区侏罗系盐下碳酸盐岩储层特征及预测新方法[J]. 岩性油气藏, 2023, 35(6): 147-158.
[5]	许鑫, 杨午阳, 张凯, 魏新建, 张向阳, 李海山. 三维初至波旅行时层析速度反演算法优化[J]. 岩性油气藏, 2023, 35(4): 79-89.
[6]	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.
[7]	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.
[8]	宋宣毅, 刘月田, 马晶, 王俊强, 孔祥明, 任兴南. 基于灰狼算法优化的支持向量机产能预测[J]. 岩性油气藏, 2020, 32(2): 134-140.
[9]	刘桂珍，张德诗，李能武 . 昆北断阶带基岩储层特征及油气成藏条件[J]. 岩性油气藏, 2015, 27(2): 62-69.
[10]	何龙，郑荣才，梁西文，徐文礼. 川东涪陵地区大安寨段裂缝控制因素及期次分析[J]. 岩性油气藏, 2014, 26(4): 88-96.
[11]	Yuriy Tyapkin， Iana Mendrii. 改进的地震相干体算法及其应用———以乌克兰顿涅茨盆地裂缝型储层为例[J]. 岩性油气藏, 2013, 25(5): 8-12.
[12]	刘迪仁，夏培，万文春，闫林辉，赵建武. 水平井碳酸盐岩裂缝型储层双侧向测井响应特性[J]. 岩性油气藏, 2012, 24(3): 1-4.