基于机器学习的岩芯渗透率及裂缝开度预测

doi:10.11885/j.issn.1674-5086.2021.04.30.04

西南石油大学学报(自然科学版) ›› 2023, Vol. 45 ›› Issue (4): 155-163.DOI: 10.11885/j.issn.1674-5086.2021.04.30.04

基于机器学习的岩芯渗透率及裂缝开度预测

陈林¹, 黎棚武², 张绍俊¹, 李志杰², 杜小勇¹

1. 中国石油塔里木油田分公司油气工程研究院, 新疆库尔勒 841000;
2. 油气藏地质及开发工程全国重点实验室 · 西南石油大学, 四川成都 610500

收稿日期:2021-04-30 出版日期:2023-08-10 发布日期:2023-07-18
通讯作者: 陈林,E-mail:chenl-tlm@petrochina.com.cn
作者简介:陈林,1969年生,男,汉族,四川崇州人,高级工程师,硕士,主要从事钻井液与完井液等方面的研究工作。E-mail:chenl-tlm@petrochina.com.cn;黎棚武,1997年生,男,汉族,四川德阳人,硕士研究生,主要从事提高油气采收率及数值模拟研究工作。E-mail:1446905204@qq.com;张绍俊,1981年生,男,汉族,四川隆昌人,高级工程师,硕士,主要从事油田化学剂生产、研发方面的工作。E-mail:11174721107@qq.com;李志杰,1996年生,男,汉族,甘肃临洮人,硕士研究生,主要从事油气田开发等方面的研究工作。E-mail:1500154100@qq.com;杜小勇,1969年生,男,汉族,四川射洪人,高级工程师,硕士,主要从事钻井液方面的研究。E-mail:dxy_tlm@petrochina.com.cn

Prediction Method of Core Permeability and Fracture Aperture Based on Machine Learning

CHEN Lin¹, LI Pengwu², ZHANG Shaojun¹, LI Zhijie², DU Xiaoyong¹

1. Research Institute of Oil and Gas Engineering, Tarim Oilfield Branch, PetroChina, Korla, Xinjiang 841000, China;
2. National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu, Sichuan 610500, China

Received:2021-04-30 Online:2023-08-10 Published:2023-07-18

摘要/Abstract

摘要： 应力敏感是致密砂岩气藏损害的主要原因之一，预测应力敏感损害下岩芯渗透率和裂缝开度的变化规律一直是致密砂岩储层保护领域的重点。以塔里木盆地克拉苏构造带岩样为研究对象，基于应力敏感实验及调研数据，采用机器学习多元线性回归算法，耦合了围压渗透率关系模型和K-p函数参数预测模型，建立了岩芯渗透率预测模型和裂缝开度预测模型，并通过决定系数、均方根误差和相对误差检验模型精度。结果表明，围压渗透率关系模型在裂缝性岩芯和非裂缝性岩芯中预测结果决定系数平均值均大于0.960； K-p函数参数预测模型在裂缝性岩芯中的均方根误差高于非裂缝性岩芯，但裂缝性岩芯的相对误差要低于非裂缝性岩芯，综合来看岩芯渗透率预测模型更适用于裂缝性岩芯；裂缝开度预测模型与实测值决定系数0.978，预测精度较高。建立的渗透率预测模型和裂缝开度预测模型可为致密砂岩储层的开采与保护提供指导。

关键词: 机器学习, 渗透率预测, 裂缝开度, 应力敏感, 致密砂岩, 多元线性回归

Abstract: Stress sensitivity is one of the main reasons for the damage of tight sandstone gas reservoirs. The prediction of the change law of core permeability and fracture aperture under stress sensitivity damage is always the key point in the field of tight sandstone reservoir protection. Based on the stress-sensitive experiment and survey data, the core permeability prediction model and fracture opening prediction model were established by using machine learning multiple linear regression algorithm coupled with the confining pressure permeability relationship model and the K-p function parameter prediction model. The accuracy of the model was tested by correlation coefficient, root mean square error and relative error. The results show that the average correlation coefficient of the prediction results of the confining pressure permeability model in fractured and nonfractured cores is greater than 0.96. The prediction results of K-p function parameter prediction model show that the root mean square error in fractured cores is higher than that in non-fractured cores, but the relative error of fractured cores is lower than that of non-fractured cores. It shows that the permeability prediction model is more suitable for fractured cores. The coefficient of determination between the fracture opening prediction model and the measured value is 0.978, indicating a high prediction accuracy. The permeability prediction model and fracture aperture prediction model can provide guidance for the exploitation and protection of tight sandstone reservoir.

Key words: machine learning, permeability prediction, fracture aperture, stress sensitivity, tight sandstone, multiple linear regression

中图分类号:

TE311

陈林, 黎棚武, 张绍俊, 李志杰, 杜小勇. 基于机器学习的岩芯渗透率及裂缝开度预测[J]. 西南石油大学学报(自然科学版), 2023, 45(4): 155-163.

CHEN Lin, LI Pengwu, ZHANG Shaojun, LI Zhijie, DU Xiaoyong. Prediction Method of Core Permeability and Fracture Aperture Based on Machine Learning[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2023, 45(4): 155-163.

0
/ / 推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://journal15.magtechjournal.com/Jwk_xnzk/CN/10.11885/j.issn.1674-5086.2021.04.30.04

http://journal15.magtechjournal.com/Jwk_xnzk/CN/Y2023/V45/I4/155

参考文献

[1] GOLAB A N, KNACKSTEDT M A, AVERDUNK H, et al. 3D porosity and mineralogy characterization in tight gas sandstones[J]. The Leading Edge, 2010, 29(12):1476-1483. doi:10.1190/1.3525363
[2] HOLDITCH S A. Tight gas sands[J]. Journal of Petroleum Technology, 2006, 58(6):86-93. doi:10.2118/103356-JPT
[3] XIAO D, JIANG S, THUL D, et al. Impacts of clay on pore structure, storage and percolation of tight sandstones from the Songliao Basin, China:Implications for genetic classification of tight sandstone reservoirs[J]. Fuel, 2018, 211:390-404. doi:10.1016/j.fuel.2017.09.084
[4] 朱金智,雷明,任玲玲,等. 致密砂岩气藏高温高压敏感性评价及机理探讨——以塔里木盆地B区块致密气藏为例[J]. 断块油气田, 2017, 24(2):222-225. doi:10.6056/dkyqt201702018 ZHU Jinzhi, LEI Ming, REN Lingling, et al. Sensitivity evaluation and mechanism of tight sandstone gas reservoir under high temperature and high pressure:A case study of tight gas reservoir in B Zone[J]. Fault-Block Oil & Gas Field, 2017, 24(2):222-225. doi:10.6056/dkyqt201702-018
[5] BAHRAMI H, REZAEE R, CLENNELL B. Water blocking damage in hydraulically fractured tight sand gas reservoirs:An example from Perth Basin, western Australia[J]. Journal of Petroleum Science and Engineering, 2012, 88-89:100-106. doi:10.1016/j.petrol.2012.04.002
[6] REINICKE A, RYBACKI E, STANCHITS S, et al. Hydraulic fracturing stimulation techniques and formation damage mechanisms Implications from laboratory testing of tight sandstone-proppant systems[J]. Geochemistry, 2010, 70:107-117. doi:10.1016/j.chemer.2010.05.016
[7] FARQUHAR R A, SMART B G D, TODD A C, et al. Stress sensitivity of low-permeability sandstones from the Rotliegendes sandstone[C]. SPE 26501-MS, 1993. doi:10.2118/26501-MS
[8] HUANG Z, SHIMELD J, WILLIAMSON M, et al. Permeability prediction with artificial neural network modeling in the Venture Gas Field, offshore eastern Canada[J]. Geophysics, 1996, 61(2):422-436. doi:10.1190/-1.1443970
[9] LIU S, HARPALANI S. Permeability prediction of coalbed methane reservoirs during primary depletion[J]. International Journal of Coal Geology, 2013, 113:1-10.
[10] 张路锋,周福建,辜富洋,等. 裂缝性致密砂岩气藏入井流体伤害规律[J]. 钻井液与完井液, 2018, 35(5):121-126. doi:10.3969/j.issn.1001-5620.2018.05.023 ZHANG Lufeng, ZHOU Fujian, GU Fuyang, et al. Regularities of fractured tight sandstone gas reservoirs damaged by work fluids[J]. Drilling Fluid & Completion Fluid, 2018, 35(5):121-126. doi:10.3969/j.issn.1001-5620.2018.05.023
[11] 蔡李梅,叶素娟,付菊,等. 多参数约束的致密砂岩储层渗透率预测方法——以川西拗陷中江气田沙溪庙组为例[J]. 成都理工大学学报(自然科学版), 2018, 45(4):468-477. doi:10.3969/j.issn.1671-9727.2018.04.07 CAI Limei, YE Sujuan, FU Ju, et al. Permeability prediction technique based on multi-parameter constrain for tight sandstone reservoir:A case study of the Zhongjiang Gas Field in Jurassic Shaximiao Formation in Sichuan Basin, China[J]. Journal of Chengdu University of Technology (Science & Technology Edition), 2018, 45(4):468-477. doi:10.3969/j.issn.1671-9727.2018.04.07
[12] 程辉,王付勇,宰芸,等. 基于高压压汞和核磁共振的致密砂岩渗透率预测[J]. 岩性油气藏, 2020, 32(3):122-132. doi:10.12108/yxyqc.20200312 CHENG Hui, WANG Fuyong, ZAI Yun, et al. Prediction of tight sandstone permeability based on highpressure mercury intrusion (HPMI) and nuclear magnetic resonance (NMR)[J]. Lithologic Reservoirs, 2020, 32(3):122-132. doi:10.12108/yxyqc.20200312
[13] 张鹏,吴通,李中,等. BP神经网络法预测顺北超深碳酸盐岩储层应力敏感程度[J]. 石油钻采工艺, 2020, 42(5):622-626. doi:10.13639/j.odpt.2020.05.016 ZHANG Peng, WU Tong, LI Zhong, et al. Application of BP neural network method to predict the stress sensitivity of ultra deep carbonate reservoir in Shunbei Oilfield[J]. Oil Drilling & Production Technology, 2020, 42(5):622-626. doi:10.13639/j.odpt.2020.05.016
[14] 陈龙伟,汪关妹,冯小英,等. 沁水盆地LB区块煤系地层渗透率预测[J]. 石油地球物理勘探, 2020, 55(S1):85-91, 8. doi:10.13810/j.cnki.issn.1000-7210.2020.S.013 CHEN Longwei, WANG Guanmei, FENG Xiaoying, et al. Permeability prediction of coal strata in Block LB, Qinshui Basin[J]. Oil Geophysical Prospecting, 2020, 55(S1):85-91, 8. doi:10.13810/j.cnki.issn.1000-7210.2020.S.013
[15] 谷宇峰,张道勇,鲍志东,等. 利用梯度提升决策树(GBDT)预测渗透率——以姬塬油田西部长4+5段致密砂岩储层为例[J]. 地球物理学进展, 2021, 36(2):585-594. doi:10.6038/pg2021EE0216 GU Yufeng, ZHANG Daoyong, BAO Zhidong, et al. Permeability prediction using gradient boosting decision tree (GBDT):A case study of tight sandstone reservoirs of member of Chang 4+5 in western Jiyuan Oilfield[J]. Progress in Geophysics, 2021, 36(2):585-594. doi:10.6038/pg2021EE0216
[16] 谷宇峰,张道勇,鲍志东. 测井资料PSO-XGBoost渗透率预测[J]. 石油地球物理勘探, 2021, 56(1):26-37. doi:10.13810/j.cnki.issn.1000-7210.2021.01.003 GU Yufeng, ZHANG Daoyong, BAO Zhidong, et al. Permeability prediction using PSO-XG Boost based on logging data[J]. Oil Geophysical Prospecting, 2021, 56(1):26-37. doi:10.13810/j.cnki.issn.1000-7210.2021.01.003
[17] 闫国峰,姜琪,乔国满,等. 致密油储层压裂后渗透率预测模型[J]. 钻采工艺, 2021, 44(1):69-73. doi:10.3969/J.ISSN.1006-768X.2021.01.15 YAN Guofeng, JIANG Qi, QIAO Guoman, et al. Permeability prediction model of tight oil reservoir after fracturing[J]. Drilling & Production Technology, 2021, 44(1):69-73. doi:10.3969/J.ISSN.1006-768X.2021.01.15
[18] 景文龙,李博涵,杨守磊,等. 基于TensorFlow的均质数字岩心渗透率预测方法及应用[J]. 中国石油大学学报(自然科学版), 2021, 45(4):108-113. doi:10.3969/j.issn.1673-5005.2021.04.013 JING Wenlong, LI Bohan, YANG Shoulei, et al. Method and application of homogeneous digital core permeability prediction based on TensorFlow[J]. Journal of China University of Petroleum (Edition of Natural Science), 2021, 45(4):108-113. doi:10.3969/j.issn.1673-5005.2021.04.013
[19] 李佳. 基于机器学习的多孔介质渗透率预测研究[D]. 杭州:浙江大学, 2019. LI Jia. Study on permeability prediction of porous media based on machine learning[D]. Hangzhou:Zhejiang University, 2019.
[20] 魏佳明. 机器学习在储层参数预测中的应用研究[D]. 西安:西安石油大学, 2019. WEI Jiaming. Application of machine learning in reservoir parameter prediction[D]. Xi'an:Xi'an Petroleum University, 2019.
[21] 虞兵,冉晓军,侯秋元,等. 裂缝性致密砂岩储层品质评价[J]. 测井技术, 2019, 43(4):405-409, 415. doi:10.16489/i.issn.1004-1338.2019.04.01 YU Bing, RAN Xiaojun, HOU Qiuyuan, et al. Reservoir quality evaluation of fractured tight sandstone[J]. Well Logging Technology, 2019, 43(4):405-409, 415. doi:10.16489/i.issn.1004-1338.2019.04.01
[22] 唐雁刚,张荣虎,魏红兴,等. 致密砂岩储层多尺度裂缝渗透率定量表征及开发意义[J]. 特种油气藏, 2018, 25(5):30-34. doi:10.3969/j.issn.1006-6535.2018.05.006 TANG Yangang, ZHANG Ronghu, WEI Hongxing, et al. Quantitative permeability characterization of multi-scale fractures and its development significance in tight sandstone gas reservoir[J]. Special Oil & Gas Reservoirs, 2018, 25(5):30-34. doi:10.3969/j.issn.1006-6535.2018.05.006
[23] 高文杰,李贤庆,张光武,等. 塔里木盆地库车坳陷克拉苏构造带深层致密砂岩气藏储层致密化与成藏关系[J]. 天然气地球科学, 2018, 29(2):226-235. doi:10.11764/j.issn.1672-1926.2017.12.007 GAO Wenjie, LI Xianqing, ZHANG Guangwu, et al. The relationship research between densification of reservoir and accumulation of the deep tight sandstone gas reservoirs of the Kelasu tectonic zone in Kuqa Depression, Tarim Basin[J]. Natural Gas Geoscience, 2018, 29(2):226-235. doi:10.11764/j.issn.1672-1926.2017.12.007
[24] 黄思静,侯中健. 地下孔隙率和渗透率在空间和时间上的变化及影响因素[J]. 沉积学报, 2001, 19(2):224-232. doi:10.14027/j.canki.cjxb.2001.02.010 HUANG Sijing, HOU Zhongjian. Spatio-temporal variation of subsurface porosity and permeability and its influential factors[J]. Acta Sedimentologica Sinica, 2001, 19(2):224-232. doi:10.14027/j.canki.cjxb.2001.02.010
[25] HEILAND J. Permeability of triaxially compressed sandstone:Influence of deformation and strain-rate on permeability[M]//KÜMPEL H J. Thermo-hydro-mechanical coupling in fractured rock. Basel:Birkhaüser Verlag, Basel, 2003:889-908. doi:10.1007/978-3-0348-8083-1_6
[26] ARSON C, PEREIRA J M. Influence of damage on pore size distribution and permeability of rocks[J]. International Journal for Numerical and Analytical Methods in Geomechanics, 2013, 37(8):810-831. doi:10.1002/nag.1123
[27] NGO V T, LU V D, NGUYEN M H, et al. A comparison of permeability prediction methods using core analysis data[C]. SPE 175650-MS, 2015. doi:10.2118/175650-MS
[28] LI Tao, LI Min, JING Xueqi, et al. Influence mechanism of pore-scale anisotropy and pore distribution heterogeneity on permeability of porous media[J]. Petroleum Exploration and Development, 2019, 46(3):594-604. doi:10.1016/S1876-3804(19)60039-X
[29] 熊繁升,甘利灯,孙卫涛,等. 裂缝-孔隙介质储层渗透率表征及其影响因素分析[J]. 地球物理学报, 2021, 64(1):279-288. doi:10.6038/cjg2021No175 XIONG Fansheng, GAN Lideng, SUN Weitao, et al. Characterization of reservoir permeability and analysis of influencing factors in fracture-pore media[J]. Chinese Journal of Geophysics, 2021, 64(1):279-288. doi:10.6038/-cjg2021No175
[30] TIAN Ye. Experimental study on stress sensitivity of naturally fractured reservoirs[C]. SPE 173463-STU, 2014. doi:10.2118/173463-STU
[31] HAN G, BARTKO K. Stress-sensitivity of fractured tight reservoirs[C]. IPTC 20260-MS, 2020. doi:10.2523/IPTC-20260-MS
[32] 康毅力,李潮金,游利军,等. 塔里木盆地深层致密砂岩气层应力敏感性[J]. 天然气地球科学, 2020, 31(4):532-541. doi:10.11764/j.issn.1672-1926.2020.01.002 KANG Yili, LI Chaojin, YOU Lijun, et al. Stress sensitivity of deep tight gas-reservoir sandstone in Tarim Basin[J]. Natural Gas Geoscience, 2020, 31(4):532-541. doi:10.11764/j.issn.1672-1926.2020.01.002
[33] TANG Jun, ZHANG Chengguang, XIN Yi. A fracture evaluation by acoustic logging technology in oil-based mud:A case from tight sandstone reservoirs in Keshen Area of Kuqa Depression, Tarim Basin, NW China[J]. Petroleum Exploration and Development, 2017, 44(3):418-427. doi:10.1016/S1876-3804(17)30048-4
[34] HE Jianming, LIN Chong, LI Xiao, et al. Initiation, propagation, closure and morphology of hydraulic fractures in sandstone cores[J]. Fuel, 2017, 208:65-70. doi:10.1016/-j.fuel.2017.06.080

基于机器学习的岩芯渗透率及裂缝开度预测

Prediction Method of Core Permeability and Fracture Aperture Based on Machine Learning

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	刘言, 刘露. 新场JS₂致密砂岩气藏开发中后期加密界限研究[J]. 西南石油大学学报(自然科学版), 2023, 45(4): 103-110.
[2]	柳朝阳, 郭奇, 李刚, 黄博, 王振宇. 高含水油藏流线场表征与评价方法[J]. 西南石油大学学报(自然科学版), 2023, 45(1): 89-96.
[3]	刘绪钢, 周涌沂, 张骏强, 肖文联, 任席瑶. 非线性应力作用下裂缝砂岩应力敏感性特征[J]. 西南石油大学学报(自然科学版), 2023, 45(1): 127-135.
[4]	马先林, 周德胜, 蔡文斌, 李宪文, 何明舫. 基于可解释机器学习的水平井产能预测方法[J]. 西南石油大学学报(自然科学版), 2022, 44(4): 81-90.
[5]	刘言. 中江气田致密砂岩气藏“一体化”甜点评价技术[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 12-25.
[6]	王荐, 段文燊, 毕有益. 川西致密砂岩气藏“暗点”型河道砂岩识别方法[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 37-46.
[7]	熊亮, 衡勇. 中江沙溪庙组致密砂岩气藏气水分布及主控因素[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 47-58.
[8]	刘成川, 陈俊, 程洪亮. 川西致密砂岩气藏测井评价技术及其发展展望[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 59-69.
[9]	詹国卫, 顾战宇, 庞河清, 蔡左花. 致密砂岩储层孔隙结构特征及其对开发的影响[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 70-84.
[10]	曾焱, 曹廷宽, 高伟. 致密砂岩气藏剩余气开发潜力定量评价[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 93-101.
[11]	刘露, 段永明, 邹陈蓉. 新场蓬莱镇低渗致密气藏效益潜力评价新方法[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 102-109.
[12]	李华昌, 黎华继, 李峰, 许鑫. 大型高叠置致密砂岩气藏提高采收率技术[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 110-120.
[13]	谭佳, 刘殷韬, 潘宝风. 致密砂岩气藏纳米封堵型低伤害压裂液研究[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 139-147.
[14]	李胜富, 李皋, 吴建忠, 李泽. 川西致密砂岩气藏井筒积液储层损害机理研究[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 157-166.
[15]	杜洋, 郭新江, 刘通, 张国东. 川西致密砂岩气田采气工艺实践与效果[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 188-196.