Intelligent prediction of different gas composition front breakthrough time during multi-component gas flooding

Sang Guoqiang; Lü Weifeng; Sun Yuanhui; Jia Ninghong; Chen Haowei; Zhou Tiyao; Zhang Shanyan; Yin Hengfei; Hao Hongda

doi:10.7623/syxb202608007

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Intelligent prediction of different gas composition front breakthrough time during multi-component gas flooding

更新时间：2026-09-14

- Intelligent prediction of different gas composition front breakthrough time during multi-component gas flooding
- ACTA PETROLEI SINICA Vol. 47, Issue 8, Pages: 1614-1629(2026)
- 作者机构：
  
  1. 怀柔实验室新疆研究院,新疆,乌鲁木齐,830000
  2. 中国石油勘探开发研究院,北京,100083
  3. 提高油气采收率全国重点实验室,北京,100083
  4. 常州大学石油与天然气工程学院,江苏,常州,213164
- 作者简介：
- 基金信息：
- DOI：10.7623/syxb202608007
  CLC： TE357.45
- Online First：08 September 2026，
  
  Published：2026
- 稿件说明：
移动端阅览
桑国强, 吕伟峰, 孙圆辉, 贾宁洪, 陈昊卫, 周体尧, 张善严, 尹恒飞, 郝宏达. 多元气驱不同气组分前缘突破时间智能预测[J]. 石油学报, 2026, 47(8): 1614-1629.

Sang Guoqiang, Lü Weifeng, Sun Yuanhui, et al. Intelligent prediction of different gas composition front breakthrough time during multi-component gas flooding[J]. ACTA PETROLEI SINICA, 2026, 47(8): 1614-1629.
桑国强, 吕伟峰, 孙圆辉, 贾宁洪, 陈昊卫, 周体尧, 张善严, 尹恒飞, 郝宏达. 多元气驱不同气组分前缘突破时间智能预测[J]. 石油学报, 2026, 47(8): 1614-1629. DOI： 10.7623/syxb202608007.

Sang Guoqiang, Lü Weifeng, Sun Yuanhui, et al. Intelligent prediction of different gas composition front breakthrough time during multi-component gas flooding[J]. ACTA PETROLEI SINICA, 2026, 47(8): 1614-1629. DOI： 10.7623/syxb202608007.

摘要

在石油开采领域

注CO

在提高采收率方面具有显著优势

但存在气体窜流严重、波及效率有限等问题

为此基于注烟道气提高采收率理论提出了以CH

、N

、CO

为主的多元气体提高采收率新技术。在低渗透油藏多元气驱技术中

准确预测不同组分气体突破时间对优化开采策略意义重大。以新疆地区低渗透油藏为研究对象

构建了典型油藏模型

考虑渗透率、非均质性、原油黏度、多元气组成等地质、流体和工艺参数

通过分析多元气驱过程中油、气组分动态及饱和度剖面变化

建立了多组分前缘识别方法

确定了组分波及前缘、富CH

前缘、有效组分前缘、富N

前缘、富CO

前缘和气段塞前缘6种前缘类型及其特征

并得到了不同前缘突破时间。其次

运用灰色关联度分析

研究了多因素对突破时间的影响

明确了渗透率、非均质性、多元气组成等主控因素。最后

对比线性回归、随机森林、神经网络等算法

经超参数优化+特征选择方法、集成学习、超参数优化+交叉验证和学习曲线+超参数优化随机森林模型后

基于集成学习优化的随机森林模型预测效果最佳

判定系数最大为0.837 7

均方根误差最小为0.046 4

实现了多元气驱多组分前缘突破时间的智能预测。

Abstract

In petroleum exploration

flooding demonstrates significant advantages in enhancing oil recovery; however

issues such as severe gas channeling and limited sweep efficiency remain prominent. To address these challenges

a novel multi-component gas EOR technology utilizing flue gas components-primarily CH

and CO

is proposed. For multi-component gas flooding in low-pe

rmeability reservoirs

accurate prediction of gas breakthrough time is crucial for optimizing production strategies. In this study

a low-permeability reservoir in Xinjiang is selected as the research subject

and a representative reservoir model is constructed using CMG numerical simulation software. Key geological and fluid parameters

including permeability

heterogeneity

crude oil viscosity

and multi-component gas composition

are incorporated into the model to ensure a realistic simulation of reservoir conditions. By analyzing the dynamic evolution of oil-gas components during multi-component gas flooding

and changes in saturation profiles

a methodology for identifying multi-component displacement fronts is established. Six types of displacement fronts are defined—compositional sweep front

-rich front

effective compositional front

-rich front

and gas slug front—and their respective characteristics are systematically described. Furthermore

the breakthrough times of these different fronts are determined. Subsequently

grey relational analysis was employed to investigate the influence of multiple factors on breakthrough time

with the permeability

reservoir heterogeneity

and multi-component gas composition identified as dominant factors. Finally

a comparative analysis of linear regression

random forest

and neural network algorithms was conducted. After implementing hyperparameter optimization with feature selection

ensemble learning

and learning-curve-guided hyperparameter tuning with cross-validation

the ensemble-optimized Random Forest model demonstrated superior predictive performance. The optimized model achieved a maximum

of 0.837 7 and a minimum RMSE of 0.046 4

enabling intelligent prediction of multi-component gas front breakthrough time in multi-component gas flooding processes.

关键词

Keywords

references

KANG Wanli,ZHOU Bobo,ISSAKHOV M,et al.Advances in enhanced oil recovery technologies for low permeability reservoirs[J].Petroleum Science,2022,19(4):1622-1640.

王光付,李阳,王锐,等.二氧化碳地质封存与利用新进展[J].石油与天然气地质,2024,45(4):1168-1179. WANG Guangfu,LI Yang,WANG Rui,et al.Recent advances in geological carbon dioxide storage and utilization[J].Oil & Gas Geology,2024,45(4):1168-1179.

袁士义,马德胜,李军诗,等.二氧化碳捕集、驱油与埋存产业化进展及前景展望[J].石油勘探与开发,2022,49(4):828-834. YUAN Shiyi,MA Desheng,LI Junshi,et al.Progress and prospects of carbon dioxide capture,EOR-utilization and storage industrialization[J].Petroleum Exploration and Development,2022,49(4):828-834.

TARIQ Z,ELKATATNY S,MAHMOUD M,et al.A new technique to develop rock strength correlation using artificial intelligence tools[C]//Society of Petroleum Engineers-SPE Reservoir Characterisation and Simulation Conference and Exhibition,RCSC 2017.Dallas:SPE,2017:1340-1353.

SHAHRAEENI M,HOORFAR M.Effect of gas diffusion layer properties on the time of breakthrough[J].Journal of Power Sources,2011,196(14):5918-5921.

XIAN Bihua,HAO Hongda,DENG Song,et al.Laboratory experiments of hydrocarbon gas flooding and its influencing factors on oil recovery in a low permeability reservoir with medium viscous oil[J].ACS Omega,2024,9(7):8381-8396.

邹积瑞,岳湘安,孔艳军,等.裂缝性低渗油藏二氧化碳驱注入方式实验[J].断块油气田,2016,23(6):800-802. ZOU Jirui,YUE Xiangan,KONG Yanjun.Injection experiment of carbon dioxide flooding in low-permeability fissure reservoirs[J].Fault-Block Oil & Gas Field,2016,23(6):800-802.

LUO Juan,WANG Lei.Research on gas channeling identification method for gas injection development in high-pressure heterogeneous reservoir[J].Processes,2022,10(11):2366.

[J].Journal of Petroleum Science and Engineering,2016,145:22-33.

LI Ran,CHEN Zhangxin,WU Keliu,et al.An analytical model for water-oil two-phase flow in inorganic nanopores in shale oil reservoirs[J].Petroleum Science,2021,18(6):1776-1787.

窦立荣,孙龙德,吕伟峰,等.全球二氧化碳捕集、利用与封存产业发展趋势及中国面临的挑战与对策[J].石油勘探与开发,2023,50(5):1083-1096. DOU Lirong,SUN Longde,LÜ Weifeng,et al.Trend of global carbon dioxide capture,utilization and storage industry and challenges and countermeasures in China[J].Petroleum Exploration and Development,2023,50(5):1083-1096.

LIU Sifeng,YANG Yingjie,CAO Ying,et al.A summary on the research of GRA models[J].Grey Systems:Theory and Application,2013,3(1):7-15.

JORDAN M I,MITCHELL T M.Machine learning:trends,perspectives,and prospects[J].Science,2015,349(6245):255-260.

BZDOK D,KRZYWINSKI M,ALTMAN N.Machine learning:a primer[J].Nature Methods,2017,14(12):1119-1120.

ANIFOWOSE F.Advances in hybrid computational intelligence application in oil and gas reservoir characterization[C]//SPE Saudi Arabia section Young Professionals Technical Symposium.Dhahran:SPE,2012.

龚斌,王虹雅,王红娜,等.基于大数据分析算法的深部煤层气地质—工程一体化智能决策技术[J].石油学报,2023,44(11):1949-1958. GONG Bin,WANG Hongya,WANG Hongna,et al.Integrated intelligent decision-making technology for deep coalbed methane geology and engineering based on big data analysis algorithms[J].Acta Petrolei Sinica,2023,44(11):1949-1958.

ANIFOWOSE F A,ABDULRAHEEM A,AL-SHUHAIL A,et al.Improved permeability prediction from seismic and log data using artificial intelligence techniques[C]//SPE Middle East Oil and Gas Show and Conference.Manama:SPE,2013.

AL-MARHOUN M A,OSMAN E A.Using artificial neural networks to develop new PVT correlations for Saudi crude oils[C]//Abu Dhabi International Petroleu m Exhibition and Conference.Abu Dhabi:SPE,2002.

TARIQ Z,ELKATATNY S,MAHMOUD M,et al.A new technique to develop rock strength correlation using artificial intelligence tools[C]//SPE Reservoir Characterisation and Simulation Conference and Exhibition.Abu Dhabi:SPE,2017.

SPEISER J L,MILLER M E,TOOZE J,et al.A comparison of random forest variable selection methods for classification prediction modeling[J].Expert Systems with Application,2019,134:93-101.

张茂林,梅海燕,顾鸿君,等.克拉玛依油田五2西区克下组油藏气水交替驱开发效果预测及分析[J].中国海上油气,2006,18(1):31-35. ZHANG Maolin,MEI Haiyan,GU Hongjun,et al.Predicting and analyzing effects of water and gas alternate drive on oil production of Lower Kelamayi reservoir in the western Wu-Ⅱ area,Kelamayi oilfield[J].China Offshore Oil and Gas,2006,18(1):31-35.

宫汝祥,张雪娜,黄子俊,等.海上油田烃气驱气窜规律及封窜策略研究[J].当代化工,2024,53(6):1425-1430. GONG Ruxiang,ZHANG Xuena,HUANG Zijun,et al.Research on gas channeling law and sealing strategy of hydrocarbon gas drive in offshore oilfield[J].Contemporary Chemical Industry,2024,53(6):1425-1430.

杜俊辉.中渗透油藏天然气驱气窜规律分析及封堵对策研究[D].大庆:东北石油大学,2024. DU Junhui.Analysis of gas channeling law of natural gas flooding in medium permeability reservoirs and research on plugging countermeasures[D].Daqing:Northeast Petroleum University,2024.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Numerical simulation of the 3D oil-water phase dynamic permeability for low-permeability reservoirs

Study on Flow Patterns in the Filtration and Backwashing Processes of Deep Bed Filters

Comparison of Numerical Simulations of Oxygen Production via Water Electrolysis Coupled With Nitrogen-Free Combustion and Traditional Cement Production Technology

Multi Objective Performance Optimization of PEM Electrolyzer Based on Flow Field Regulation

Advances in Bipolar Plate Flow Field Design for Proton Exchange Membrane Water Electrolyzer

Related Author

YIN Zhilin1 SUN Wenjing1 YAO Jun2

孙文静

姚军

HE Mingzhe

WANG Jiangyun

LIN Yu

WANG Qinghong

CHEN Chunmao

Related Institution

Exploration and Development Research Institute,PetroChina Daqing Oilfield Company Limited

College of Petroleum Engineering,China University of Petroleum

College of Mechanical and Transportation Engineering， China University of Petroleum

State Key Laboratory of Heavy Oil Processing， China University of Petroleum

College of Engineering， China University of Petroleum-Beijing at Karamay

AI问答

⁰