大数据驱动下的智能气藏数字孪生系统关键技术及应用研究

孙亚隆; 牛浩; 张永利; 陈宇轩; 古毅; 方军龄; 张仕帆

doi:10.13809/j.cnki.cn32-1825/te.2024614

欢迎来到能源电力期刊网！

您当前的位置：

首页 >

文章列表页 >

大数据驱动下的智能气藏数字孪生系统关键技术及应用研究

综合研究 | 更新时间：2026-03-10

- 大数据驱动下的智能气藏数字孪生系统关键技术及应用研究
- Research on key technologies and applications of intelligent gas reservoir digital twin system driven by big data
- 油气藏评价与开发 2026年16卷第2期页码：479-488
- 作者机构：
  
  1.陕西延长石油（集团）有限责任公司气田公司，陕西延安 716000
  2.延安市天然气勘探开发工程技术研究中心，陕西延安 716000
  3.特雷西能源科技股份有限公司，浙江杭州 310000
  4.中国地质大学（武汉）未来技术学院，湖北武汉 430074
- 作者简介：
  
  孙亚隆（1985—），男，硕士，工程师，主要从事油气田地质勘探与开发研究工作。地址：陕西省延安市宝塔区南泥湾镇，邮政编码：716006。E-mail：1302501330@qq.com
  张仕帆（1996—），男，在读博士研究生，主要从事人工智能辅助油气藏开发及提高采收率方面的研究。地址：湖北省武汉市洪山区鲁磨路388号，邮政编码：430074。E-mail：zhangshifan0314@163.com
- 基金信息：
  
  国家重点研发计划项目“地质资源精准开发风险预测的大数据智能分析技术及平台建设”(2022YFF0801202)
- DOI：10.13809/j.cnki.cn32-1825/te.2024614
  中图分类号： TE319
- 收稿：2025-07-04，
  
  纸质出版：2026-03-26
- 稿件说明：
移动端阅览
孙亚隆, 牛浩, 张永利, 等. 大数据驱动下的智能气藏数字孪生系统关键技术及应用研究[J]. 油气藏评价与开发, 2026, 16(2): 479-488.

SUN Yalong, NIU Hao, ZHANG Yongli, et al. Research on key technologies and applications of intelligent gas reservoir digital twin system driven by big data[J]. Petroleum Reservoir Evaluation and Development, 2026, 16(2): 479-488.
孙亚隆, 牛浩, 张永利, 等. 大数据驱动下的智能气藏数字孪生系统关键技术及应用研究[J]. 油气藏评价与开发, 2026, 16(2): 479-488. DOI： 10.13809/j.cnki.cn32-1825/te.2024614.

SUN Yalong, NIU Hao, ZHANG Yongli, et al. Research on key technologies and applications of intelligent gas reservoir digital twin system driven by big data[J]. Petroleum Reservoir Evaluation and Development, 2026, 16(2): 479-488. DOI： 10.13809/j.cnki.cn32-1825/te.2024614.

摘要

传统油气藏研究方法通常依赖各专业领域的分工合作，通过接力推进的方式进行研究与开发。然而，这种模式难以实现各环节之间的高效协同，且在整体效益优化方面存在局限。为解决这一问题，研究提出了一种智能气藏数字孪生系统，融合人工智能算法适配、数据预处理、数据分析应用及模型自动更新预测四大核心技术，旨在构建一个集多学科协同、高效数据利用与动态优化预测于一体的综合平台。研究表明：针对勘探与开发过程中数据的多维度、异构性与高噪声特性，系统通过异常值处理、缺失值填补、数据变换、统计分析与质量评估于一体的数据预处理方案，保障了数据的准确性与可靠性；通过封装随机森林、梯度提升等人工智能算法，系统能够构建多参数与气藏产能之间的最佳回归模型，重点解决产量分析、压裂分析和“甜点”预测三大关键问题，从而提高产量预测精度、优化压裂施工参数，并有效识别“甜点”区域。此外，系统采用自动建模引擎，动态更新气藏的构造模型、相模型和属性模型，并结合模拟器引擎进行实时模拟、跟踪与预测，保证了模型在气藏开发过程中的适应性与准确性。系统借助数字孪生技术，在虚拟空间中构建了与气藏实体一致的虚拟模型，实现了对气藏全生命周期的分析、预测与优化管理。研究成果为推动气藏管理向智能化、精细化与高效化方向发展提供了有力的理论支撑和技术保障。

Abstract

Traditional oil and gas reservoir research methods usually rely on the division of labor and collaboration among different specialized disciplines

with research and development conducted in a relay-style approach. However

this model faces challenges in achieving efficient collaboration across different stages and has limitations in optimizing overall benefits. To address this issue

an intelligent gas reservoir digital twin system was proposed

integrating four core technologies: artificial intelligence algorithm adaptation

data preprocessing

data analysis applications

and automatic model updating and prediction

aiming to construct a comprehensive platform that integrates multidisciplinary collaboration

efficient data utilization

and dynamic optimization and prediction. The results showed that

in response to the multidimensional

heterogeneous

and high-noise characteristics of data during the exploration and development process

the system ensured data accuracy and reliability through an integrated data preprocessing scheme incorporating outlier handling

missing value imputation

data transformation

statistical analysis

and quality assessment. By encapsulating artificial intelligence algorithms such as random forest and gradient boosting

the system was able to construct the optimal regression model between multiple parameters and gas reservoir productivity

focusing on three key problems—production analysis

fracturing analysis

and “sweet spot” prediction—thereby improving production prediction accuracy

optimizing fracturing operation parameters

and effectively identifying “sweet spot” areas. In addition

the system adopted an automatic modeling engine to dynamically update the structural

phase

and attribute models of the gas reservoir

and combined it with a simulator engine for real-time simulation

tracking

and prediction

thereby ensuring model adaptability and accuracy throughout the gas reservoir development process. By leveraging digital twin technology

the system constructed a virtual model consistent with the physical gas reservoir in virtual space

enabling analysis

prediction

and optimized management throughout the entire lifecycle of the gas reservoir. The research results provide strong theoretical support and technical assurance for promoting the development of gas reservoir management toward intelligent

refined

and efficient practices.

关键词

Keywords

references

刘文岭 , 韩大匡 . 数字孪生油气藏: 智慧油气田建设的新方向 [J ] . 石油学报 , 2022 , 43 ( 10 ): 1450 - 1461 .

LIU Wenling , HAN Dakuang . Digital twin system of oil and gas reservoirs: A new direction for smart oil and gas field construction [J ] . Acta Petrolei Sinica , 2022 , 43 ( 10 ): 1450 - 1461 .

姚军 , 孙海 , 李爱芬 , 等 . 现代油气渗流力学体系及其发展趋势 [J ] . 科学通报 , 2018 , 63 ( 4 ): 425 - 451 .

YAO Jun , SUN Hai , LI Aifen , et al . Modern system of multiphase flow in porous media and its development trend [J ] . Chinese Science Bulletin , 2018 , 63 ( 4 ): 425 - 451 .

杨剑锋 , 杜金虎 , 杨勇 , 等 . 油气行业数字化转型研究与实践 [J ] . 石油学报 , 2021 , 42 ( 2 ): 248 - 258 .

YANG Jianfeng , DU Jinhu , YANG Yong , et al . Research and practice on digital transformation of the oil and gas industry [J ] . Acta Petrolei Sinica , 2021 , 42 ( 2 ): 248 - 258 .

刘金朋 , 钟明睿 , 杜皓 . 基于人工智能的残余绕射多次波衰减技术研究及应用 [J ] . 石油物探 , 2024 , 63 ( 6 ): 1177 - 1185 .

LIU Jinpeng , ZHONG Mingrui , DU Hao . Diffracted multiples attenuation based on artificial intelligence [J ] . Geophysical Prospecting for Petroleum , 2024 , 63 ( 6 ): 1177 - 1185 .

陶飞 , 刘蔚然 , 刘检华 , 等 . 数字孪生及其应用探索 [J ] . 计算机集成制造系统 , 2018 , 24 ( 1 ): 1 - 18 .

TAO Fei , LIU Weiran , LIU Jianhua , et al . Digital twin and its potential application exploration [J ] . Computer Integrated Manufacturing Systems , 2018 , 24 ( 1 ): 1 - 18 .

唐文虎 , 陈星宇 , 钱瞳 , 等 . 面向智慧能源系统的数字孪生技术及其应用 [J ] . 中国工程科学 , 2020 , 22 ( 4 ): 74 - 85 .

TANG Wenhu , CHEN Xingyu , QIAN Tong , et al . Technologies and applications of digital twin for developing smart energy systems [J ] . Strategic Study of CAE , 2020 , 22 ( 4 ): 74 - 85 .

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 .

计秉玉 , 张文彪 , 何应付 , 等 . 油藏地质建模与数值模拟一体化内涵及发展趋势 [J ] . 石油学报 , 2024 , 45 ( 7 ): 1152 - 1162 .

JI Bingyu , ZHANG Wenbiao , HE Yingfu , et al . Connotation and development trends of integration between geological reservoir modeling and numerical reservoir simulation [J ] . Acta Petrolei Sinica , 2024 , 45 ( 7 ): 1152 - 1162 .

FENG D , WANG J G , ZHANG H , et al . Application and prospect of digital twin in oil and gas drilling & completion engineering [J ] . Petroleum Drilling Techniques , 2024 , 52 ( 5 ): 26 - 34 .

李泽伟 , 朱培民 , 张昊 , 等 . 基于MultiRes-Unet神经网络的三维断层识别研究 [J ] . 石油物探 , 2024 , 63 ( 1 ): 91 - 103 .

LI Zewei , ZHU Peimin , ZHANG Hao , et al . 3D fault identification based on MultiRes-Unet neural network [J ] . Geophysical Prospecting for Petroleum , 2024 , 63 ( 1 ): 91 - 103 .

何清 , 李宁 , 罗文娟 , 等 . 大数据下的机器学习算法综述 [J ] . 模式识别与人工智能 , 2014 , 27 ( 4 ): 327 - 336 .

HE Qing , LI Ning , LUO Wenjuan , et al . A survey of machine learning algorithms for big data [J ] . Pattern Recognition and Artificial Intelligence , 2014 , 27 ( 4 ): 327 - 336 .

尹宝才 , 王文通 , 王立春 . 深度学习研究综述 [J ] . 北京工业大学学报 , 2015 , 41 ( 1 ): 48 - 59 .

YIN Baocai , WANG Wentong , WANG Lichun . Review of deep learning [J ] . Journal of Beijing University of Technology , 2015 , 41 ( 1 ): 48 - 59 .

秦峰 , 闫正和 , 唐圣来 , 等 . 基于深度学习的代理模型在实际气藏三维模拟中的应用 [J ] . 油气地质与采收率 , 2022 , 29 ( 1 ): 152 - 159 .

QIN Feng , YAN Zhenghe , TANG Shenglai , et al . Application of agent models based on deep learning in actual three-dimensional gas reservoir simulation [J ] . Petroleum Geology and Recovery Efficiency , 2022 , 29 ( 1 ): 152 - 159 .

舒红林 , 王利芝 , 尹开贵 , 等 . 地质工程一体化实施过程中的页岩气藏地质建模 [J ] . 中国石油勘探 , 2020 , 25 ( 2 ): 84 - 95 .

SHU Honglin , WANG Lizhi , YIN Kaigui , et al . Geological modeling of shale gas reservoir during the implementation process of geology-engineering integration [J ] . China Petroleum Exploration , 2020 , 25 ( 2 ): 84 - 95 .

柳洁 , 田冷 , 刘士鑫 , 等 . 基于复合机器算法的致密气井产能预测模型: 以鄂尔多斯盆地SM区块为例 [J ] . 大庆石油地质与开发 , 2024 , 43 ( 5 ): 69 - 78 .

LIU Jie , TIAN Leng , LIU Shixin , et al . Prediction model of tight gas well productivity based on composite machine algorithm: Taking Block SM of Ordos Basin as an example [J ] . Petroleum Geology & Oilfield Development in Daqing , 2024 , 43 ( 5 ): 69 - 78 .

薛永超 , 袁志乾 , 金青爽 , 等 . 基于深度森林算法的油井产量预测 [J ] . 科学技术与工程 , 2022 , 22 ( 11 ): 4327 - 4334 .

XUE Yongchao , YUAN Zhiqian , JIN Qingshuang , et al . Production prediction of oil well based on deep forest algorithm [J ] . Science Technology and Engineering , 2022 , 22 ( 11 ): 4327 - 4334 .

郭子熙 , 马骉 , 张帅 , 等 . 深度学习在油气产量预测中的研究进展与技术展望 [J ] . 天然气工业 , 2024 , 44 ( 9 ): 88 - 98 .

GUO Zixi , MA Biao , ZHANG Shuai , et al . Research status and prospects of deep learning in oil and gas production prediction [J ] . Natural Gas Industry , 2024 , 44 ( 9 ): 88 - 98 .

蒋文超 . 基于机器学习与模型融合的大庆油田SN区块油井压裂效果预测技术 [J ] . 大庆石油地质与开发 , 2023 , 42 ( 1 ): 64 - 72 .

JIANG Wenchao . Prediction model for production well hydraulic fracturing effect of Block SN in Daqing Oilfield based on machine learning and model ensemble [J ] . Petroleum Geology & Oilfield Development in Daqing , 2023 , 42 ( 1 ): 64 - 72 .

盖建 . 基于自动机器学习的采油井压裂效果预测方法 [J ] . 油气地质与采收率 , 2023 , 30 ( 1 ): 161 - 170 .

GAI Jian . Prediction method for hydraulic fracturing effect of oil production well based on automatic machine learning technology [J ] . Petroleum Geology and Recovery Efficiency , 2023 , 30 ( 1 ): 161 - 170 .

张荔 , 王博 , 吕振虎 , 等 . 非常规储层整体压裂智能优化 [J ] . 新疆石油天然气 , 2024 , 20 ( 4 ): 36 - 43 .

ZHANG Li , WANG Bo , LYU Zhenhu , et al . Intelligent optimization of integral fracturing in unconventional reservoirs [J ] . Xinjiang Oil & Gas , 2024 , 20 ( 4 ): 36 - 43 .

郭建春 , 张宇 , 曾凡辉 , 等 . 非常规油气储层智能压裂技术研究进展与展望 [J ] . 天然气工业 , 2024 , 44 ( 9 ): 13 - 26 .

GUO Jianchun , ZHANG Yu , ZENG Fanhui , et al . Research progress and prospects of intelligent fracturing technology for unconventional reservoirs [J ] . Natural Gas Industry , 2024 , 44 ( 9 ): 13 - 26 .

王冠民 , 祝新怡 , 刘海 , 等 . 沉积微相在致密砂岩可压裂性分析中的应用: 以鄂尔多斯盆地陇东地区延长组7段为例 [J ] . 地质力学学报 , 2024 , 30 ( 6 ): 893 - 905 .

WANG Guanmin , ZHU Xinyi , LIU Hai , et al . The application of sedimentary microfacies on the fracability of tight sandstone reservoir in Chang 7 member of Longdong area in the Ordos Basin [J ] . Journal of Geomechanics , 2024 , 30 ( 6 ): 893 - 905 .

李根生 , 王天宇 , 李杰 , 等 . 多能融合下油气智能绿色开发路径与展望 [J ] . 新疆石油天然气 , 2025 , 21 ( 3 ): 1 - 13 .

LI Gensheng , WANG Tianyu , LI Jie , et al . Pathways and prospects for intelligent and green development of oil and gas driven by multi-energy integration [J ] . Xinjiang Oil & Gas , 2025 , 21 ( 3 ): 1 - 13 .

张菲菲 , 王茜 , 王学迎 , 等 . 油气井工程多源多模态数据融合技术与展望 [J ] . 天然气工业 , 2024 , 44 ( 9 ): 152 - 166 .

ZHANG Feifei , WANG Xi , WANG Xueying , et al . Multi-source and multi-modal data fusion technology and its prospect in oil and gas well engineering [J ] . Natural Gas Industry , 2024 , 44 ( 9 ): 152 - 166 .

宋洪庆 , 都书一 , 周园春 , 等 . 油气资源开发的大数据智能平台及应用分析 [J ] . 工程科学学报 , 2021 , 43 ( 2 ): 179 - 192 .

SONG Hongqing , DU Shuyi , ZHOU Yuanchun , et al . Big data intelligent platform and application analysis for oil and gas resource development [J ] . Chinese Journal of Engineering , 2021 , 43 ( 2 ): 179 - 192 .

闵超 , 文国权 , 李小刚 , 等 . 可解释机器学习在油气领域人工智能中的研究进展与应用展望 [J ] . 天然气工业 , 2024 , 44 ( 9 ): 114 - 126 .

MIN Chao , WEN Guoquan , LI Xiaogang , et al . Research progress and application prospect of interpretable machine learning in artificial intelligence of oil and gas industry [J ] . Natural Gas Industry , 2024 , 44 ( 9 ): 114 - 126 .

郭子熙 , 马骉 , 张帅 , 等 . 深度学习在油气产量预测中的研究进展与技术展望 [J ] . 天然气工业 , 2024 , 44 ( 9 ): 88 - 98 .

GUO Zixi , MA Biao , ZHANG Shuai , et al . Research status and prospects of deep learning in oil and gas production prediction [J ] . Natural Gas Industry , 2024 , 44 ( 9 ): 88 - 98 .

光新军 , 马广军 , 闫娜 , 等 . 智慧油气藏数字孪生技术新进展与发展思考 [J ] . 世界石油工业 , 2025 , 32 ( 2 ): 13 - 22 .

GUANG Xinjun , MA Guangjun , YAN Na , et al . New progress and development considerations of digital twin technology for smart oil and gas reservoirs [J ] . World Petroleum Industry , 2025 , 32 ( 2 ): 13 - 22 .

于强 , 王宝江 , 张禄明 , 等 . 深度学习技术在油气勘探中的研究进展与应用挑战 [J ] . 天然气工业 , 2025 , 45 ( 5 ): 43 - 56 .

YU Qiang , WANG Baojiang , ZHANG Luming , et al . Research progress and application challenges of deep learning technology in oil and gas exploration [J ] . Natural Gas Industry , 2025 , 45 ( 5 ): 43 - 56 .

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 .

范彩伟 , 周刚 , 周凡 , 等 . 基于OBC数据方位优选的甜点叠前预测技术及应用: 以涠西南凹陷流三段为例 [J ] . 石油物探 , 2025 , 64 ( 6 ): 1149 - 1161 .

FAN Caiwei , ZHOU Gang , ZHOU Fan , et al . Prestack sweet spotting based on OBC data azimuth optimization: A case study of Liu3 Member in Weixinan Sag [J ] . Geophysical Prospecting for Petroleum , 2025 , 64 ( 6 ): 1149 - 1161 .

张卫卫 , 肖张波 , 易浩 , 等 . 致密砂岩储层“双甜点”识别方法在南海东部陆丰地区古近系储层的应用 [J ] . 石油物探 , 2024 , 63 ( 1 ): 217 - 228 .

ZHANG Weiwei , XIAO Zhangbo , YI Hao , et al . Geologic-engineering sweet spotting in Paleogene tight sandstone reservoirs, Lufeng, eastern South China Sea [J ] . Geophysical Prospecting for Petroleum , 2024 , 63 ( 1 ): 217 - 228 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

水平井井地模型人工智能预测方法研究与应用

非常规油气勘探开发地质工程一体化管理：概念模型与实施路径

基于体积源的气藏渗流与水平井筒流动耦合的非稳态模型

石英砂在苏里格致密砂岩气藏压裂的适应性