基于数据驱动的储气库井底压力预测

蒋华全; 曾娟; 李力民; 温廷钧; 周俊池; 陈小凡; 王剑

doi:10.3969/j.issn.1006-6535.2025.04.014

特种油气藏 >

2025 , Vol. 32 >Issue 4: 122 - 129

DOI: https://doi.org/10.3969/j.issn.1006-6535.2025.04.014

油藏工程

基于数据驱动的储气库井底压力预测

蒋华全 ,
曾娟 ,
李力民 ,
温廷钧 ,
周俊池 ,
陈小凡 ,
王剑

展开

1.中国石油西南油气田重庆相国寺储气库有限公司,重庆 401121;
2.西南石油大学油气藏地质及开发工程全国重点实验室,四川成都 610500

蒋华全(1970—),男,高级工程师,1993年毕业于西安石油学院采油工程专业,现主要从事储气库生产技术与管理方面的研究工作。

收稿日期: 2024-08-25

修回日期: 2025-04-01

网络出版日期: 2025-09-03

基金资助

四川省科技计划项目“致密储层复杂结构并多尺度非线性流动耦合模型研究”(2024NSFSC2012)

收起

Data-driven bottomhole pressure prediction for gas storage reservoirs

JIANG Huaquan ,
ZENG Juan ,
LI Limin ,
WEN Tingjun ,
ZHOU Junchi ,
CHEN Xiaofan ,
WANG Jian

Expand

1. PetroChina Southwest Oil & Gas Field Chongqing Xiangguosi Gas Storage Co., Ltd., Chongqing 401121, China;
2. State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu, Sichuan 610500, China

Received date: 2024-08-25

Revised date: 2025-04-01

Online published: 2025-09-03

Fold

摘要

针对储气库井底压力难以准确快速获取的问题,以相国寺储气库为研究对象,基于数据驱动原理,运用监督学习方法,对该储气库10口井共14组数据的12种特征参数进行了分析,开展井底压力预测研究,建立了高斯过程回归(GPR)、支持向量回归(SVR)和人工神经网络(ANN)3种井底压力预测模型,并对模型预测精度进行评价。研究表明:影响井底压力的主要因素为日注采量、井口压力、地层压力和井口温度;SVR、GPR、ANN模型的预测精度分别为99.2%、97.4%、95.1%。说明数据驱动方法能有效预测井底压力,其中,SVR模型可为储气库的注采调控提供更可靠的预测手段。该研究对提高储气库运行的安全性和经济性具有重要的实践指导意义。

关键词： 地下储气库; 井底压力; 机器学习; 数据驱动; 生产监测数据; 预测模型

本文引用格式

蒋华全 , 曾娟 , 李力民 , 温廷钧 , 周俊池 , 陈小凡 , 王剑 . 基于数据驱动的储气库井底压力预测[J]. 特种油气藏, 2025 , 32(4) : 122 -129 . DOI: 10.3969/j.issn.1006-6535.2025.04.014

Abstract

For the difficulty in accurately and swiftly obtaining bottomhole pressure in gas storage reservoirs,in this study,Xiangguosi Gas Storage was taken as the research object to analyze 12 characteristic parameters from 14 datasets across 10 wells based on the data-driven principles and supervised learning methods.Three bottomhole pressure prediction models:Gaussian Process Regression (GPR),Support Vector Regression (SVR),and Artificial Neural Network (ANN),were developed and evaluated for prediction accuracy.The study shows that the main factors influencing bottomhole pressure are daily injection-production volume,wellhead pressure,formation pressure,and wellhead temperature,and the prediction accuracy of SVR,GPR,and ANN models are 99.2%,97.4%,and 95.1%,respectively.This indicates that data-driven methods can effectively predict bottomhole pressure,with the SVR model offering a more reliable prediction for gas storage injection-production control.This research is of great practical significance for enhancing the safety and economy of gas storage operations.

Key words： underground gas storage; bottomhole pressure; machine learning; data-driven; production monitoring data; prediction model

参考文献

[1] 丁国生,魏欢.中国地下储气库建设20年回顾与展望[J].油气储运,2020,39(1):25-31.
DING Guosheng,WEI Huan.Review on 20 years′ UGS construction in China and the prospect[J].Oil & Gas Storage and Transportation,2020,39(1):25-31.
[2] 江同文,王锦芳,王正茂,等.地下储气库与天然气驱油协同建设实践与认识[J].天然气工业,2021,41(9):66-74.
JIANG Tongwen,WANG Jinfang,WANG Zhengmao,et al.Practice and understanding of collaborative construction of underground gas storage and natural gas flooding[J].Natural Gas Industry,2021,41(9):66-74.
[3] 汤勇,龙科吉,王皆明,等.凝析气藏型储气库多周期注采过程中流体相态变化特征[J].石油勘探与开发,2021,48(2):337-346.
TANG Yong,LONG Keji,WANG Jieming,et al.Change of phase state during multi-cycle injection and production process of condensate gas reservoir based underground gas storage[J].Petroleum Exploration and Development,2021,48(2):337-346.
[4] CULLENDER M H,SMITH R V.Practical solution of gas-flow equations for wells and pipelines with large temperature gradients[J].Transactions of the AIME,1956,207(1):281-287.
[5] HAGEDORN A R,BROWN K E.Experimental study of pressure gradients occurring during continuous two-phase flow in small-diameter vertical conduits[J].Journal of Petroleum Technology,1965,17(4):475-484.
[6] HASAN A R,KABIR C S,SAYARPOUR M.Simplified two-phase flow modeling in wellbores[J].Journal of Petroleum Science and Engineering,2010,72(1):42-49.
[7] 丁国生,王云,完颜祺琪,等.不同类型复杂地下储气库建库难点与攻关方向[J].天然气工业,2023,43(10):14-23.
DING Guosheng,WANG Yun,WANYAN Qiqi,et al.Construction difficulties and research directions of various complex UGSs[J].Natural Gas Industry,2023,43(10):14-23.
[8] 廖伟,罗双涵,胡书勇,等.气藏型储气库出砂规律研究的新方法[J].西南石油大学学报(自然科学版),2023,45(3):119-130.
LIAO Wei,LUO Shuanghan,HU Shuyong,et al.A New Method for the study of sand production in gas reservoir storage[J].Journal of Southwest Petroleum University (Science & Technology Edition),2023,45(3):119-130.
[9] 李阳,廉培庆,薛兆杰,等.大数据及人工智能在油气田开发中的应用现状及展望[J].中国石油大学学报(自然科学版),2020,44(4):1-11.
LI Yang,LIAN Peiqing,XUE Zhaojie,et al.Application status and prospect of big data and artificial intelligence in oil and gas field development[J].Journal of China University of Petroleum(Edition of Natural Sciences),2020,44(4):1-11.
[10] 卜亚辉.基于机器学习的高含水油田剩余油预测方法[J].油气地质与采收率,2022,29(4):135-142.
BU Yahui.Prediction of remaining oil in high water cut oilfield based on machine learning[J].Petroleum Geology and Recovery Efficiency,2022,29(4):135-142.
[11] 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.
[12] 杨琨,罗山贵,花凌旭,等.致密砾岩油藏压裂“甜点”预测研究——以玛18井区为例[J].科学技术与工程,2022,22(32):14174-14183.
YANG Kun,LUO Shangui,HUA Lingxu,et al.Investigation on the fracturing sweet spot prediction of conglomerate tight oil reservoir:a case study of the Ma 18 Well Block[J].Science Technology and Engineering,2022,22(32):14174-14183.
[13] AHMADI M A,CHEN Z.Machine learning models to predict bottom hole pressure in multi-phase flow in vertical oil production wells[J].The Canadian Journal of Chemical Engineering,2019,97(11):2928-2940.
[14] ALI A,ALIYUDA K,ELMITWALLY N,et al.Towards more accurate and explainable supervised learning-based prediction of deliverability for underground natural gas storage[J].Applied Energy,2022,327:120098.
[15] RATHNAYAKE S,RAJORA A,FIROUZI M.A machine learning-based predictive model for real-time monitoring of flowing bottom-hole pressure of gas wells[J].Fuel,2022,317:123524.
[16] 刘慧,丁心鲁,张士杰,等.地下储气库注气过程一体化压力及地层参数计算方法[J].石油钻探技术,2022,50(6):64-71.
LIU Hui,DING Xinlu,ZHANG Shijie,et al.Integrated calculation method of pressure and formation parameters in gas injection process of underground gas storage[J].Petroleum Drilling Techniques,2022,50(6):64-71.
[17] 隋顾磊,傅钰江,朱洪翔,等.基于数据驱动的地下储气库地层压力预测[J].深圳大学学报(理工版),2023,40(3):353-360.
SUI Gulei,FU Yujiang,ZHU Hongxiang,et al.Prediction of formation pressure in underground gas storage based on data-driven method[J].Journal of Shenzhen University(Science & Engineering),2023,40(3):353-360.
[18] 祝兆鹏,张瑞,宋先知,等.数据拓展和增量更新的井底压力实时预测方法[J].石油机械,2023,51(6):1-10.
ZHU Zhaopeng,ZHANG Rui,SONG Xianzhi,et al.Real-time prediction of bottomhole pressure based on data expansion and incremental update[J].China Petroleum Machinery,2023,51(6):1-10.
[19] 赵昱超,罗瑜,李隆新,等.地下储气库地应力模拟研究与地质完整性评估——以相国寺为例[J].地质力学学报,2022,28(4):523-536.
ZHAO Yuchao,LUO Yu,LI Longxin,et al.In-situ stress simulation and integrity evaluation of underground gas storage:a case study of the Xiangguosi underground gas storage,Sichuan,SW China[J].Journal of Geomechanics,2022,28(4):523-536.
[20] MYERS L,SIROIS M J.Spearman Correlation Coefficients,Differences between[M].New York:John Wiley & Sons,Inc,2004:12.
[21] 曾凡辉,胡大淦,张宇,等.数据驱动的页岩油水平井压裂施工参数智能优化研究[J].石油钻探技术,2023,51(5):78-87.
ZENG Fanhui,HU Dagan,ZHANG Yu,et al.Research on data-driven intelligent optimization of fracturing treatment parameters for shale oil horizontal wells[J].Petroleum Drilling Techniques,2023,51(5):78-87.
[22] 盛茂,张家麟,张彦军,等.基于数据驱动的水平井暂堵压裂有效性评价新模型[J].天然气工业,2023,43(9):132-140.
SHENG Mao,ZHANG Jialin,ZHANG Yanjun,et al.A new data-driven effectiveness evaluation model of temporary plugging fracturing for horizontal wells[J].Natural Gas Industry,2023,43(9):132-140.
[23] 沈英.t检验和F检验在化学测试质控数据趋势分析中的应用[J].检验检疫学刊,2019,29(2):105-107.
SHEN Ying.The application of t-test and F-test in trend analysis of chemical test quality data[J].Journal of Inspection and Quarantine,2019,29(2):105-107.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献