一种基于知识图谱和随机森林算法的致密气井产能预测方法

李文倚; 侯明雨; 全航; 余杰

doi:10.3969/j.issn.1006-6535.2024.05.009

特种油气藏 >

2024 , Vol. 31 >Issue 5: 77 - 84

DOI: https://doi.org/10.3969/j.issn.1006-6535.2024.05.009

油藏工程

一种基于知识图谱和随机森林算法的致密气井产能预测方法

李文倚 ,
侯明雨 ,
全航 ,
余杰

展开

1.中国海油研究总院有限责任公司,北京 100028;
2.成都理工大学,四川成都 610059

李文倚(1971—),男,高级工程师,1992年毕业于河北大学油气田开发专业,现主要从事信息集成、数据库应用系统等方面的研究工作。

收稿日期: 2023-07-03

修回日期: 2024-06-07

网络出版日期: 2024-12-24

基金资助

国家自然科学基金面上项目“页岩储层纳米孔隙结构表征及渗流机理研究”(51674044)

收起

A Productivity Prediction Method for Tight Gas Wells Based on Knowledge Graph and Random Forest Algorithm

Li Wenyi ,
Hou Mingyu ,
Quan Hang ,
Yu Jie

Expand

1. CNOOC Research Institute Ltd.,Beijing 100028,China;
2. Chengdu University of Technology,Chengdu,Sichuan 610059,China

Received date: 2023-07-03

Revised date: 2024-06-07

Online published: 2024-12-24

Fold

摘要

气井产能预测受地质、工程等多种因素影响,传统的数学解析、数值模拟等方法难以快速准确预测致密气井产能。针对上述问题,基于大数据及机器学习的思想,创新性地融合了知识图谱和随机森林算法,形成了一种针对致密气井的产能预测方法。通过数据预处理对不同类型的基础数据进行规范化处理,采用实体识别和链接技术将不同数据源的实体整合到知识图谱中。使用关系抽取和建模技术,建立实体之间的关系和属性,形成完整的知识图谱,准确预测产能。在此基础上,依托随机森林机器学习算法建立致密气井产能预测模型,利用模型对秋林区块致密气井产能进行预测,预测精度达到89.7%。该方法可以在开发前期快速准确预测气井产能,大幅度提高预测的准确度,为致密气开发产能部署和高产井的发掘提供决策支持。

关键词： 致密气; 机器学习; 知识图谱算法; 随机操作算法; 产能预测

本文引用格式

李文倚 , 侯明雨 , 全航 , 余杰 . 一种基于知识图谱和随机森林算法的致密气井产能预测方法[J]. 特种油气藏, 2024 , 31(5) : 77 -84 . DOI: 10.3969/j.issn.1006-6535.2024.05.009

Abstract

The productivity prediction of gas well is influenced by various factors such as geology and engineering.Traditional methods like mathematical analysis and numerical simulation struggle to quickly and accurately predict the productivity of tight gas wells.To address this issue,an innovative method combining knowledge graph and the random forest algorithm is proposed based on big data and machine learning concepts to develop a productivity prediction method of tight gas wells.Data preprocessing standardizes different types of basic data,and entity recognition and linking technologies integrate entities from various data sources into the knowledge graph.Relationship extraction and modeling techniques are used to establish relationships and attributes among entities,developing a complete knowledge graph for accurate productivity prediction.On this basis,a productivity prediction model for tight gas wells is developed using the random forest machine learning algorithm,and the model predicts the productivity of tight gas wells in the Qiulin Block with an accuracy of 89.7%.This method allows for rapid and accurate productivity predictions in the early stages of development,significantly improving prediction accuracy and providing decision support for productivity deployment and high-yield well cultivation in tight gas development.

Key words： tight gas; machine learning; knowledge graph algorithm; ramdom forest algorithm; productivity prediction

参考文献

[1] 陈正阳.基于大数据技术的页岩气产量预测[D].成都:电子科技大学,2022.
CHEN Zhengyang.Prediction of shale gas production based on big data technology[D].Chengdu:University of Electronic Science and Technology of China,2022.
[2] JOSHI S D.Augmentation of well productivity using slant and horizontal wells[J].Journal of Petroleum Technology,1986,40(6):729-739.
[3] MUKHERJEE H,ECONOMIDES M J.A parametric comparison of horizontal and vertical well performance[J].SPE Formation Evaluation,1991,6(2):209-216.
[4] 宁正福,韩树刚,程林松,等.低渗透油气藏压裂水平井产能计算方法[J].石油学报,2002,23(2):68-71.
NING Zhengfu,HAN Shugang,CHENG Linsong,et al.Productivity calculation method of fractured horizontal wells in low permeability oil or gas field[J].Acta Petrolei Sinica,2002,23(2):68-71.
[5] SHEIKHOUSHAGHI A,GHARAEI N Y,NIKOOFARD A.Application of rough neural network to forecast oil production rate of an oil field in a comparative study[J].Journal of Petroleum Science and Engineering,2022,209:109935.
[6] 郭俊葳.构造地质模型知识图谱构建及表征方法研究[D].成都:电子科技大学,2022.
GUO Junwei.Construction and representation methods of structural geological model knowledge graph[D].Chengdu:University of Electronic Science and Technology of China,2022.
[7] 陆锋,诸云强,张雪英.时空知识图谱研究进展与展望[J].地球信息科学学报,2023,25(6):1091-1105.
LU Feng,ZHU Yunqiang,ZHANG Xueying.Spatiotemporal knowledge graph:advances and perspectives[J].Journal of Geo-information Science,2023,25(6):1091-1105.
[8] 王鑫,邹磊,王朝坤,等.知识图谱数据管理研究综述[J].软件学报,2019,30(7):2139-2174.
WANG Xin,ZOU Lei,WANG Zhaokun,et al.Research on knowledge graph data management:a survey[J].Journal of Software,2019,30(7):2139-2174.
[9] 王萌,王昊奋,李博涵,等.新一代知识图谱关键技术综述[J].计算机研究与发展,2022,59(9):1947-1965.
WANG Meng,WANG Haofen,LI Bohan,et al.Survey on key technologies of new generation knowledge graph[J].Journal of Computer Research and Development,2022,59(9):1947-1965.
[10] 汪玉,王鑫,张淑娟,等.异构大数据环境中高效率知识融合方法的研究[J].计算机工程与应用,2022,58(6):142-148.
WANG Yu,WANG Xin,ZHANG Shujuan,et al.Research on efficient knowledge fusion method for heterogeneous big data environments[J].Computer Engineering and Applications,2022,58(6):142-148.
[11] 何佑伟,贺质越,汤勇,等.基于机器学习的页岩气井产量评价与预测[J].石油钻采工艺,2021,43(4):518-524.
HE Youwei,HE Zhiyue,TANG Yong,et al.Shale gas well production evaluation and prediction based on machine learning[J].Oil Drilling & Production Technology,2021,43(4):518-524.
[12] 黄刚.知识图谱构建方法及其在油气勘探开发领域应用研究[D].大庆:东北石油大学,2019.
HUANG Gang.Construction methods of knowledge graph and its application in oil and gas exploration and development[D].Daqing:Northeast Petroleum University,2019.
[13] 杨寒雨,赵晓永,王磊.数据归一化方法综述[J].计算机工程与应用,2023,59(3):13-22.
YANG Hanyu,ZHAO Xiaoyong,WANG Lei.Review of data normalization methods[J].Computer Engineering and Applications,2023,59(3):13-22.
[14] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[15] 何文栋.基于整体搜索的英文命名实体识别技术研究[D].广州:华南理工大学,2021.
HE Wendong.Research on english named entity recognition technology based on global search[D].Guangzhou:South China University of Technology,2021.
[16] 李天然,刘明童,张玉洁,等.基于深度学习的实体链接研究综述[J].北京大学学报(自然科学版),2021,57(1):91-98.
LI Tianran,LIU Mingtong,ZHANG Yujie,et al.A review of entity linking research based on deep learning[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2021,57(1):91-98.
[17] 段宗涛,李菲,陈柘.实体消歧综述[J].控制与决策,2021,36(5):1025-1039.
DUAN Zongtao,LI Fei,CHEN Zhe.Entity disambiguation:a review[J].Control and Decision,2021,36(5):1025-1039.
[18] 鄂海红,张文静,肖思琪,等.深度学习实体关系抽取研究综述[J].软件学报,2019,30(6):1793-1818.
E Haihong,ZHANG Wenjing,XIAO Siqi,et al.Survey of entity relationship extraction based on deep learning[J].Journal of Software,2019,30(6):1793-1818.
[19] 杨东华,邹开发,王宏志,等.基于Seq2Seq模型的SparQL查询预测[J].软件学报,2021,32(3):805-817.
YANG Donghua,ZOU Kaifa,WANG Hongzhi,et al.SparQL query prediction based on Seq2Seq model[J].Journal of Software,2021,32(3):805-817.
[20] 王晓丽,王明,刘鑫,等.基于知识图谱的油气地质评价方法及系统:CN115248863A[P].2022-10-28.
WANG Xiaoli,WANG Ming,LIU Xin,et al.Oil and gas geological evaluation method and system based on knowledge graph:CN115248863A[P].2022-10-28.
[21] 王轩,顾峰,闵帆,等.基于代表的交叉验证分类[J].重庆邮电大学学报(自然科学版),2021,33(5):826-833.
WANG Xuan,GU Feng,MIN Fan,et al.Representative-based cross validation classification[J].Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition),2021,33(5):826-833.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献