用深度学习挖掘油田开发指标预测模型的知识

doi:10.11885/j.issn.1674-5086.2020.05.11.02

西南石油大学学报(自然科学版) ›› 2020, Vol. 42 ›› Issue (6): 63-74.DOI: 10.11885/j.issn.1674-5086.2020.05.11.02

• 油气田人工智能技术与应用专刊 • 上一篇下一篇

用深度学习挖掘油田开发指标预测模型的知识

钟仪华^1,2, 王淑宁¹, 罗兰¹, 杨金莲¹, 岳永鹏³

1. 西南石油大学理学院, 四川成都 610500;
2. 西南石油大学人工智能研究院, 四川成都 610500;
3. 北京知道创宇信息技术有限公司成都分公司, 四川成都 610000

收稿日期:2020-05-11 发布日期:2020-12-21
通讯作者: 钟仪华,E-mail:zhongyh_65@126.com
作者简介:钟仪华,1965年生,女,汉族,四川简阳人,教授,博士,主要从事最优化理论与方法、预测与决策、石油工程计算技术及数据挖掘等方面的研究工作。E-mail:zhongyh_65@126.com;王淑宁,1994年生,女,汉族,陕西榆林人,硕士研究生,主要从事应用数学方面的研究工作。E-mail:393875885@qq.com;罗兰,1995年生,女,汉族,四川资阳人,硕士研究生,主要从事数据挖掘方面的研究工作。E-mail:1978684224@qq.com;杨金莲,1996年生,女,汉族,四川遂宁人,硕士研究生,主要从事知识挖掘方面的研究工作。E-mail:2806234881@qq.com;岳永鹏,1987年生,男,汉族,四川巴中人,高级工程师,硕士,主要从事自然语言处理及知识图谱方面的研究工作。E-mail:yueyongpeng@outlook.com

Knowledge Mining for Oilfield Development Index Prediction Model Using Deep Learning

ZHONG Yihua^1,2, WANG Shuning¹, LUO Lan¹, YANG Jinlian¹, YUE Yongpeng³

1. School of Science, Southwest Petroleum University, Chengdu, Sichuan 610500, China;
2. Institute for Artificial Intelligence, Southwest Petroleum University, Chengdu, Sichuan 610500, China;
3. Chengdu Branch, Beijing KnownSec Information Technology Co. Ltd, Chengdu, Sichuan 610000, China

Received:2020-05-11 Published:2020-12-21

摘要/Abstract

摘要： 油田开发指标变化特征被当作油田开发规划、油田开采状况评价、油田开发方案设计与调整及油田开发风险预测预警等决策管理问题的重要依据。针对至今没有很好解决的建立智慧油田的瓶颈问题之一——油田开发指标智能预测系统的选择预测方法和模型的知识挖掘问题，基于油田开发的海量数据，利用深度学习的卷积神经网络和循环神经网络，提取反映油田开发动态特征和知识。在此基础上，结合已建立的油田开发指标预测的模型库及知识库，利用深度学习的实体和关系的联合提取方法，提出通过油田开发输入信息、油田开发动态特征指标、油田开发指标预测的模型库和知识库挖掘选择油田开发指标最佳预测模型的知识方法。概念设计的模拟实例表明，提出的知识挖掘流程可实现只要输入油田开发的相关信息，就能自主获得恰当的油田开发指标预测模型。

关键词: 油田开发指标, 预测模型, 知识挖掘, 深度学习, 实体与关系

Abstract: The changing characteristics of oilfield development index are regarded as the important basis of oilfield development planning, oilfield exploitation evaluation, oilfield development scheme design and adjustment, decision management problems of oilfield development risk prediction and early warning, etc. For one of the unsolved bottleneck problem of building intelligent oilfield, i.e. the problem on knowledge mining of selecting prediction method and model of oilfield development indexes intelligent prediction system, based on the massive data of oilfield development, this paper uses the convolutional neural network and cyclic neural network of deep learning to extract the characteristics and knowledge reflecting the development dynamic of oilfield. On this basis, combining the model base and knowledge base of oilfield development index prediction, a knowledge mining method to select the optimal prediction model of oilfield development index is proposed through the input information and dynamic characteristics index of oilfield development, the model base and the knowledge base of oilfield development index prediction by using the joint extraction method of entity and relationship of deep learning. The simulation example of conceptual design shows that the proposed knowledge mining process may realize autonomous obtaining an appropriate prediction model of oilfield development index as long as inputting relevant information of oilfield development.

Key words: oilfield development index, prediction model, knowledge mining, deep learning, entities and relationship

中图分类号:

TE33

钟仪华, 王淑宁, 罗兰, 杨金莲, 岳永鹏. 用深度学习挖掘油田开发指标预测模型的知识[J]. 西南石油大学学报(自然科学版), 2020, 42(6): 63-74.

ZHONG Yihua, WANG Shuning, LUO Lan, YANG Jinlian, YUE Yongpeng. Knowledge Mining for Oilfield Development Index Prediction Model Using Deep Learning[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2020, 42(6): 63-74.

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.1674-5086.2020.05.11.02

http://journal15.magtechjournal.com/Jwk_xnzk/CN/Y2020/V42/I6/63

参考文献

[1] 钟仪华. 特高含水期油田开发规划动态预测方法研究[D]. 成都:西南石油大学, 2008. ZHONG Yihua. The study of dynamic prediction methods for oilfield development programming in extra-high watercut stage[D]. Chengdu:Southwest Petroleum University, 2008.
[2] ZHONG Yihua, LI Lina, WANG Yu. The study of model selection method on intelligent prediction system and its applications[C]. International Conference on Computational & Information Sciences, 2011. doi:10.1109/ICCIS. 2011.301
[3] ZHONG Yihua, ZHU Mingxia, ZHANG Zhiyin. An intelligent prediction model for oilfield production based on fuzzy expert system[J]. Advances in Intelligent and Soft Computing, 2012, 147:475-484. doi:10.1007/978-3-642-28592-9_50
[4] 张志银. 油田开发指标系统的智能预测研究[D]. 成都:西南石油大学, 2012. ZHANG Zhiyin. The research of intelligent prediction on oilfield development index system[D]. Chengdu:Southwest Petroleum University, 2012.
[5] 廖昱芯. 基于智能预测系统的知识挖掘及应用研究[D]. 成都:西南石油大学, 2013. LIAO Yuxin. The research of knowledge mining based on intelligent prediction system and its application[D]. Chengdu:Southwest Petroleum University, 2013.
[6] 李丽娜. 基于智能预测的模糊预测控制方法及应用研究[D]. 成都:西南石油大学, 2013. LI Lina. The research of fuzzy predictive control method based on intelligent prediction and its application[D]. Chengdu:Southwest Petroleum University, 2013.
[7] ZHONG Yihua, WANG Dan, YUE Yongpeng, et al. Intelligent prediction system of oilfield development index[C]. Proceedings of the Asia-Pacific Computer Science and Application Conference, 2014:229-233. doi:10.1201/b18508-40
[8] 王丹. 基于Agent的油田开发指标的智能预测系统研究[D]. 成都:西南石油大学, 2015. WANG Dan. The research on intelligent prediction system of oilfield development index based on Agent[D]. Chengdu:Southwest Petroleum University, 2015.
[9] ZHONG Yihua, LÜ Xiaodie, BAO Min, et al. Design for intelligent prediction system of oilfield development index based on pattern recognition[J]. Filomat, 2018, 32(5):1757-1764. doi:10.2298/FIL1805757Z
[10] YANG Qingjun, ZHANG Shulin, FEI Qi. Integrating neural network and numerical simulation for production performance prediction of low permeability reservoir[J]. Petroleum Science and Technology, 2005, 23(5-6):579-590. doi:10.1081/LFT-200032851
[11] AI-JASMI A K, GOEL H K, NASR H, et al. Short-term production prediction in real time using intelligent techniques[C]. SPE 164813-MS, 2013.
[12] ZHONG Yihua, ZHAO Lei, LIU Zhibin, et al. Using a support vector machine method to predict the development indices of very high water cut oilfields[J]. Petroleum Science, 2010, 7(3):379-384. doi:10.1007/s12182-010-0081-1
[13] 朱秀莉,李龙,李盼池. 基于T-S推理网络的油田开发指标预测方法[J]. 计算机应用研究, 2011, 28(8):2991-2993. doi:10.3969/j.issn.1001-3695.2011.08.052 ZHU Xiuli, LI Long, LI Panchi. Forecasting methods of oil field development indexes based on T-S reasoning networks[J]. Application Research of Computers, 2011, 28(8):2991-2993. doi:10.3969/j.issn.1001-3695.2011.08.052
[14] 张巧翠. 基于模糊计算的油田开发指标预测模型及应用研究[D]. 大庆:东北石油大学, 2011. ZHANG Qiaocui. Research on model and application of oilfield development index prediction based on fuzzy computation[D]. Daqing:Northeast Petroleum University, 2011.
[15] 张宇航. 基于油藏建模成果的油田开发指标预测及状态评估方法[D]. 大庆:东北石油大学, 2016. ZHANG Yuhang. The method of oilfield development index prediction and condition assessment based on the reservoir modeling results[D]. Daqing:Northeast Petroleum University, 2016.
[16] SRIDEVI S, RAJARAM S, SWADHIKAR C. An intelligent prediction system for time series data using periodic pattern mining in temporal databases[C]. Proceedings of the First International Conference on Intelligent Interactive Technologies and Multimedia, 2010:163-171. doi:10.1145/1963564.1963592
[17] ROSLI N S, IBRAHIM R, ISMAIL I. Intelligent prediction system for gas metering system using particle swarm optimization in training neural network[J]. Procedia Computer Science, 2017, 105:165-169. doi:10.1016/j.procs. 2017.01.197
[18] HAMED Z S, JAMES P K, S A. Developing an intelligent expert system for stream flow prediction, integrated in a dynamic decision support system for managing multiple reservoirs:A case study[J]. Expert Systems with Applications, 2017, 83:145-163. doi:10.1016/j.eswa.2017.04.039
[19] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521:436-444. doi:10.1038/nature14539
[20] 谷建伟,周梅,李志涛,等. 基于数据挖掘的长短期记忆网络模型油井产量预测方法[J]. 特种油气藏,2019,26(2):77-81. doi:10.3969/j.issn.1006-6535.2019.02.013 GU Jianwei, ZHOU Mei, LI Zhitao, et al. Oil well production forecast with long-short term memory network model based on data mining[J]. Special Oil and Gas Reservoir, 2019, 26(2):77-81. doi:10.3969/j.issn.1006-6535.2019.02.013
[21] 邹晶. 基于深度学习的实体与关系联合提取方法研究[D]. 成都:电子科技大学, 2019. ZOU Jing. Research on entity and relationship joint extraction method based on deep learning[D]. Chengdu:University of Electronic Science and Technology of China, 2019.
[22] 李元,冯成成. 基于一维卷积神经网络深度学习的工业过程故障检测[J]. 测控技术, 2019, 38(9):36-40. doi:10.19708/j.ckjs.2019.09.007 LI Yuan, FENG Chengcheng. Fault detection of industrial process based on deep learning of one-dimensional convolutional neural network[J]. Measurement & Control Technology, 2019, 38(9):36-40. doi:10.19708/j.ckjs.2019.09.007
[23] 林锦发,程良伦,应稼田. 基于一维卷积神经网络的多特征社交网络流行度预测研究[J]. 现代计算机, 2019, 643(7):3-9. doi:10.3969/j.issn.1007-1423.2019.07.001 LIN Jinfa, CHENG Lianglun, YING Jiatian. Research on popularity prediction of multi-feature social networks based on one-dimensional convolutional neural networks[J]. Modern Computer, 2019, 643(7):3-9. doi:10.3969/j.issn.1007-1423.2019.07.001
[24] 李道全,王雪,于波,等. 基于一维卷积神经网络的网络流量分类方法[J]. 计算机工程与应用, 2020, 56(3):94-99. doi:10.3778/j.issn.1002-8331.1905-0139 LI Daoquan, WANG Xue, YU Bo, et al. Network traffic classification method based on one-dimensional convolutional neural network[J]. Computer Engineering and Applications, 2020, 56(3):94-99. doi:10.3778/j.issn.1002-8331.1905-0139
[25] 宋辉,陈伟,李谋杰,等. 基于卷积门控循环单元网络的储层参数预测方法[J]. 油气地质与采收率, 2019, 26(5):73-78. doi:10.13673/j.cnki.cn37-1359/te.2019.05.009 SONG Hui, CHEN Wei, LI Moujie, et al. A method to predict reservoir parameters based on convolutional neural network-gated recurrent unit(CNN-GRU)[J]. Petroleum Geology and Recovery Efficiency, 2019, 26(5):73-78. doi:10.13673/j.cnki.cn37-1359/te.2019.05.009
[26] 李大中,颖宇,王超. 基于卷积循环神经网络深度学习的短期风速预测[J]. 电力科学与工程, 2019, 35(8):1-6. doi:10.3969/j.ISSN.1672-0792.2019.08.001 LI Dazhong, YING Yu, WANG Chao. Short-term wind speed prediction based on convolutional cyclic neural network and deep learning[J]. Electric Power Science and Engineering, 2019, 35(8):1-6. doi:10.3969/j.ISSN.1672-0792.2019.08.001
[27] 李东东,王浩,杨帆,等. 基于一维卷积神经网络和Soft-Max分类器的风电机组行星齿轮箱故障检测[J]. 电机与控制应用, 2018, 45(6):80-87, 108. LI Dongdong, WANG Hao, YANG Fan, et al. Fault detection of wind turbine planetary gear box using 1D convolutional neural networks and soft-max classifier[J]. Electric Machines & Control Application, 2018, 45(6):80-87, 108.

用深度学习挖掘油田开发指标预测模型的知识

Knowledge Mining for Oilfield Development Index Prediction Model Using Deep 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 12

编辑推荐

Metrics

本文评价

[1]	黄诚, 潘雯晋. 基于机器学习的石油多峰模型研究及应用[J]. 西南石油大学学报(自然科学版), 2020, 42(6): 75-81.
[2]	黄旭日, 代月, 徐云贵, 唐静. 基于深度学习算法不同数据集的地震反演实验[J]. 西南石油大学学报(自然科学版), 2020, 42(6): 16-25.
[3]	闵超, 代博仁, 张馨慧, 杜建平. 机器学习在油气行业中的应用进展综述[J]. 西南石油大学学报(自然科学版), 2020, 42(6): 1-15.
[4]	张智, 刘金铭, 张华礼, 李玉飞, 罗伟. 注CO₂采油井油管柱腐蚀速率预测[J]. 西南石油大学学报(自然科学版), 2019, 41(2): 175-184.
[5]	袁宗明1，王勇1 *，谢英1，王大鹏2. 原油高温结垢速率测定和预测模型研究进展[J]. 西南石油大学学报(自然科学版), 2016, 38(1): 170-180.
[6]	刘文东1 *，刘性全2. 新井试井曲线类型预测新方法研究[J]. 西南石油大学学报(自然科学版), 2015, 37(3): 115-121.
[7]	石立华1 *，赵习森1，郭尚平2，王艳1，芦超3. 薄互层水平井蒸汽吞吐热采水平段加热范围预测[J]. 西南石油大学学报(自然科学版), 2015, 37(3): 93-97.
[8]	李志军1，戚志林1，宿亚仙2，李继强1，严文德1. 基于水侵预警的边水气藏动态预测模型[J]. 西南石油大学学报(自然科学版), 2014, 36(3): 87-92.
[9]	王智许江文谷斌. 基于测井资料的低孔低渗储层产能预测研究[J]. 西南石油大学学报(自然科学版), 2009, 31(6): 51-55.
[10]	赵金省李兆敏李宾飞孙辉翟亮. 基于支持向量机的蒸汽吞吐井调剖参数优化[J]. 西南石油大学学报(自然科学版), 2007, 29(5): 53-56.
[11]	谢祥俊a 贾闽惠杜志敏b. 预测油气田产量的β模型[J]. 西南石油大学学报(自然科学版), 2005, 27(2): 50-52(6.
[12]	李大昌. 油气田动态灰色预测模型的选择方法[J]. 西南石油大学学报(自然科学版), 1989, 11(1): 48-57.