基于灰色网络组合优化的年增油量预测

doi:10.11885/j.issn.1674-5086.2020.06.05.01

西南石油大学学报(自然科学版) ›› 2020, Vol. 42 ›› Issue (6): 89-96.DOI: 10.11885/j.issn.1674-5086.2020.06.05.01

• 油气田人工智能技术与应用专刊 • 上一篇下一篇

基于灰色网络组合优化的年增油量预测

刘浩瀚^1,2, 颜永勤³, 闵令元⁴, 乐平⁵, 殷艳玲⁴

1. 四川建筑职业技术学院基础教学部, 四川德阳 618000;
2. 西南石油大学地质资源与地质工程博士后流动站, 四川成都 610500;
3. 四川建筑职业技术学院经济管理系, 四川德阳 618000;
4. 中国石化胜利油田分公司勘探开发研究院, 山东东营 257000;
5. 西南石油大学石油与天然气工程学院, 四川成都 610500

收稿日期:2020-06-05 发布日期:2020-12-21
通讯作者: 刘浩瀚,E-mail:tsinghua616@163.com
作者简介:刘浩瀚,1985年生,男,汉族,湖南常德人,副教授,博士(后),主要从事人工智能算法、数学建模及油田应用方面的研究。E-mail:tsinghua616@163.com;颜永勤,1989年生,女,汉族,四川资阳人,讲师,硕士,主要从事电子商务、全全生命周期管理及油田应用研究。E-mail:yanyongqin77@126.com;闵令元,1963年生,男,汉族,山东聊城人,高级工程师,主要从事油气田开发及渗流机理等方面的研究工作。E-mail:yinyanling.slyt@sinopec.com;乐平,1983年生,男,汉族,湖北随州人,副教授,博士,主要从事油藏数值模拟研究。E-mail:yuepingaa@126.com;殷艳玲,1975年生,女,汉族,甘肃金塔人,高级工程师,主要从事油气田开发及油气层保护实验方面的研究。E-mail:yinyanling.slyt@sinopec.com
基金资助:
中国石化胜利油田分公司科技项目（YKY1913）；四川省教育厅项目（15ZB0447，18ZB0394）；西华大学校人才引进项目（Z201076）

Prediction of Annual Increase of Oil Production Based on GM (1, 1)Neural Network Combined Optimization

LIU Haohan^1,2, YAN Yongqin³, MIN Lingyuan⁴, YUE Ping⁵, YIN Yanling⁴

1. Basic Teaching Department of Sichuan College of Architectural Technology, Deyang, Sichuan 618000, China;
2. Postdoctoral Station of Geological Resources and Geological Engineering, Southwest Petroleum University, Chengdu, Sichuan 610500, China;
3. Economic Management Department of Sichuan College of Architectural Technology, Deyang, Sichuan 618000, China;
4. Research Institute of Exploration and Development of Sinopec Shengli Oilfield Branch, Dongying, Shandong 257000, China;
5. School of Petroleum and Natural Gas Engineering, Southwest Petroleum University, Chengdu, Sichuan 610500, China

Received:2020-06-05 Published:2020-12-21

摘要/Abstract

摘要： 老井措施增油成为油田稳产、降低油田区块开发成本的必然选择。针对多项式回归预测的局限性、灰色理论不能反映影响因素特征、神经网络需求数据多且数据敏感性差等特征，通过建立最优控制模型，实现GM（1，1）灰色理论与神经网络的高精度组合预测。以某油田区块2011-2018年的措施增油为例，对影响措施增油量的因素进行识别，建立了最优控制灰色神经网络模型对老井措施年增油量进行预测，相比多项式回归预测、GM（1，1）预测及BP神经网络预测方法，新模型模拟效果更好，预测精度更高。新方法对2018年措施年增油量的预测精度达97.34%。基于最优控制的灰色神经网络模型可以作为一种人工智能组合最优化模型预测措施年增油量，为准确预测措施增油效果，指导油田开发决策提供了新的思路。

关键词: 措施有效井, 年增油量, 灰色预测, BP神经网络, 最优控制

Abstract: Increasing oil production of old wells has become an inevitable choice to stabilize production and reduce development costs of oilfield block development. In view of the limitation of polynomial regression prediction, the fact that the grey theory cannot reflect the characteristics of influence factors, and the neural network needs more data and is less sensitive to data, this paper establishes an optimal control model, combining the high precision forecasting of grey theory with the neural network. Taking the actual measures to increase oil production in an oilfield block from 2011 to 2018 as an example, by confirming the influence factors of annual oil increment, a new optimal control grey neural network model is established, which is used to predict the annual oil increment with different measures. Compared with polynomial regression prediction, GM(1, 1) prediction and BP neural network prediction, the results show that the new model has better simulation effect and higher prediction precision. The prediction accuracy of the annual oil increment with the new method is 97.34% in 2018. The grey neural network model based on optimal control can be an artificial intelligence model to predict the annual oil increment with different measures, which provides a new idea for accurately predicting of oil increment with different measures and decision-making of oilfield development.

Key words: measure effective well, annual oil increment, grey prediction, BP neural network, optimal control

中图分类号:

TE121.1

刘浩瀚, 颜永勤, 闵令元, 乐平, 殷艳玲. 基于灰色网络组合优化的年增油量预测[J]. 西南石油大学学报(自然科学版), 2020, 42(6): 89-96.

LIU Haohan, YAN Yongqin, MIN Lingyuan, YUE Ping, YIN Yanling. Prediction of Annual Increase of Oil Production Based on GM (1, 1)Neural Network Combined Optimization[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2020, 42(6): 89-96.

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.1674-5086.2020.06.05.01

http://journal15.magtechjournal.com/Jwk_xnzk/CN/Y2020/V42/I6/89

参考文献

[1] 刘浩瀚. 特高含水期剩余油滴可动条件及水驱油效率变化机理研究[D]. 成都:西南石油大学, 2013. LIU Haohan. Study on remaining oil droplet dynamic conditions and water flood efficiency changing mechanisms in the ultra-high water cut period[D]. Chengdu:Southwest Petroleum University, 2013.
[2] 李金蔓,霍宏博,胡勇,等. 特高含水期强非均质油藏剩余油研究新方法[J]. 辽宁石油化工大学学报,2019,39(6):43-47. doi:10.3969/j.issn.1672-6952.2019.06.008 LI Jinman, HUO Hongbo, HU Yong, et al. New research method for residual oil in strong heterogeneous reservoirs at extra ultra-high water cut stage[J]. Journal of Liaoning Shihua University, 2019, 39(6):43-47. doi:10.3969/j.issn.1672-6952.2019.06.008
[3] 刘美佳,周凤军,陈存良,等. 海上中轻质油藏产量预测新模型[J]. 石油化工应用, 2019, 38(3):9-12. doi:10.3969/j.issn.1673-5285.2019.03.003 LIU Meijia, ZHOU Fengjun, CHEN Cunliang, et al. A new model of predicting the output for offshore light oil reservoirs[J]. Petrochemical Industry Application, 2019, 38(3):9-12. doi:10.3969/j.issn.1673-5285.2019.03.003
[4] 侯春华. 基于长短期记忆神经网络的油田新井产油量预测方法[J]. 油气地质与采收率, 2019, 26(3):105-110. doi:10.13673/j.cnki.cn37-1359/te.2019.03.014 HOU Chunhua. New well oil production forecast method based on long-term and short-term memory neural network[J]. Petroleum Geology and Recovery Efficiency, 2019, 26(3):105-110. doi:10.13673/j.cnki.cn37-1359/te. 2019.03.014
[5] 周芸,周福建,冯连勇. 一种新型油气产量预测模型[J]. 大庆石油地质与开发, 2018, 37(5):76-80. doi:10.19597/J.ISSN.1000-3754.201711011 ZHOU Yun, ZHOU Fujian, FENG Lianyong. A new model for predicting oil ang gas production[J]. Petroleum Geology and Oilfield Development in Daqing, 2018, 37(5):76-80. doi:10.19597/J.ISSN.1000-3754.201711011
[6] 崔传智,吴忠维,李昱东,等. 应用PSO-改进GM (1, 1)模型预测油田产量[J]. 数学的实践与认识, 2018, 48(17):119-123. CUI Chuanzhi, WU Zhongwei, LI Yudong, et al. Application of the PSO-modified GM(1, 1) model in oilfield production forecast[J]. Mathematics in Practice and Theory, 2018, 48(17):119-123.
[7] 陈东虎,朱维耀,朱华银,等. 应用广义回归神经网络预测油井含水率[J]. 重庆科技学院学报(自然科学版), 2012, 14(6):97-101. doi:10.19406/j.cnki. cqkjxyxbzkb.2012.06.026 CHEN Donghu, ZHU Weiyao, ZHU Huayin, et al. Using general regression neural networks method to predict water cut in oil well[J]. Journal of Chongqing University of Science and Technology (Natural Science Edition), 2012, 14(6):97-101. doi:10.19406/j.cnki.cqkjxyxbzkb.2012.06.026
[8] 王美石,陈祥光,李宇峰. 用于油田产量预测的多元线性回归和自回归模型[J]. 石油规划设计, 2005, 16(3):19-21. doi:10.3969/j.issn.004-2970.2005.03.007 WANG Meishi, CHEN Xiangguang, LI Yufeng. Multivariate linear regression and automatic regression models applied to output prediction of oilfield[J]. Petroleum Planning & Engineering, 2005, 16(3):19-21. doi:10.3969/j.issn.004-2970.2005.03.007
[9] 国亮. 改进多元线性回归模型在某油田产量预测中的应用[J]. 西安电子科技大学学报(社会科学版), 2009, 19(3):71-75. doi:10.16348/j.cnki.cn61-1336/c. 2009.03.005 GUO Liang. Application of improved multivariate linear regression to output prediction of an oilfield[J]. Journal of Xidian University (Social Science Edition), 2009, 19(3):71-75. doi:10.16348/j.cnki.cn61-1336/c.2009.03.005
[10] 陈武,吴焘宏,陈尘,等. 基于偏最小二乘回归分析的油田操作成本预测——以DX油田为例[J]. 西南石油大学学报(社会科学版), 2019, 21(1):8-13. doi:10.11885/j.issn.1674-5094.2018.09.26.03 CHEN Wu, WU Taohong, CHEN Chen, et al. Prediction of oilfield operation cost through partial least squares regression:A case study on DX Oilfield[J]. Journal of Southwest Petroleum University (Social Sciences Edition), 2019, 21(1):8-13. doi:10.11885/j.issn.1674-5094.2018.09.26.03
[11] 陈鹏宇. GM(1, 1)幂模型的改进及其在沉降预测中的应用[J]. 大地测量与地球动力学, 2020, 40(5):464-469. doi:10.14075/j.jgg.2020.05.005 CHEN Pengyu. Improvement of GM(1, 1) power model and its application settlement prediction[J]. Journal of Geodesy and Geodynamics, 2020, 40(5):464-469. doi:10.14075/j.jgg.2020.05.005
[12] 林旺,范洪富,王志平,等. 致密油藏体积压裂水平井产量预测研究[J]. 油气地质与采收率, 2018, 25(6):107-113. doi:10.13673/j.cnki.cn37-1359/te.2018.06.017 LIN Wang, FAN Hongfu, WANG Zhiping, et al. Prediction on production of volume fractured horizontal well in tight reservoirs[J]. Petroleum Geology and Recovery Efficiency, 2018, 25(6):107-113. doi:10.13673/j.cnki.cn37-1359/te.2018.06.017
[13] 李志强,赵金洲,胡永全,等. 致密油层多区体积压裂产能预测[J]. 油气地质与采收率, 2016, 23(1):134-138. doi:10.3969/j.issn.1009-9603.2016.01.022 LI Zhiqiang, ZHAO Jinzhou, HU Yongquan, et al. Productivity forecast of tight oil reservoirs after multi-zone stimulated reservoir volume fracturing[J]. Petroleum Geology and Recovery Efficiency, 2016, 23(1):134-138. doi:10.3969/j.issn.1009-9603.2016.01.022
[14] YUE Ping, XIE Zhiwei, HUANG Siyuan, et al. The application of N₂ huff and puff for IOR in fracture-vuggy carbonate reservoir[J]. Fuel, 2018, 234:1507-1517. doi:10.1016/j.fuel.2018.07.128
[15] LIU Zhibin, LIU Haohan. An effective method to predict oil recovery in high water cut stage[J]. Journal of Hydrodynamics, Ser. B, 2015, 27(6):988-995. doi:10.1016/S1001-6058(15)60561-3
[16] YUE Ping, CHEN Xiaofan, LIU Haohan, et al. The critical parameters of a horizontal well influenced by a semipermeable barrier considering thickness in a bottom water reservoir[J]. Journal of Petroleum Science and Engineering, 2015, 129:88-96. doi:10.1016/j.petrol.2015.02.029
[17] NEGASH B M, YAW A D. 基于人工神经网络的注水开发油藏产量预测[J]. 石油勘探与开发, 2020, 47(2):357365. doi:10.11698/PED.2020.02.14 NEGASH B M, YAW A D. Artificial neural network based production forecasting for a hydrocarbon reservoir under water injection[J]. Petroleum Exploration and Development, 2020, 47(2):357-365. doi:10.11698/PED.2020.02.14
[18] YUE Ping, XIE Zhiwei, LIU Haohan, et al. Application of water injection curves for the dynamic analysis of fractured-vuggy carbonate reservoirs[J]. Journal of Petroleum Science and Engineering, 2018, 169:220-229. doi:10.1016/j.petrol.2018.05.062
[19] 张翼成,陈欣,杨红军,等. 基于组合特征的BP神经网络数字识别方法[J]. 计算机系统应用, 2013, 22(3):113-116. doi:10.3969/j.issn.1003-3254.2013.03.026 ZHANG Yicheng, CHEN Xin, YANG Hongjun, et al. Neural network digital characters recognition based on the combined feature[J]. Computer Systems & Applications, 2013, 22(3):113-116. doi:10.3969/j.issn.1003-3254.2013.03.026
[20] 宋明,李旭阳,曹宇光,等. 基于BP神经网络与小冲杆试验确定在役管道钢弹塑性性能方法研究[J]. 力学学报, 2020, 52(1):82-92. doi:10.6052/0459-1879-19-297 SONG Ming, LI Xuyang, CAO Yuguang, et al. Determination of elastoplastic properties of in-service pipeline steel based on BP neural network and small punch test[J]. Chinese Journal of Theoretical and Applied Mechanics, 2020, 52(1):82-92. doi:10.6052/0459-1879-19-297
[21] 邓聚龙. 灰色控制系统[J]. 华中工学院学报, 1982, 10(3):9-18. doi:10.13245/j.hust.1982.03.002 DENG Julong. The grey control system[J]. Journal of Central China Institute of Technology, 1982, 10(3):9-18. doi:10.13245/j.hust.1982.03.002
[22] 黄魁,苏春. 基于灰色神经网络组合模型的故障预测[J]. 系统工程与电子技术, 2020, 42(1):238-244. doi:10.3969/j.issn.1001-506X.2020.01.32 HUANG Kui, SU Chun. Failure prediction based on com-bined model of grey neural network[J]. Systems Engineering and Electronics, 2020, 42(1):238-244. doi:10.3969/j.issn.1001-506X.2020.01.32
[23] 花超. 基于灰色理论的铁路线路方案多目标优选分析及决策模型研究[J]. 铁道勘察, 2020(4):88-92. doi:10.19630/j.cnki.tdkc.201909090005 HUA Chao. Study on multi-objective optimal selection analysis and decision model of railway route schemes based on grey theory[J]. Railway Investigation and Surveying, 2020(4):88-92. doi:10.19630/j.cnki.tdkc. 201909090005
[24] 孙明明. 采油工程压裂增油技术措施研究[J]. 化工设计通讯, 2019, 45(2):51. doi:10.3969/j.issn.1003-6490.2019.02.046 SUN Mingming. Study technical measures for fracturing and oil increase in oil production engineering[J]. Chemical Engineering Design Communications, 2019, 45(2):51. doi:10.3969/j.issn.1003-6490.2019.02.046
[25] 范鹏,孟令为,杨学武,等. 高含水油田剩余油分布规律及挖潜效果评价[J]. 石油化工应用, 2020, 39(4):52-54, 62. doi:10.3969/j.issn.1673-5285.2020.04.012 FAN Peng, MENG Lingwei, YANG Xuewu, et al. Distribution law of remaining oil and evaluation of tapping potential effect[J]. Petrochemical Industry Application, 2020, 39(4):52-54, 62. doi:10.3969/j.issn.1673-5285.2020.04.012
[26] YUE Ping, JIA Bingyi, SHENG James, et al. A coupling model of water breakthrough time for a multilateral horizontal well in a bottom water-drive reservoir[J]. Journal of Petroleum Science and Engineering, 2019, 177:317-330. doi:10.1016/j.petrol.2019.02.033
[27] 刘浩瀚. 概率论与数理统计[M]. 北京:高等教育出版社, 2015:113-115. LIU Haohan. Probability theory and mathematical statistics[M]. Beijing:Higher Education Press, 2015:113-115.

基于灰色网络组合优化的年增油量预测

Prediction of Annual Increase of Oil Production Based on GM (1, 1)Neural Network Combined Optimization

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 9

编辑推荐

Metrics

本文评价

[1]	刘永辉, 罗程程, 刘通, 任桂蓉, 王中武. 水平气井井筒气液两相流型预测[J]. 西南石油大学学报(自然科学版), 2019, 41(3): 107-112.
[2]	李建, 李珂, 王兵. 粗糙集和神经网络相融合的钻井安全评价模型[J]. 西南石油大学学报(自然科学版), 2017, 39(5): 120-128.
[3]	贺懿;张进;刘怀山. 基于神经网络的面波迭代反演应用研究[J]. 西南石油大学学报(自然科学版), 2010, 32 (1): 40-44.
[4]	李海涛a 唐庆吴杰生谭灿b. 油气藏相渗特征参数的非线性参数识别[J]. 西南石油大学学报(自然科学版), 2009, 31(5): 83-88.
[5]	刘强张莹张立庆. 沙19断块E¹f¹^₃低电阻率油层成因及识别[J]. 西南石油大学学报(自然科学版), 2009, 31(3): 49-52.
[6]	王勇;鲍志东;刘虎. 低孔低渗储层评价中数学方法的应用研究[J]. 西南石油大学学报(自然科学版), 2007, 29(5): 8-12.
[7]	罗天雨郭建春赵金洲吴建发. 求取压裂气井无阻流量的BP神经网络法[J]. 西南石油大学学报(自然科学版), 2006, 28(3): 67-69.
[8]	刘志斌傅青山丁辉凡括元. 油田开发规划决策软件系统 [J]. 西南石油大学学报(自然科学版), 2004, 26(1): 79-82.
[9]	肖伟杜俊怀刘前云. 油田开发最优控制之神经网络实现[J]. 西南石油大学学报(自然科学版), 2003, 25(5): 39-42.