提出了一种基于多变量时间序列（MTS）及向量自回归（VAR）机器学习模型的水驱油藏产量预测方法,并进行了实例应用。该方法在井网分析的基础上通过MTS分析对注采井组数据进行优选,并将井组内不同采出井产油量及注入井注水量作为彼此相关的时间序列,通过建立VAR模型从多个时间序列中提取出相互作用规律,挖掘注采井间流量的依赖关系从而进行产量预测。水驱油藏历史生产数据分析结果表明,与数值模拟历史拟合结果相比,机器学习模型产量预测结果具有更高精度,同时不确定性分析提升了预测结果的安全性。通过脉冲响应分析对注入井的采油贡献量进行评价,可为注水开发方案调整提供理论指导。图10表5参28
A forecasting method of oil well production based on multivariate time series (MTS) and vector autoregressive (VAR) machine learning model for waterflooding reservoir is proposed, and an example application is carried out. This method first uses MTS analysis to optimize injection and production data on the basis of well pattern analysis. The oil production of different production wells and water injection of injection wells in the well group are regarded as mutually related time series. Then a VAR model is established to mine the linear relationship from MTS data and forecast the oil well production by model fitting. The analysis of history production data of waterflooding reservoirs shows that, compared with history matching results of numerical reservoir simulation, the production forecasting results from the machine learning model are more accurate, and uncertainty analysis can improve the safety of forecasting results. Furthermore, impulse response analysis can evaluate the oil production contribution of the injection well, which can provide theoretical guidance for adjustment of waterflooding development plan.
[1] 林伯韬, 郭建成. 人工智能在石油工业中的应用现状探讨[J]. 石油科学通报, 2019, 4(4): 403-413.
LIN Botao, GUO Jiancheng.Discussion on current application of artificial intelligence in petroleum industry[J]. Petroleum Science Bulletin, 2019, 4(4): 403-413.
[2] 贾爱林, 郭建林. 智能化油气田建设关键技术与认识[J]. 石油勘探与开发, 2012, 39(1): 118-122.
JIA Ailin, GUO Jianlin.Key technologies and understandings on the construction of smart fields[J]. Petroleum Exploration and Development, 2012, 39(1): 118-122.
[3] LI J, CASTAGNA J, LI D, et al.Reservoir prediction via SVM pattern recognition[C]//SEG Technical Program Expanded Abstracts 2004. Tulsa: Society of Exploration Geophysicists, 2004: 425-428.
[4] 邢明海, 陈祥光, 王渝. 应用模糊神经网络预测油田产量[J]. 计算机仿真, 2005, 22(2): 187-190.
XING Minghai, CHEN Xiangguang, WANG Yu.Oilfield output forecast using fuzzy neural network[J]. Computer Simulation, 2005, 22(2): 187-190.
[5] WEBER D, EDGAR T F, LAKE L W, et al.Improvements in capacitance-resistive modeling and optimization of large scale reservoirs[R]. SPE 121299, 2009.
[6] ANIFOWOSE F A.Artificial intelligence application in reservoir characterization and modeling: Whitening the black box[R]. SPE 155413, 2011.
[7] GHERABATI S A, HUGHES R G, ZHANG H, et al.A large scale network model to obtain interwell formation characteristics[R]. SPE 153386, 2012.
[8] SALAZAR M, GONZALEZ H, MATRINGE S, et al.Combining decline-curve analysis and capacitance-resistance models to understand and predict the behavior of a mature naturally fractured carbonate reservoir under gas injection[R]. SPE 153252, 2012.
[9] HOLDAWAY K R.Data mining methodologies enhance probabilistic well forecasting[R]. SPE 167428-MS, 2013.
[10] 张方舟, 严胡勇, 杨立全, 等. 改进型灰色神经网络模型在油田产量中的应用[J]. 计算机技术与发展, 2013, 23(6): 241-244.
ZHANG Fangzhou, YAN Huyong, YANG Liquan, et al.Application of improved grey neural network model to oil yields[J]. Computer Technology and Development, 2013, 23(6): 241-244.
[11] GUPTA S, FUEHRER F, JEYACHANDRA B C.Production forecasting in unconventional resources using data mining and time series analysis[R]. SPE 171588-MS, 2014.
[12] ZHOU Q, DILMORE R, KLEIT A, et al.Evaluating gas production performances in Marcellus using data mining technologies[J]. Journal of Natural Gas Science and Engineering, 2014, 20(1): 109-120.
[13] LI J, LEI Z, LI S, et al. Optimizing water flood performance to improve injector efficiency in fractured low-permeability reservoirs using streamline simulation[R]. SPE 182779, 2016.
[14] CAO Q, BANERJEE R, GUPTA S, et al. Data driven production forecasting using machine learning[R]. SPE 180984, 2016.
[15] 赵辉, 康志江, 孙海涛, 等. 水驱开发多层油藏井间连通性反演模型[J]. 石油勘探与开发, 2016, 43(1): 99-106.
ZHAO Hui, KANG Zhijiang, SUN Haitao, et al.An interwell connectivity inversion model for waterflooded multilayer reservoirs[J]. Petroleum Exploration and Development, 2016, 43(1): 99-106.
[16] MAQUI A F, ZHAI X, SUAREZ N A, et al. A comprehensive workflow for near real time waterflood management and production optimization using reduced-physics and data-driven technologies[R]. SPE 182696, 2017.
[17] 武志军. Spark环境下基于数据挖掘的油田产量预测技术研究与应用[D]. 青岛: 中国石油大学(华东), 2017.
WU Zhijun.Research and application of oilfield production forecast technology based on data mining in Spark environment[D]. Qingdao: China University of Petroleum, 2017.
[18] MARTIN E, WILLS P, HOHL D, et al. Using machine learning to predict production at a Peace River thermal EOR site[R]. SPE 180984, 2017.
[19] 贾虎, 邓力珲. 基于流线聚类人工智能方法的水驱油藏流场识别[J]. 石油勘探与开发, 2018, 45(2): 312-319.
JIA Hu, DENG Lihui. Oil reservoir water flooding flowing area identification based on the method of streamline clustering artificial intelligence[J]. Petroleum Exploration and Development, 2018, 45(2): 312-319.
[20] KHAN M, ALNUAIM S, TARIQ Z, et al. Machine learning application for oil rate prediction in artificial gas lift wells[R]. SPE 194713, 2019.
[21] NOSHI C, EISSA M, ABDALLA R, et al. An intelligent data driven approach for production prediction[R]. SPE 29243-MS, 2019.
[22] 杨海民, 潘志松, 白玮. 时间序列预测方法综述[J]. 计算机科学, 2019, 46(1): 21-28.
YANG Haimin, PAN Zhisong, BAI Wei.Review of time series prediction methods[J]. Computer Science, 2019, 46(1): 21-28.
[23] 梁吉业, 冯晨娇, 宋鹏. 大数据相关分析综述[J]. 计算机学报, 2016, 39(1): 1-18.
LIANG Jiye, FENG Chenjiao, SONG Peng.A survey on correlation analysis of big data[J]. Chinese Journal of Computers, 2016, 39(1): 1-18.
[24] PEARSON K. Mathematical contributions to the theory of evolution (Ⅲ): Regression, heredity, and panmixia[J]. Philosophical Transactions of the Royal Society of London. Series A, 1896, 187: 253-318.
[25] LÜTKEPOHL H. New introduction to multiple time series analysis[M]. Berlin: Springer Science & Business Media, 2005.
[26] AKAIKE H.Information theory and an extension of the maximum likelihood principle[R]. Budapest: 2nd International Symposium on Information Theory, 1973.
[27] SCHWARZ G.Estimating the dimension of a model[J]. Annals of Statistics, 1978, 6: 461-464.
[28] HANNAN E J, QUINN B G.The determination of the order of an autoregression[J]. Journal of the Royal Statistical Society. Series B (Methodological), 1979, 41: 190-195.
