[1]谷建伟,隋顾磊,李志涛,等.基于ARIMA-Kalman滤波器数据挖掘模型的油井产量预测[J].深圳大学学报理工版,2018,35(6):575-581.[doi:10.3724/SP.J.1249.2018.06575]
　GU Jianwei,SUI Gulei,LI Zhitao,et al.Oil well production forecasting method based on ARIMA-Kalman filter data mining model[J].Journal of Shenzhen University Science and Engineering,2018,35(6):575-581.[doi:10.3724/SP.J.1249.2018.06575]
点击复制

基于ARIMA-Kalman滤波器数据挖掘模型的油井产量预测()
分享到：

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第35卷
期数:
2018年第6期
页码:
575-581
栏目:
【环境与能源】
出版日期:
2018-11-16

文章信息/Info

Title:
Oil well production forecasting method based on ARIMA-Kalman filter data mining model
作者:
谷建伟1; 隋顾磊1; 李志涛1; 刘巍1; 王依科1; 张以根2; 崔文富3
1）中国石油大学（华东）石油工程学院，山东青岛 266580
2）中国石化胜利油田分公司勘探开发研究院，山东东营 257015
3）中国石化胜利油田分公司胜利采油厂，山东东营 257015
Author(s):
GU Jianwei1;  SUI Gulei1;  LI Zhitao1;  LIU Wei1;  WANG Yike1;  ZHANG Yigen2;  and CUI Wenfu3
1) School of Petroleum Engineering, China University of Petroleum (East China), Qingdao 266580, Shandong Province, P.R.China
2) Institute of Petroleum Exploration and Development, Shengli Oilfield Branch Company, SINOPEC, Dongying 257015, Shandong Province, P.R.China
3) Shengli Oil Production Plant, SINOPEC, Dongying 257015, Shandong Province, P.R.China
关键词:
油气田开发工程; 时间序列; 产量预测; 数据挖掘; ARIMA模型; 卡尔曼滤波器
Keywords:
oil and gas field development engineering;  time series;  production forecast;  data mining;  autoregressive integrated moving average (ARIMA) model;  Kalman filter
分类号:
TE 341
DOI:
10.3724/SP.J.1249.2018.06575
文献标志码:
A
摘要:
影响水驱开发油田产量的因素众多，针对常规产量预测方法无法考虑时序影响因素的非同步性以及滞后性，应用时间序列分析方法，结合卡尔曼滤波器(Kalman filter)，建立考虑因素动态关系的产量ARIMA-Kalman滤波器时间序列模型．根据历史产量数据建立时间序列中的产量差分自回归积分移动平均(autoregressive integrated moving average, ARIMA)模型；再将ARIMA模型与Kalman滤波器相结合，构建产量预测算法；以实例油田资料开展机器学习和数据挖掘，并采用数据拟合及预测检验评价算法合理性，实现最终产量数据预测．研究结果表明，ARIMA-Kalman滤波器具有高效的时序影响因素的分析能力，能够排除非同步性和滞后性的影响，使识别出的产量时间序列模型具有精准的拟合结果和预测能力．该研究可为油田产量预测提供一种有效方法，为后续的油井开采提供决策和理论依据．
Abstract:
There are many factors affecting oilfield production in water flooding development. The conventional production forecasting method cannot consider the effects of asynchronization and hysteresis of the timing factors. In this paper, the time series analysis is adopted by combining with Kalman filter to establish the ARIMA-Kalman filter time series model of production considering dynamic relationship. Firstly, the ARIMA (autoregressive integrated moving average) model time series model of production is established according to the production history data. Secondly, the ARIMA model is combined with Kalman filter to build an oilfield forecasting algorithm. Finally, we carry out machine learning and data mining for the actual oilfield data, and apply data fitting and predictive testing to evaluate the rationality of the new algorithm, then achieve the ultimate oilfield production forecasting. The research results show that ARIMA-Kalman filter has the ability to analyze time series factors by eliminating the effects of asynchronization and hysteresis. The identified production time series model can deliver accurate fitting results and predictive ability. This research work can provide an effective method for oilfield production forecasting, and deliver reliable decision-making and basis for subsequent oil well production.

参考文献/References:

［1］ 刘秀婷，杨军，程仲平，等．油田产量预测的新方法及其应用［J］．石油勘探与开发，2002(4)：74-76．
LIU Xiuting, YANG Jun, CHENG Zhongping, et al. A new method of predicting oilfield output and its application［J］. Petroleum Exploration and Development, 2002(4): 74-76.(in Chinese)
［2］ 刘晓华，邹春梅，姜艳东，等．现代产量递减分析基本原理与应用［J］．天然气工业，2010，30(5)：50-54．
LIU Xiaohua, ZOU Chunmei, JIANG Yandong, et al. Theory and application of modern production decline analysis［J］. Natural Gas Industry, 2010, 30(5): 50-54.(in Chinese)
［3］ 钟仪华．特高含水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 ulter-high water-cut stage　［J］. Chengdu: Southwest Petroleum University, 2008.(in Chinese)
［4］ 马林茂，李德富，郭海湘，等．基于遗传算法优化BP神经网络在原油产量预测中的应用：以大庆油田BED试验区为例［J］．数学的实践与认识，2015，45(24)：117-128．
MA Linmao, LI Defu, GUO Haixiang, et al. BP neural network based on genetic algorithm applied in crude oil production forecast: taking the BED test area of the Daqing Oilfield as an example［J］. Mathematics in Practice and Theory, 2015, 45(24): 117-128.(in Chinese)
［5］ 钟仪华，林旭旭，刘雨鑫．基于多元混沌时间序列的油田产量预测模型［J］．数学的实践与认识，2016，46(6)：99-105．
ZHONG Yihua, LIN Xuxu, LIU Yuxin. The oilfield output prediction model based on multivariate chaotic time series［J］. Mathematics in Practice and Theory, 2016, 46(6): 99-105.(in Chinese)
［6］ 马新．基于灰色系统与核方法的油藏动态预测方法研究［D］．成都：西南石油大学，2016．
MA Xin. Study on dynamical prediction methods based on grey system and kernel method［D］. Chengdu: Southwest Petroleum University, 2016.(in Chinese)
［7］ EDIGER V S, AKAR S, UURLU B. Forecasting production of fossil fuel sources in Turkey using a comparative regression and ARIMA model［J］. Energy Policy, 2006, 34(18): 3836-3846.
［8］ 王滨，赵伟，计小宇，等．基于传递函数模型的油田产油量预测方法［J］．油气地质与采收率，2014，21(5)：77-80．
WANG Bin, ZHAO Wei, JI Xiaoyu, et al. Oilfield output prediction method based on transfer function model［J］. Petroleum Geology and Recovery Efficiency, 2014, 21(5): 77-80.(in Chinese)
［9］ FRAUSTO-SOLS J, CHI-CHIM M, SHEREMETOV L. Forecasting oil production time series with a population-based simulated annealing method［J］. Arabian Journal for Science and Engineering, 2015, 40(4): 1081-1096.
［10］ HARVEY A C. Forecasting, structural time series models and the Kalman filter［M］. Cambridge, UK: Cambridge University Press, 1990.
［11］ XU Dongwei, WANG Yongdong, JIA Limin, et al. Real-time road traffic state prediction based on ARIMA and Kalman filter［J］. Frontiers of Information Technology & Electronic Engineering, 2017, 18(2): 287-302..
［12］ 王燕．应用时间序列分析［M］．4版．北京：中国人民大学出版社，2015．
WANG Yan. Applied time series analysis［M］. 4th ed. Beijing: China Renmin University Press, 2015.(in Chinese)
［13］ XIN Jingzhou, ZHOU Jianting, YANG S X, et al. Bridge structure deformation prediction based on GNSS data using Kalman-ARIMA-GARCH model［J］. Sensors, 2018, 18(1): 298.
［14］ JANSSON M, STOICA P. Optimal Yule walker method for pole estimation of ARMA signals［C］// In: 13th IFAC Sympium on Systemium Identification. Rotterdam. Netherlands:［s. n.］, 2003, 36(16):1891-1895.
［15］ 邓露，张晓峒．ADF检验中滞后长度的选择——基于ARIMA(0, 1, q)过程的模拟证据［J］．数量经济技术经济研究，2008(9)：126-138．
DENG Lu, ZHANG Xiaotong. The lag length selection in ADF test: simulation evidence from an ARIMA (0, 1, q) process［J］. The Journal of Quantitative & Technical Economics, 2008(9):126-138.(in Chinese)
［16］ HO S L, XIE M, GOH T N. A comparative study of neural network and Box-Jenkins ARIMA modeling in time series prediction［J］. Computers & Industrial Engineering, 2002, 42(2/3/4):371-375.
［17］ LIU Hui, TIAN Hongqi, LI Yanfei. Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction［J］. Applied Energy, 2012, 98(1): 415-424.

相似文献/References:

[1]罗建新,张烈辉,赖南君,等.两区线性复合油藏产能典型理论曲线分析[J].深圳大学学报理工版,2011,28(No.5(377-470)):384.
　LUO Jian-xin,ZHANG Lie-hui,LAI Nan-jun,et al.Typical deliverability curve analysis in bi-zonal linear composite reservoirs[J].Journal of Shenzhen University Science and Engineering,2011,28(6):384.
[2]姚同玉,李继山,黄延章.温度和有效应力对低渗储层孔渗性质的影响[J].深圳大学学报理工版,2012,29(No.2(095-188)):154.[doi:10.3724/SP.J.1249.2012.02154]
　YAO Tong-yu,LI Ji-shan,and HUANG Yan-zhang.Effects of temperature and stress on porosity and permeability of low permeability reservoir[J].Journal of Shenzhen University Science and Engineering,2012,29(6):154.[doi:10.3724/SP.J.1249.2012.02154]
[3]王传飞,吴光焕,韦涛,等.薄层特超稠油油藏双水平井SAGD开发指标预测模型[J].深圳大学学报理工版,2015,32(5):473.[doi:10.3724/SP.J.1249.2015.05473]
　Wang Chuanfei,Wu Guanghuan,Wei Tao,et al.Predictive models of dual horizontal well SAGD for thin formation and super heavy oil reservoirs[J].Journal of Shenzhen University Science and Engineering,2015,32(6):473.[doi:10.3724/SP.J.1249.2015.05473]
[4]苏玉亮,姜妙伦,孟凡坤,等.基于分流理论的低渗透油藏CO2泡沫驱渗流模拟[J].深圳大学学报理工版,2018,35(2):187.[doi:10.3724/SP.J.1249.2018.02187]
　SU Yuliang,JIANG Miaolun,MENG Fankun,et al.Flow modelling of CO2 foam flooding in low permeability reservoirs based on fractional flow function[J].Journal of Shenzhen University Science and Engineering,2018,35(6):187.[doi:10.3724/SP.J.1249.2018.02187]
[5]秦辉东,杨加,李笑难,等.基于多特征的DNS异常检测技术研究[J].深圳大学学报理工版,2020,37(增刊1):36.[doi:10.3724/SP.J.1249.2020.99036]
　QIN Huidong,YANG Jia,LI Xiaonan,et al.Research on DNS anomaly detection technology based on multiple features[J].Journal of Shenzhen University Science and Engineering,2020,37(6):36.[doi:10.3724/SP.J.1249.2020.99036]
[6]戴彩丽,等.微纳孔隙油-水-岩石微观界面相互作用研究进展[J].深圳大学学报理工版,2021,38(6):551.[doi:10.3724/SP.J.1249.2021.06551]
　DAI Caili,CAO Mengjiao,et al.Research progress on oil-water-rock interface interaction in micro-nano porous medium[J].Journal of Shenzhen University Science and Engineering,2021,38(6):551.[doi:10.3724/SP.J.1249.2021.06551]
[7]曹小朋.页岩油储层微观特征分析与流动模拟[J].深圳大学学报理工版,2021,38(6):605.[doi:10.3724/SP.J.1249.2021.06605]
　CAO Xiaopeng.Microscopic characteristics analysis and flow simulation of shale oil reservoir[J].Journal of Shenzhen University Science and Engineering,2021,38(6):605.[doi:10.3724/SP.J.1249.2021.06605]

备注/Memo

备注/Memo:
Received：2018-08-01；Accepted：2018-09-01
Foundation：National Science and Technology Major Project of China（2016ZX05011-001）
Corresponding author：Professor GU Jianwei. E-mail: gjwLcp@163.com
Citation：GU Jianwei, SUI Gulei, LI Zhitao, et al. Oil well production forecasting method based on ARIMA-Kalman filter data mining model［J］. Journal of Shenzhen University Science and Engineering, 2018, 35(6): 575-581.（in Chinese）
基金项目：国家科技重大专项基金资助项目（2016ZX05011-001）
作者简介：谷建伟（1971—），男，中国石油大学（华东）教授．研究方向：油气田开发．E-mail：gjwLcp@163.com
引文：谷建伟，隋顾磊，李志涛，等．基于ARIMA-Kalman滤波器数据挖掘模型的油井产量预测［J］. 深圳大学学报理工版，2018，35(6)：575-581.
更新日期/Last Update: 2018-11-30