基于GA-SVR的CO2驱原油最小混相压力预测模型PREDICTING MODEL OF THE OIL MINIMAL MISCIBLE PRESSURE FOR THE CO2 FLOODING BASED ON GA-SVR
孙雷,罗强,潘毅,冯洋
SUN Lei,LUO Qiang,PAN Yi,FENG Yang
摘要(Abstract):
为了得到更精确的CO_2驱原油最小混相压力,考虑挥发组分(N_2+CO_2+CH_4+H_2S)含量、中间烃组分(C_(2-6))含量、重质组分(C_7~+)含量、重质组分的相对分子质量、重质组分密度以及温度的影响,建立了基于遗传算法参数寻优的支持向量回归机模型。模型优点在于使数据结构风险最小化,是基于数据精度高和回归函数复杂性适宜的条件下进行全局参数寻优得到最优模型,根据测试样本数据可以给出预测结果,得到更为准确的最小混相压力数值。该模型计算结果平均相对误差为3.44%,与文献中的实验结果、细管实验结果对比,具有较好的准确性。
In order to more precisely obtain the oil minimal miscible pressure of CO_2 flooding,considering the influences of the Use other people's result,study the various factors between contents of volatile( N_2+ CO_2+ CH_4+H_2S),intermediate hydrocarbon( C_(2-6)),heavy hydrocarbon( C_7~+),molecular weight( M_(C_7~+)) and density( ρ_(C_7~+))of the heavy components and temperature,the optimized support vector regression( SVR) machine model was established on the basis of the genetic algorithm( GA) parameters. The advantages of this model is to make the data structure risk minimal,which is the obtained optimized model from the overall parameters under the conditions of the high-precision data and suitable complexity of the regression function,and moreover with the help of the testing sample data,the predicted results were presented,thus the more accurate minimal miscible pressure value was obtained. Comparing the model calculation results with the experimental ones in the references and slim-tube test,the average relative error is 3. 44% i. e. much better accuracy is presented.
关键词(KeyWords):
CO_2驱;最小混相压力;遗传算法;模型;支持向量回归机
carbon dioxide(CO_2) flooding;minimum miscible pressure;genetic algorithm(GA);model;support vector regression(SVR) machine
基金项目(Foundation): 中国石油天然气股份有限公司“十二五”重大科技项目“天然气开发关键技术研究”(2011B-1507)
作者(Author):
孙雷,罗强,潘毅,冯洋
SUN Lei,LUO Qiang,PAN Yi,FENG Yang
参考文献(References):
- [1]徐阳.低渗油藏CO2近混相驱提高采收率机理研究[D].青岛:中国石油大学,2011.
- [2]黄世军,杨静宜,王利明,等.二氧化碳驱最小混相压力动态预测方法[J].大庆石油地质与开发,2016,35(4):121-125.
- [3]张可,李实,秦积舜,等.溶度差法计算地层油CO2体系的最小混相压力[J].特种油气藏,2013,20(1):122-125.
- [4]孙业恒,吕广忠,王延芳,等.确定CO2最小混相压力的状态方程法[J].油气地质与采收率,2006,13(1):82-84.
- [5]Amao A M,Siddiqui S,Menouar H,et al.A new look at the minimum miscibility pressure(MMP)determination from slim tube measurements[R].SPE-153383-MS,2012.
- [6]Cronquist C.Carbon dioxide dynamic miscibility with light reservoir oils[R].Proceeding of 4th Annual U.S.DOE Symposium,Tulsa,1978.
- [7]Lee J I.Effectiveness of carbon dioxide displacement under miscible and immiscible conditions[R].Calgary:Petroleum Recovery Institute,1979.
- [8]Yellig W F,Metcalfe R S.Determination and prediction of CO2minimum miscibility pressures[J].Journal of Petroleum Technology,1980,32(1):160-168.
- [9]Jensen C M.Interpretation of pressure composition phase diagrams for CO2/crude oil systems[J].Society of Petroleum Engineers Joumal,1984,24(5):485-497.
- [10]Glaso O.Generalized minimum miscibility pressure correlation[J].Society of Petroleum Engineers Joumal,1985,25(6):927-934.
- [11]Alomair O,Iqbal M.CO2Minimum Miscible Pressure(MMP)Estimation using Multiple Linear Regression(MLR)Technique[R].SPE-172184-MS,2014.
- [12]孙雷,纪明强,郑家朋,等.柳北砂砾岩油藏CO2驱提高采收率可行性[J].大庆石油地质与开发,2016,35(5):123-127.
- [13]余华杰,朱国金,田冀.海上强边底水油帽稠油油藏注CO2提高采收率[J].大庆石油地质与开发,2013,32(5):137-142.
- [14]Vapnik V.The nature of statistical learning theory[M].New York:Springer-Verlag,1999.
- [15]Li Huazhou,Qin Jishun,Yang Daoyong.An Improved CO2-Oil Minimum Miscibility Pressure Correlation for Live and Dead Crude Oils[J].Industrial&Engineering Chemistry Research,2012,51(8):3516-3523.
- [16]Jaubert J N,Avaullee L,Souvay J F.A crude oil data bank containing more than 5000 PVT and gas injection data[J].Journal of Petroleum Science&Engineering,2002,34(1-4):65-107.
- [17]Zuo Y X,Chu J Z,Ke S L,et al.Study on the minimum miscibility pressure for miscible flooding systems[J].Journal of Petroleum Science&Engineering,1993,8(4):315-328.
- [18]Eakin B E,Mitch F J.Measurement and correlation of miscibility pressures of reservoir oils[R].SPE 18065,1988.
- [19]孙业恒,吕广忠,王延芳,等.确定CO2最小混相压力的状态方程法[J].油气地质与采收率,2006,13(1):82-84.
- [20]Alston R B,Kokolis G P,James C F.CO2minimum miscibility pressure:a correlation for impure CO2streams and live oil systems[J].Society of Petroleum Engineers Journal,1985,25(2):268-274.
- [21]Metcalfe R S,Yarborought L.Discussion[J].Journal of Petroleum Technology,1974,26(12):1463-1437.
- [22]Rathmell J J,Stalkup F I,Hassinger R C.A laboratory investigation of miscible displacement by carbon dioxide[R].SPE 3483,1971.
- [23]Yuan H,John R T,Egwuenu A M,et al.Improved MMP correlations for CO2floods using analytical gas flooding theory[J].SPE Reserroir Evalution&Engineering,2004,8(5):6-18.
- [24]Dong M,Huang D,Dyer S B,et al.A comparison of CO2minimum miscibility pressure determinations of Weyburn crude oil[J].Journal of Petroleum Science&Engineering,2001,31(1):13-22.
- [25]Shelton J L,Yarborough L.Multiple phase behavior in porous media during CO2or rich-gas flooding[J].Journal of Petroleum Technology,1977,29(9):1711-1178.
- [26]张平,赵荣彩,李清宝.基于相关性的同步优化算法[J].计算机工程,2005,31(17):68-70.
- [27]Sebastian H M,Rrenner T A,Wenger R S.Correlation of minimum miscibility pressure for impure CO2stream[R].SPE12648,1984.
- [28]Abdassah D,Siregar S,Kristanto D.The Potential of Carbon Dioxide Gas Injection Application in Improved Oil Recovery[R].SPE 64730,2000.
- [29]Dichary R M,Perryman T L,Ronquille J D.Evaluation and Design of a CO2Miscible Flood Project-SACROC Unit,Kelly-Snyder Filed[J].Journal of Petroleum Technology,1973,25(11):1309-1318.
- [30]Cardenas R L,Alston R B,Nute A J,et al.Laboratory Design of a Gravity-Stable Miscible CO2Process[J].Journal of Petroleum Technology,1984,36(1):111-118.
- [31]Chaback J J,William M L.Phase Equilibria in the SACROC OilCarbon Dioxide System[J].SPE Reservoir Engineering,1986,3(1):103-111.
- [32]Spence A S Jr,Watkins R W.The Effect of Microscopic Core Heterogeneity on Miscible Flood Residual Oil Saturation[R].SPE-9229-MS,1980.
- [33]侯大力,罗平亚,孙雷,等.预测烃类气体—原油体系最小混相压力的改进模型[J].新疆石油地质,2013,34(6):684-688.