基于GPR-DE模型的CO_(2)-原油体系最小混相压力研究  

Study on minimum miscibility pressure of CO_(2)-crude oil system based on GPR-DE model

作　　者：侯智玮 刘勇[1] 叶锋[1] 官志锐[1] 石丹[1] 杨兴超 HOU Zhiwei;LIU Yong;YE Feng;GUAN Zhirui;SHI Dan;YANG Xingchao(Exploration and Development Research Institute,Liaohe Oilfield Company,CNPC,Panjin City,Liaoning Province,124010,China)

机构地区：[1]中国石油辽河油田分公司勘探开发研究院,辽宁盘锦124010

出　　处：《油气地质与采收率》2021年第3期126-133,共8页Petroleum Geology and Recovery Efficiency

基　　金：中国石油天然气股份公司重大科技专项“辽河油田千万吨稳产关键技术研究与应用”(2017E-16)。

摘　　要：在对中外35个CO_(2)驱油藏注入气体组分、油藏温度、原油组分、注入气体临界温度和最小混相压力进行数据统计和处理的基础上,结合高斯过程回归(GPR)与差分进化算法(DE),建立了预测CO_(2)-原油体系最小混相压力的新模型——GPR-DE模型。利用统计误差和图形误差评价GPR-DE模型的精确度,利用实验数据和敏感性分析对模型结果进行了验证,并与现有模型的预测结果进行对比。结果表明,GPR-DE模型与其他模型相比,精确度更高、应用范围更广,平均绝对相对误差仅为2.060%,标准差仅为0.0532。GPR-DE模型不仅可以预测CO_(2)-原油体系最小混相压力,还可以预测其他气体与原油体系最小混相压力。Based on the statistics and processing of injected gas composition,reservoir temperature,crude oil composition,critical temperature of injected gas,and minimum miscible pressure of 35 CO_(2) flooding reservoirs at home and abroad,a new GPR-DE model integrating Gaussian process regression(GPR)and differential evolution algorithm(DE)is proposed for predicting the minimum miscibility pressure of a CO_(2)-crude oil system.The accuracy of the GPR-DE model is evaluat⁃ed with regard to statistical errors and graphical errors.The model results are verified by experimental data and sensitivity analysis and compared with the prediction results of existing models.The results demonstrate that,compared with other models,the GPR-DE model has higher accuracy and wider applicability,with the average absolute relative error of only 2.060%and the standard deviation of only 0.0532.The GPR-DE model can predict the minimum miscibility pressure of the CO_(2)-crude oil system and other gas and crude oil systems.

关 键 词：CO_(2) 最小混相压力 高斯过程回归 差分进化算法 GPR-DE模型 

分 类 号：TE348[石油与天然气工程—油气田开发工程]