首页    期刊浏览 2025年02月20日 星期四
登录注册

文章基本信息

  • 标题:Oil‐CO2 minimum miscible pressure (MMP) determination using a stimulated smart approach
  • 本地全文:下载
  • 作者:Ghassem Zargar ; Parisa Bagheripour ; Mojtaba Asoodeh
  • 期刊名称:Canadian Journal of Chemical Engineering
  • 印刷版ISSN:0008-4034
  • 出版年度:2015
  • 卷号:93
  • 期号:10
  • 页码:1730-1735
  • DOI:10.1002/cjce.22265
  • 语种:English
  • 出版社:Chemical Institute of Canada
  • 摘要:Multi‐contact miscible displacement of reservoir petroleum by injection of the relatively inexpensive carbon dioxide (CO2) gas represents one of the most efficient currently available techniques of enhanced oil recovery. Experimental determination of optimal injection pressure, known as minimum miscible pressure (MMP), is very costly, laborious, and time‐intensive. Therefore, the quest for a quick, cost‐effective, and accurate way of determining MMP is inevitable. In this study an improved approach was followed to predict oil‐CO2 MMP. First, input/output data are transformed to a higher correlated data space using an alternative condition expectation (ACE) algorithm to reduce complexity of the problem for a generalized regression neural network (GRNN). Then, transformed data are introduced to the GRNN to construct a model for estimation of MMP. Eventually, a hybrid genetic algorithm‐pattern search technique is employed for optimizing the GRNN and producing more accurate estimations. This model was constructed using worldwide experimental data from open literature. The performance of the constructed model was assessed by introducing experimental data from Iran Oils as test data. A comparison between the current study and previous models, including outstanding correlations and intelligent systems, demonstrated the superiority of the proposed model.
  • 关键词:enmulti‐contact miscible displacementoil‐CO2 MMPGA‐PSACENN
国家哲学社会科学文献中心版权所有