蒸汽驱油过程优化问题的数值模拟  

Numerical Simulation Study on Optimization of Steam Flooding Process

作　　者：吕梦瑶 LYU Meng-yao(School of Resources and Environment,Yangtze University,Wuhan 430100,China)

机构地区：[1]长江大学资源与环境学院,武汉430100

出　　处：《当代化工》2021年第2期451-454,共4页Contemporary Chemical Industry

基　　金：国家科技重大专项课题,致密油气藏数值模拟新方法与开发设计(项目编号:2017ZX05009-005)。

摘　　要：将动态或时间相关的代理模型用于蒸汽驱油过程中的不确定性分析和优化研究。计算过程中引入了一种新的时变人工神经网络作为动态响应面,进而确保了其在整个过程时间间隔内的有效性。通过将此响应面与遗传算法结合,可以在无浸层状稠油油藏中获得最佳注入条件,例如蒸汽注入速率、蒸汽质量以及最佳注入时间。此种方式可作为一种快速且具有成本效益的工具,用于稠油油藏蒸汽驱油过程中的风险分析和优化。Dynamic or time-dependent proxy models were used for uncertainty analysis and optimization research in the process of steam flooding. A new time-varying artificial neural network was introduced as a dynamic response surface in the calculation process, which in turn ensured its effectiveness in the entire process time interval. By combining this response surface with genetic algorithm, the best injection conditions in the non-immersion layered heavy oil reservoir were obtained, such as steam injection rate, steam quality and optimal injection time. This method can be used as a fast and cost-effective tool for risk analysis and optimization of steam flooding in heavy oil reservoirs.

关 键 词：模型 蒸汽驱油 流程优化 动态 油藏 

分 类 号：TQ013.2[化学工程]