Abstract Water alternating gas (WAG) is an enhanced oil recovery (EOR) method integrating the improved macroscopic sweep of water flooding with the increased microscopic displacement of gas injection. The optimal design of the WAG operating parameters is usually based on numerical reservoir simulation via trial and error. In this study, robust evolutionary algorithms are utilized to automatically optimize hydrocarbon WAG performance in the E-segment of the Norne field. Net present value (NPV) and two global semi-random search strategies, a genetic algorithm (GA) and particle swarm optimization (PSO), are used to optimize over an increasing number of operating parameters. The operating parameters include water and gas injection rates, bottom-hole pressures of the oil production wells, cycle ratio, cycle time, the composition of the injected hydrocarbon gas and the total WAG period. In progressive case studies, the number of decision-making variables is increased, increasing the problem complexity while potentially improving the efficacy of the WAG process. We also optimize the incremental recovery factor (IRF) within a fixed total WAG simulation time. The distinctions between the WAG parameters found by optimizing NPV and oil recovery are highlighted. This is the first known work to optimize over such a wide set of WAG variables and the first use of PSO to optimize a WAG project at the field scale. Compared to the reference cases, the best overall values of the objective functions found by GA and PSO were 13.8% and 14.2% higher, respectively, if NPV is optimized over all the above WAG operating variables, and 14.2% and 16.2% higher, respectively, if the IRF is optimized.

中文翻译：

---

Norne油田烃水交替气优化：演化算法的应用

摘要 水交替气（WAG）是一种提高采收率（EOR）方法，将改进的水驱宏观波及与增加注气的微观驱替相结合。WAG 操作参数的优化设计通常基于通过试错法进行的数值储层模拟。在这项研究中，利用稳健的进化算法自动优化 Norne 油田 E 段的碳氢化合物 WAG 性能。净现值 (NPV) 和两种全局半随机搜索策略，遗传算法 (GA) 和粒子群优化 (PSO)，用于优化越来越多的操作参数。作业参数包括注水注气速率、采油井井底压力、循环比、循环时间、注入烃气的组成和总 WAG 周期。在渐进式案例研究中，决策变量的数量增加，增加了问题的复杂性，同时潜在地提高了 WAG 过程的效率。我们还在固定的总 WAG 模拟时间内优化了增量恢复因子 (IRF)。突出显示了通过优化 NPV 和石油采收率发现的 WAG 参数之间的区别。这是第一个在如此广泛的 WAG 变量上进行优化的已知工作，也是首次使用 PSO 在现场规模优化 WAG 项目。与参考案例相比，如果 NPV 对上述所有 WAG 操作变量进行优化，GA 和 PSO 发现的目标函数的最佳总体值分别高出 13.8% 和 14.2%，分别高出 14.2% 和 16.2% ,