Summary Two of the most critical properties for multiphase flow in a reservoir are relative permeability (Kr) and capillary pressure (Pc). To determine these parameters, careful interpretation of coreflooding and centrifuge experiments is necessary. In this work, a machine learning (ML) technique was incorporated to assist in the determination of these parameters quickly and synchronously for steady-state drainage coreflooding experiments. A state-of-the-art framework was developed in which a large database of Kr and Pc curves was generated based on existing mathematical models. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from the corefloods including pressure drop and water saturation profile, along with other conventional core analysis data, were fed as features into the ML model. The entire data set was split into 70% for training, 15% for validation, and the remaining 15% for the blind testing of the model. The 70% of the data set for training teaches the model to capture fluid flow behavior inside the core, and then 15% of the data set was used to validate the trained model and to optimize the hyperparameters of the ML algorithm. The remaining 15% of the data set was used for testing the model and assessing the model performance scores. In addition, K-fold split technique was used to split the 15% testing data set to provide an unbiased estimate of the final model performance. The trained/tested model was thereby used to estimate Kr and Pc curves based on available experimental results. The values of the coefficient of determination (R2) were used to assess the accuracy and efficiency of the developed model. The respective crossplots indicate that the model is capable of making accurate predictions with an error percentage of less than 2% on history matching experimental data. This implies that the artificial-intelligence- (AI-) based model is capable of determining Kr and Pc curves. The present work could be an alternative approach to existing methods for interpreting Kr and Pc curves. In addition, the ML model can be adapted to produce results that include multiple options for Kr and Pc curves from which the best solution can be determined using engineering judgment. This is unlike solutions from some of the existing commercial codes, which usually provide only a single solution. The model currently focuses on the prediction of Kr and Pc curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.

中文翻译：

---

用于特殊岩心数据分析的人工智能岩心洪水模拟器

总结 油藏中多相流最关键的两个特性是相对渗透率 (Kr) 和毛管压力 (Pc)。为了确定这些参数，需要仔细解释核心驱油和离心机实验。在这项工作中，结合了机器学习 (ML) 技术，以帮助快速、同步地确定这些参数，以进行稳态排水岩心驱替实验。开发了一个最先进的框架，其中基于现有的数学模型生成了一个大型的 Kr 和 Pc 曲线数据库。该数据库用于执行代表油水排水稳态实验的数千次岩心驱替模拟运行。从岩心驱替中获得的结果包括压降和含水饱和度剖面，与其他传统的岩心分析数据一起，作为特征输入到 ML 模型中。整个数据集分为 70% 用于训练，15% 用于验证，剩下的 15% 用于模型的盲测。用于训练的 70% 的数据集教导模型捕捉核心内部的流体流动行为，然后使用 15% 的数据集来验证训练的模型并优化 ML 算法的超参数。剩余 15% 的数据集用于测试模型和评估模型性能得分。此外，K-fold 拆分技术用于拆分 15% 的测试数据集，以提供对最终模型性能的无偏估计。因此，训练/测试模型用于根据可用的实验结果估计 Kr 和 Pc 曲线。确定系数 (R2) 的值用于评估所开发模型的准确性和效率。相应的交叉图表明，该模型能够对历史匹配实验数据进行准确的预测，误差百分比小于 2%。这意味着基于人工智能 (AI-) 的模型能够确定 Kr 和 Pc 曲线。目前的工作可能是解释 Kr 和 Pc 曲线的现有方法的替代方法。此外，ML 模型可以适应产生的结果，其中包括 Kr 和 Pc 曲线的多个选项，可以使用工程判断从中确定最佳解决方案。这与一些现有商业代码的解决方案不同，后者通常只提供一个解决方案。该模型目前侧重于预测排水稳态实验的 Kr 和 Pc 曲线；然而，这项工作也可以扩展到捕捉自吸循环。