Alakbari Fahd Saeed, Mahmood Syed Mohammad, Bamumen Salem Saleh, Tsegab Haylay, Hagar Haithm Salah, Babikir Ismailalwali, Darkwah-Owusu Victor
Center of Flow Assurance, Institute of Subsurface Resources, Universiti Teknologi PETRONAS, 32610 Seri Iskandar, Perak Darul Ridzuan, Malaysia.
Petroleum Engineering Department, Universiti Teknologi PETRONAS, 32610 Seri Iskandar, Perak Darul Ridzuan, Malaysia.
ACS Omega. 2024 Sep 19;9(39):40687-40706. doi: 10.1021/acsomega.4c04930. eCollection 2024 Oct 1.
Static Young's modulus ( ) is a critical property required in numerous petroleum calculations. Various models to forecast have been proposed in the literature. However, existing models, by and large, lack precision and are confined to specific data set ranges. This study proposes an alternative approach for determination, utilizing different machine learning methods, such as an adaptive neuro-fuzzy inference system (ANFIS). In these proposed methods, the predictor variables include bulk formation density (RHOB), shear wave velocity (DTs), and compressional wave velocity (DTc). The models were trained on a data set comprising 1853 hydrocarbon reservoir rock samples from globally diverse locations. They were evaluated using trend, group error, and statistical error analyses. To test the efficacy of the proposed models, the optimally performing model was identified and used to detect the rock types along with the previously published models. Results indicated that ANFIS is the optimum model and can predict with an average absolute percentage relative error (AAPRE) of 5.1% and a correlation coefficient () of 0.9602. The ANFIS method has some benefits over other machine learning approaches insofar as its superiority in reaching a quicker decision about the mapped relationship between the inputs and outputs because it combines artificial neural networks and fuzzy logic in one tool. The ANFIS can perform a highly nonlinear mapping and displays a better learning ability. The proposed ANFIS model demonstrates its ability to capture accurate physical relationships between input rock properties and through trend analysis, which shows that increasing the RHOB increases the . Contrarily, increasing the DTc and DTs reduces the . Furthermore, the ANFIS model can accurately detect the rock types based on its determinations. This research demonstrates the importance of accurately predicting for the proper identification of rock types. Thus, this study offers potential advancements in geological assessments of hydrocarbon reservoirs and improvements in many petroleum engineering applications.
静态杨氏模量（ ）是众多石油计算中所需的关键属性。文献中已提出各种预测 的模型。然而，现有的模型总体上缺乏精度，并且局限于特定的数据集范围。本研究提出了一种利用不同机器学习方法（如自适应神经模糊推理系统（ANFIS））来确定 的替代方法。在这些提出的方法中，预测变量包括地层体积密度（RHOB）、剪切波速度（DTs）和纵波速度（DTc）。这些模型是在一个包含来自全球不同地点的1853个油气藏岩石样本的数据集上进行训练的。使用趋势分析、分组误差分析和统计误差分析对它们进行评估。为了测试所提出模型的有效性，确定了性能最优的模型，并将其与先前发表的模型一起用于检测岩石类型。结果表明，ANFIS是最优模型，能够以5.1%的平均绝对百分比相对误差（AAPRE）和0.9602的相关系数（ ）预测 。ANFIS方法相对于其他机器学习方法具有一些优势，因为它在将人工神经网络和模糊逻辑结合在一个工具中，从而在对输入和输出之间的映射关系做出更快决策方面具有优越性。ANFIS可以进行高度非线性映射，并显示出更好的学习能力。所提出的ANFIS模型通过趋势分析展示了其捕捉输入岩石属性与 之间准确物理关系的能力，这表明增加RHOB会增加 。相反，增加DTc和DTs会降低 。此外，ANFIS模型可以根据其对 的确定准确检测岩石类型。本研究证明了准确预测 对于正确识别岩石类型的重要性。因此，本研究为油气藏的地质评估提供了潜在的进展，并在许多石油工程应用中有所改进。
