Enayatallah Emami Meybodi; Syed Khaliq Hussain; Mohammad Fatehi Marji
Abstract
In this research work, X-ray diffraction (XRD) tests and petrographic studies are performed to analyze the mineral composition and lamination in the shale rock specimens. Afterward, point load (PL) and uniaxial compressive strength (UCS) tests are carried out on the anisotropic laminated shale rock. ...
Read More
In this research work, X-ray diffraction (XRD) tests and petrographic studies are performed to analyze the mineral composition and lamination in the shale rock specimens. Afterward, point load (PL) and uniaxial compressive strength (UCS) tests are carried out on the anisotropic laminated shale rock. Based on the macro-mechanical properties of these tests, the discrete element method implemented in a two-dimensional particle flow code (PFC2D) is adjusted to numerically simulate the shale rock specimens. The aim of this work is to validate the numerical models by failure process, stress-strain curves, and peak failure strengths of the shale samples. Therefore, point load test is used for assessing the pattern failure mechanism, and uniaxial compressive strength test is performed for obtaining the stress-strain curves and peak strength failure points in the laboratory shale rock samples. Validation of peak strengths criteria provides the best results; the determination coefficient values for lab and numerical modeling with (R2 = 0.99). Several numerical models are prepared for estimating the mechanical behavior of shale rocks in PFC2D. The smooth joint model (SJM) is used for preparing the consistent and appropriate constitutive models for simulating the mechanical behavior of laminated shale. It is concluded that SJM provides more reasonable results for laminated shale rock that can be used for several petroleum engineering projects, especially in the central geological zone of Iran.
E. Emami Meybodi; Syed Kh. Hussain; M. Fatehi Marji; V. Rasouli
Abstract
In this work, the machine learning prediction models are used in order to evaluate the influence of rock macro-parameters (uniaxial compressive strength, tensile strength, and deformation modulus) on the rock fracture toughness related to the micro-parameters of rock. Four different types of machine ...
Read More
In this work, the machine learning prediction models are used in order to evaluate the influence of rock macro-parameters (uniaxial compressive strength, tensile strength, and deformation modulus) on the rock fracture toughness related to the micro-parameters of rock. Four different types of machine learning methods, i.e. Multivariate Linear Regression (MLR), Multivariate Non-Linear Regression (MNLR), copula method, and Support Vector Regression (SVR) are used in this work. The fracture toughness of mode I and mode II (KIC and KIIC) is selected as the dependent variable, whereas the tensile strength, compressive strength, and elastic modulus are considered as the independent variables, respectively. The data is collected from the literature. The results obtained show that the SVR model predicts the values of KIC and KIIC with the determination coefficients (R2) of 0.73 and 0.77. The corresponding determination coefficient values of the MLR model and the MNLR model for KI and KII are R2 = 0.63, R2 = 0.72, and R2 = 0.62,0.75, respectively. The copula model predicts that the value of R2 for KI is 0.52, and for KII R2=0.69. K-fold cross-validation testing method performs for all these machine learning models. The cross-validation technique shows that SVR is the best-designed model for predicting the fracture toughness mode-I and mode-II.