Enayatallah Emami Meybodi; Fatemeh Taajobian
Abstract
Due to the challenge of finding identical rock samples with varying grain sizes, investigating the impact of texture on rock material has been given less attention. However, macroscopic properties such as compressive strength, tensile strength, and modulus of elasticity can indicate microscopic properties ...
Read More
Due to the challenge of finding identical rock samples with varying grain sizes, investigating the impact of texture on rock material has been given less attention. However, macroscopic properties such as compressive strength, tensile strength, and modulus of elasticity can indicate microscopic properties like intergranular resistance properties influence rock fracture toughness. In this work, both the experimental and numerical methods are used to examine the effect of grain size on the mechanical properties of sandstone. Uniaxial compressive strength and indirect tensile tests are conducted on sandstone samples with varying grain sizes, and the particle flow code software is used to model the impact of grain dimensions on intergranular properties. Flat joint model is applied for numerical modeling in the particle flow code© software. The aim of this work is to validate the numerical model by peak strength failure and stress-strain curves to determine the effect of grain size on the mechanical behavior. The results show that increasing grain size significantly decrease compressive strength, tensile strength, and modulus of elasticity. The impact of the change in grain size is more significant on compressive strength than on the other two properties. The correlation coefficient for tensile strength and grain size is R2 = 0.57, while for modulus of elasticity and grain size, it is R2 = 0.79. The PFC software helps calibrate intergranular properties, and investigate the effect of changing grain size on these properties. Overall, this study offers valuable insights into the relationship between the grain size and the mechanical properties of sandstone, which can be useful in various engineering applications, especially in petroleum geo-mechanics.
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.