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.
H. R. Nejati; Seyed A. Moosavi
Abstract
Assessment of the correlation between rock brittleness and rock fracture toughness has been the subject of extensive research works in the recent years. Unfortunately, the brittleness measurement methods have not yet been standardized, and rock fracture toughness cannot be estimated satisfactorily by ...
Read More
Assessment of the correlation between rock brittleness and rock fracture toughness has been the subject of extensive research works in the recent years. Unfortunately, the brittleness measurement methods have not yet been standardized, and rock fracture toughness cannot be estimated satisfactorily by the proposed indices. In the present study, statistical analyses are performed on some data collected from the literature to develop two equations for estimation of modes I and II fracture toughness. Then a probabilistic sensitivity analysis is performed to determine the impact of the input parameters on the output ones. Based on the results obtained for the probabilistic analysis, a new empirical brittleness index including tensile strength, uniaxial compressive strength, and elastic modulus is suggested for estimating modes I and II fracture toughness. The analyses results reveal that the proposed index is capable of estimating rock fracture toughness with more satisfactory correlation compared to the previous indices.
