Investigating average infrared radiation temperature characteristics during shear and tensile cracks in sandstone under different water contents

Abstract

Shear loading and water contents can accelerate rock deformation and fracturing during loading and mining activities. The prediction of the patterns of cracks in rocks under shear loading is thus crucial for the safe and efficient execution of these activities. Previously, crack patterns were classified using Acoustic Emission (AE). Determination of the type of crack patterns on site is not only cumbersome, but may also lead to inaccurate results due improper execution of the AE procedures. Also, there is no proper experimental study which truly reflects the relationship between Average Infrared Radiation Temperature (AIRT) and crack type. In this study, AE and AIRT were used to examine the crack patterns followed by determination of the effect of sandstone crack formation, under varying water and loading conditions, on AIRT. It was found that the increase in water contents lowers AE and strain, and increases shear stress. A linear decrease in AIRT with loading time followed by a sudden increase at the point of failure was observed in dry rocks contrary to a nonlinear trend in rocks with increasing water content. The absolute rate of AIRT increases shear and decrease in tensile crack. Moreover, Shear cracks dominated pre-set shearing tests, and the ratio of acoustic fracturing to radial cracking varied with the level of water contents and loading method. Furthermore, the employed machine learning models (Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM)) demonstrated accurate classification of shear and tensile cracks with both AIRT and RF data. Based on performance metrics i.e., precision, recall, and F1 score, RF fared better than AIRT with performance metrics (precision = 1, recall = 1, and F1 score = 1). The research offered valuable guidelines for experts to predict cracks and rock failure in rocks, aiding efficient relevant engineering project monitoring and execution.