Estimation of mechanical properties of sedimentary rocks using multiple regression analysis

Since the accurate determination of uniaxial compressive strength (UCS) and modulus of elasticity (E) requires considerable time in collecting appropriate samples, their preparation and laboratory testing, development of predictive models for determining the mechanical properties of rocks seems to be essential in rock engineering. In this study, an attempt was made to develop a multivariable regression analysis (MLR) model in order to predict UCS and E of sedimentary rocks. For this, a database of laboratory tests was prepared, which includes porosity, P-wave velocity, dry density and water absorption as input parameters and UCS and E as output parameter. To make a database (including 196 datasets), different sedimentary rock samples are used. The performance of the MLR model is evaluated by comparing statistic parameters, including coefficient correlations (R), root mean square error (RMSE), mean error (MAE). To check the sensitivity of the empirical relations, a t test was performed which confirmed the validity of the proposed correlations.

Keywords:

UCS , E , Sedimentary Rocks , Linear Regression