Estimation of
Strength Properties of Some Rocks using Ball Mill Grinding Characteristics
Swamy V. Sahas, Kunar Mihir Bijay and Karra Ram Chandar
Disaster Advances; Vol. 18(5); 92-103;
doi: https://doi.org/10.25303/185da920103; (2025)
Abstract
The strength properties of rocks namely uniaxial compressive strength and tensile
strength are important in design and stability evaluation of various mining, geotechnical
engineering and other rock engineering projects. Accurate determination of these
properties relies on high-quality samples, but challenges like sample availability,
preparation of sample, cost and time constraints have led to an increasing reliance
on computational methods for prediction. In this context, an indirect approach is
proposed for predicting rock strength properties, specifically the uniaxial compressive
strength (UCS) and tensile strength (TS), using grinding characteristics of ball
mill, an unconventional yet indirect approach. A predictive modelling using multivariate
regression is carried out to estimate the relationship between UCS, TS and the grinding
characteristics of ball mill.
The developed models demonstrated high accuracy with R² values of 0.93 for UCS and
0.96 for TS. Performance evaluation metrics showed an RMSE of 6.03 MPa and a VAF
of 93.45% for UCS and an RMSE of 0.99 MPa and a VAF of 96.47% for TS. The validation
was performed using experimental UCS and TS values of basalt rocks along with ball
mill grinding test data. The error analysis revealed that UCS prediction error ranged
from 5.1% to 11.61% while TS prediction error varied between 4.26% and 16.39%.
