Journal
ENGINEERING WITH COMPUTERS
Volume 33, Issue 1, Pages 1-11Publisher
SPRINGER
DOI: 10.1007/s00366-016-0451-4
Keywords
Compressive strength; Shear strength; Regression analysis; Artificial neural network; P-wave velocity
Ask authors/readers for more resources
Uniaxial compressive and shear strength are two of the very important parameters, commonly required in the initial stages of planning and design of rock engineering projects. So, an attempt has been made in this study to predict compressive and shear strength (output) of rocks from some simple and easily determinable parameters in laboratory viz., point load index, tensile strength, unit weight and ultrasonic velocity (input). Failure modes have also been studied and correlated with their ultrasonic velocity. The study uses two of the most commonly used predictive mathematical techniques: statistical analysis and neural networks to predict the strength parameters. The regression analysis shows that the rock quality parameters are very well correlated with the ultrasonic velocity except for the unit weight. Unlike few researchers in the past, a linear correlation was best suited for the rock quality parameters in this study. On the other hand, Artificial Neural Network (ANN) was able to predict the same strength parameters with a better reliability than regression analysis. The study shows that the proposed method for the prediction of UCS and shear strength is acceptable and can be reliably applied in various rock engineering problems.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available