Prethodno priopćenje
https://doi.org/10.17794/rgn.2016.2.5
MODELS TO ESTIMATE BRAZILIAN INDIRECT TENSILE STRENGTH OF LIMESTONE IN SATURATED STATE
Zlatko Briševac
orcid.org/0000-0001-7810-8255
; University of Zagreb, Mining, Geology and Petroleum Engineering Faculty, Pierottijeva 6, p.p. 390, 10000 Zagreb
Trpimir Kujundžić
orcid.org/0000-0003-0320-5338
; University of Zagreb, Mining, Geology and Petroleum Engineering Faculty, Pierottijeva 6, p.p. 390, 10000 Zagreb
Sažetak
There are a number of methods of estimating physical and mechanical characteristics. Principally, the most widely used is the regression, but recently the more sophisticated methods such as neural networks has frequently been applied, as well. This paper presents the models of a simple and a multiple regression and the neural networks – types Radial Basis Function and Multiple Layer Perceptron, which can be used for the estimate of the Brazilian indirect tensile strength in saturated conditions. The paper includes the issues of collecting the data for the analysis and modelling and the overview of the performed analysis of the efficacy assessment of the estimate of each model. After the assessment, the model which provides the best estimate was selected, including the model which could have the most wide-spread application in the engineering practice.
Ključne riječi
estimate; Brazilian indirect tensile strength; saturation; limestone; rock mechanics
Hrčak ID:
156734
URI
Datum izdavanja:
1.6.2016.
Posjeta: 2.172 *