Rock Mass Classification by Multivariate Statistical Techniques and Artificial Intelligence
- PDF / 1,613,252 Bytes
- 22 Pages / 547.087 x 737.008 pts Page_size
- 10 Downloads / 212 Views
(0123456789().,-volV) ( 01234567 89().,-volV)
ORIGINAL PAPER
Rock Mass Classification by Multivariate Statistical Techniques and Artificial Intelligence Allan Erlikhman Medeiros Santos . Milene Sabino Lana . Tiago Martins Pereira
Received: 7 August 2020 / Accepted: 2 November 2020 Springer Nature Switzerland AG 2020
Abstract This study aims to improve the quality and accuracy of RMR classification system for rock masses in open pit mines. A database of open pit mines comprising basic parameters for obtaining the RMR was used. Techniques applied in this research were multivariate statistics and artificial intelligence. In relation to multivariate statistics, factor analysis was capable of identifying underlying factors not observable in the original variables, using the variables of these factors in the classification system, instead of all RMR variables. The proposed classifier was obtained by training neural networks. The results of the factor analysis allowed the identification of three common factors. Factor 1 represents the strength and weathering of the rock mass. Factor 3 represents the fracturing degree of the rock mass. Finally Factor 2 represents water flow conditions. Thirty artificial
A. E. M. Santos M. S. Lana (&) Graduate Program in Mineral Engineering – PPGEM, Federal University of Ouro Preto – UFOP, Campi Morro Do Cruzeiro, Bauxita, Ouro Preˆto, MG CEP: 35400000, Brazil e-mail: [email protected] A. E. M. Santos e-mail: [email protected] T. M. Pereira Statistics Department – DEEST, Federal University of Ouro Preto – UFOP, Campi Morro Do Cruzeiro, Bauxita, Ouro Preto, MG CEP: 35400000, Brazil e-mail: [email protected]
neural networks were trained with randomly selected training samples. The trained networks proved to be effective and stable. Regarding the validation of the networks, the values obtained for the overall probability of success and apparent error rate showed normal distributions and a low dispersion rate, with average rates of 0.87 and 0.13, respectively. Regarding specific errors, error values were recorded only between contiguous RMR classes. The major contribution of the study is to present a new methodology for achieving rock mass classifications based on mathematical and statistical fundamentals, aiming at optimising the selection of variables and consequent reduction of subjectivity in the parameters and classification methods. Keywords Rock mass classifications Factor analysis Artificial neural networks Geomechanical parameters Open pit mine
1 Introduction Rock mass classification systems were originally proposed for establishing supports in underground excavations; since then, many systems have been proposed and modified for various purposes. The classical classification systems include the Rock Mass Rating (RMR) proposed by Bieniawski (1973), the Q system, Rock Mass Quality (Q) proposed by Barton
123
Geotech Geol Eng
et al. (1974), and the Geological Strength Index proposed by Hoek (1994) and Hoek et al. (1995), all of which widely accepted in engi
Data Loading...
