Rock Mechanics
M. H. Kadkhodaei; E. Ghasemi
Abstract
The CERCHAR abrasivity test is very popular for determination of rock abrasivity. An accurate estimation of the CERCHAR abrasivity index (CAI) is useful for excavation operation costs. This paper presents a model to calculate CAI based on the gene expression programming (GEP) approach. This model is ...
Read More
The CERCHAR abrasivity test is very popular for determination of rock abrasivity. An accurate estimation of the CERCHAR abrasivity index (CAI) is useful for excavation operation costs. This paper presents a model to calculate CAI based on the gene expression programming (GEP) approach. This model is trained and tested based on a database collected from the experimental results available in the literature. The proposed GEP model predicts CAI based on two basic geomechanical properties of rocks, i.e. rock abrasivity index (RAI) and Brazilian tensile strength (BTS). Root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffe efficiency (NSE), and coefficient of determination (R2) are used to measure the model performance. Furthermore, the developed GEP model is compared with linear and non-linear multiple regression and other existing models in the literature. The results obtained show that GEP is a strong technique for the prediction of CAI.
Exploitation
E. Ghasemi
Abstract
In underground excavation, where the road-headers are employed, a precise prediction of the road-header performance has a vital role in the economy of the project. In this paper, a new model is developed for prediction of the road-header performance using the non-linear multivariate regression analysis. ...
Read More
In underground excavation, where the road-headers are employed, a precise prediction of the road-header performance has a vital role in the economy of the project. In this paper, a new model is developed for prediction of the road-header performance using the non-linear multivariate regression analysis. This model is able to estimate the instantaneous cutting rate (ICR) of roadheader based on rock properties such as Brazilian tensile strength (BTS), rock mass cuttability index (RMCI), and alpha angle (α: is the angle between the tunnel axis and the planes of weakness). In order to construct and test the proposed model, a database including 62 cutting cases is used in the Tabas coal mine No. 1 in Iran. Various statistical performance indices were employed to evaluate the model efficiency. The results obtained indicate that the proposed non-linear regression model can be efficiently used to predict the road-header cutting performance. Furthermore, the prediction capacity of this model is better than the empirical models developed previously. Finally, it should be noted that the developed model is site-specific, and it can be used for preliminary estimation of ICR in future phases of Tabas coal mine No. 1. The outcome of this model can be helpful in adjustment of time-scheduling of the project.