Gholamnejad, J., Bahaaddini, H., Rastegar, M. (2013). Prediction of the deformation modulus of rock masses using Artificial Neural Networks and Regression methods. Journal of Mining and Environment, 4(1), 35-43. doi: 10.22044/jme.2013.144
Javad Gholamnejad; HamidReza Bahaaddini; Morteza Rastegar. "Prediction of the deformation modulus of rock masses using Artificial Neural Networks and Regression methods". Journal of Mining and Environment, 4, 1, 2013, 35-43. doi: 10.22044/jme.2013.144
Gholamnejad, J., Bahaaddini, H., Rastegar, M. (2013). 'Prediction of the deformation modulus of rock masses using Artificial Neural Networks and Regression methods', Journal of Mining and Environment, 4(1), pp. 35-43. doi: 10.22044/jme.2013.144
Gholamnejad, J., Bahaaddini, H., Rastegar, M. Prediction of the deformation modulus of rock masses using Artificial Neural Networks and Regression methods. Journal of Mining and Environment, 2013; 4(1): 35-43. doi: 10.22044/jme.2013.144
Prediction of the deformation modulus of rock masses using Artificial Neural Networks and Regression methods
1Department of mining and metallurgical engineering
2M.Sc. student, Department of Mining and Metallurgical engineering, Yazd University, Yazd, Iran
Abstract
Static deformation modulus is recognized as one of the most important parameters governing the behavior of rock masses. Predictive models for the mechanical properties of rock masses have been used in rock engineering because direct measurement of the properties is difficult due to time and cost constraints. In this method the deformation modulus is estimated indirectly from classification systems. This paper presents the results of a study into the application of Artificial Neural Networks (ANN) technique and Regression models for estimation of the deformation modulus of rock masses. A database, including 225 actual measured deformation modulus, Uniaxial Compressive Strengths of the rock (UCS), and Rock Mass Rating (RMR) was established. Data collected from different projects. For predicting Em by regression, a nonlinear regression method was chosen. This model showed the coefficient correlation of 0.751 and mean absolute percentage error (MAPE) of 9.911%. Also a three-layer ANN was found to be optimum, with an architecture of two neurons in the input layer, four neurons in the hidden layer and one neuron in the output layer. The correlation coefficient determined for deformation modulus predicted by the ANN was 0.786 and the quantity of MAPE was 6.324%. With respect to the results obtained from two models, the ANN technique was shown to be better than the regression model because of its higher accuracy.
Top
