Development of a new empirical model and adaptive neuro-fuzzy inference systems in predicting unconfined compressive strength of weathered granite grade III

Abstract

The present paper has developed a new multivariate linear regression and adaptive neuro-fuzzy inference processing to predict UCS for weathered granite grade III based on simple input data from point load index, Schmidt rebound hardness, and P wave velocity. Data from 85 rock core samples of this granite type have been selected. By using multivariate regression analysis, three models with two independent variables and one model with three independent variables have been developed. Furthermore, another model has been obtained by using a neuro-fuzzy logic analysis. The root means square error, RMSE, coefficient of determination, R 2 , and the mean absolute percentage error, MAPE, were used as the evaluation criteria of the accuracy of the models. The results have indicated that the regression-based and neuro-fuzzy models are effective, but the accuracy of the neurofuzzy model is in good agreement with the realistic data from the direct test.

Unified Plasticity Potential of Soils

“…Santos et al [28] reduced the variable size and found out the interrelations for rock mass classification. Moosavi and Mohammadi [29] utilized factor analysis to determine the interrelations of variables to develop an equation of unconfined compressive strength for rocks. Mahdizadeh et al [30] reduced the number of rock properties to derive the geomechanical zonation of a mine.…”