granite downstream production dependent size and profitability assessment: an application of mathematical-based artificial intelligence model and wipfrag software

The purpose of this research work is to create empirical models for assessing the profitability of granite aggregate production in akure, ondo state, aggregate quarries. in addition, an artificial neural network (ann) model for granite profitability was developed. a structured survey questionnaire was used to collect data for the study. the data extracted from the case study mine for this study includes granite marketing operations, royalty, production costs, and mine production information. in this study, the efficacy of granite fragmentation was assessed using the wipfrag software. the relationship between particle size distribution, blast design, blast efficiency, and uniformity index were analyzed using the wipfrag result. the optimum blast design was also identified and recommended for mine production. the result revealed that large burden distances result in bigger x50, x80, and xmax fragmentation sizes. a burden distance of 2 m and a 2 m spacing were identified as the optimum burden and spacing. the finding revealed that blast mean size and 80% passing mesh size have a positive correlation. the result from this study indicated that the uniformity index has a positive correlation with blast efficiency and a negative correlation with maximum blast fragmentation size. the prediction accuracy of the developed models was evaluated using the coefficient of determination (r2), root mean square error (rmse), and mean square error (mse). the error analysis revealed that the ann model is suitable for predicting quarry-generated profit.