An integrated approach of ANFIS-grasshopper optimization algorithm to approximate flyrock distance in mine blasting

In open-pit mines, the blast-induced flyrock is one of the most fundamental problems, therefore, a precision prediction of flyrock can be useful to design a proper blast pattern and reduce the undesirable effects of flyrock. The aim of this study is to develop a new integrated intelligent model to approximate flyrock based on an adaptive neuro-fuzzy inference system (ANFIS) in combination with a grasshopper optimization algorithm (GOA). In addition, a cultural algorithm (CA) is combined with ANFIS to predict flyrock. In the proposed models, the hyperparameters of ANFIS were tuned using CA and GOA. To achieve the objective of this study, a comprehensive database collected from three quarry sites, located in Malaysia, was used. The performance of both ANFIS-CA and ANFIS-GOA models was evaluated by calculation of the statistical functions such as the correlation of determination (R-2). The comparison between the proposed models indicated the higher accuracy of using ANFIS-GOA (R-2 = 0.974) as an efficient model to predict flyrock compared to the ANFIS-CA (R-2 = 0.953).

Automated summary

The study developed a new integrated intelligent model for predicting flyrock in open-pit mines, using ANFIS in combination with GOA and CA to achieve high accuracy in flyrock approximation.