Development of a novel soft-computing framework for the simulation aims: a case study

The simulation of blast-induced air-overpressure (AOp) has been a major area of interest in the recent years, and many models have been employed in this field. The scope of this paper is to propose a novel soft-computing framework for predicting the AOp through the implementation of hybrid evolutionary model based on artificial neural network (ANN) with teaching–learning-based optimization (TLBO). The parameters considered during the formulation of the prediction model were maximum charge per delay, rock mass rating, and distance from the blasting face as the inputs and AOp as the output. Totally, 85 blasting events in Shur river dam region have been monitored and the mentioned parameters have been measured. Then, the performances and prediction efficiency of the models have been compared on the basis of performance indices, namely the R square (R²), root-mean-square error (RMSE). The obtained results show that the ANN–TLBO with R² of 0.932 and RMSE of 2.56 yields the better performance for the prediction of AOp as compared to ANN. As a conclusion, it can be found that the proposed ANN–TLBO model has an excellent potential for the prediction aims.