Roohollah Shirani Faradonbeh - MSC.department of mining faculty of engineering tabriat modares university tehran 14115-143,iran
Zahra Sadat chavoshi vani - MSC, Department of Mining engineering, University of Kashan, Iran
danial jahed armaghani - PHD, Department of Geotechnics and Transportation, Faculty of Civil Engineering, Universiti Teknologi Malaysia, 81310,UTM, Skudai, Johor, Malaysia

Back-break is one of the most environmental side effects induced by blasting operations and causing rock mine wall instability, increasing blasting cost as well as decreasing the performance of blasting. Therefore, the assessment and prediction of back-break have much merit. In this study, feasibility of particle swarm optimization based artificial neural network model in predicting of blast-induced back-break is examined. For this aim, 97 blasting data were recorded from Delkan iron mine of Iran. Root mean square error (RMSE) and coefficient of determination (R2) were used to control the capacity performance of the predictive model. The results were compared with the developed ANN model in another study with the same dataset. RMSE and R2 values of 0.8551 and 0.0798, respectively, for testing datasets of PSO-ANN model reveal the superiority of this model in predicting BB, while these values were obtained as 0.832 and 0.2214, respectively, for ANN model

Blasting, Back-break, Particle swarm optimization, ANN