APPLICATION OF ARTIFICIAL NEURAL NETWORK FOR BLAST PERFORMANCE EVALUATION

Ratnesh Trivedi, T.N.Singh, Keshav Mudgal, Neel Gupta

Abstract: Despite of technological advancement in the field of rock breakage, blasting is still an economical means of rock excavation for mining or civil engineering projects. Blasting has some environmental as well as societal side effects such as ground vibrations, air blasts, noises, back breaks, fly rocks, dusts and, of course, annoyance of inhabitants living surrounding the mining areas. Recent developments in the field of blasting techniques can minimize such ill effects by optimizing rock friendly explosive and blast design parameters. The purpose of this paper is to present the techniques, advances, problems and likely direction of future developments in exploring the applications of Artificial Neural Networks (ANN) in rock fragmentation by blasting and its significance in minimizing side effects to environment in particular and society at large. Many researchers have found the back-propagation algorithm in ANN is especially capable of solving predictive problems in rock blasting. ANN has been successfully applied in predicting, controlling, assessing impact of blast design parameters, ground vibrations, air blasts, back breaks etc. in mines. ANN needs to be applied in certain grey areas like predicting and controlling fly rock hazards in opencast mines, blast induced dust, blasting in jointed rockmass etc.

Keywords: Artificial Neural Networks; Blasting; Mining; Rock Fragmentation; Ground Vibrations; Airblasts; Flyrocks

DOI: https://doi.org/10.15623/ijret.2014.0305104