The quality of rock fragmentation intensively affects downstream operations and operational costs. Besides, Environmental side effects are inevitable due to mine blasting despite improvements in blasting consequences such as fly-rock and back-break. This study concentrates on optimizing mine blasting patterns for environmentally friendly mineral production and minimizing operational costs by achieving environmental-oriented and economic objectives-based on a new framework using artificial intelligence techniques. A gene expression programming (GEP) based on Monte Carlo simulations (MCs) denoted that rock size distribution can be modeled and predicted without any uncertainty. Four main objectives involving operational costs, back-break, fly-rock, and toe volume were highlighted for minimizing in the optimization framework. The multi-objective model was implemented by applying it to a running mine and solved using the grey wolf optimization algorithm. As optimizing, 17 optimal blasting plans were achieved to implement in the different rock types. The multi-objective model was able to reduce mine to crusher cost as well as undesirable blasting consequences considerable favourite of mining managers.
