An ANN-Fuzzy Cognitive Map-Based Z-Number Theory to Predict Flyrock Induced by Blasting in Open-Pit Mines

Abstract Blasting is widely employed as an accepted mechanism for rock breakage in mining and civil activities. As environmental side effect of blasting, flyrock should be investigated precisely open-pit operations. This paper proposes a novel integration artificial neural network fuzzy cognitive map (FCM) with Z -number reliability information to predict distance mine blasting. The developed model called the causality-weighted networks, based on (ACWNNsR). -numbers used eliminate uncertainty expert opinions required initial matrix FCM, which one main advantages this method. FCM calculates weights input neurons using nonlinear Hebbian differential evolution algorithms. Burden, stemming, spacing, powder factor, charge per delay are parameters, output parameter. Four hundred sixteen recorded basting rounds from real large-scale lead–zinc design architecture models. performance proposed ACWNNsR compared Bayesian regularized multilayer perceptron proven result more accurate prediction estimating blast-induced distance. In addition, results sensitivity analysis conducted effective parameters determined spacing most significant parameter controlling Based type datasets study, presented recommended surface mines where buildings close blasting site.