ABSTRACT
Development of an Excavation Damaged Zone around an underground excavation can change the physical, mechanical and hydraulic behaviours of the rock mass near the underground space. This paper presents an approach to build a prediction model for the assessment of EDZ based on an artificial intelligence method called artificial neural networks which are applied to build a prediction model for the assessment of EDZ using data of geological and blasting parameters which are chosen as a result of a literature review. Upon developing the model to evaluate rock damage from underground blasts, practical applications were accomplished for confirmation. Results showed that, because of their high accuracy in establishment of a correlation between EDZ and input parameters’ data, ANNs are appropriate tools to predict excavation damaged zone using data of parameters including perimeter powder factor, rock mass quality, tensile strength, density, wave velocity, vibration propagation coefficients and explosive detonated per delay.
