Application of cuckoo search algorithm to estimate peak particle velocity in mine blasting

Ground vibration is one of the most undesirable effects of blasting operation in surface mines. Therefore, it seems that the prediction of ground vibrations with a high degree of accuracy is necessary to reduce environmental effects. This article proposes a novel swarm intelligence algorithm based on cuckoo search (NSICS) to create a precise equation for predicting the ground vibration produced by blasting operations in Miduk copper mine, Iran. To evaluate the proposed NSICS model, several empirical equations were also utilized. In this regard, 85 blasting events were considered, and the values of two effective parameters on the ground vibration, namely, maximum charge used per delay and distance between blast face and monitoring station, were measured. In addition, the values of peck particle velocity (PPV), as a vibration descriptor, were recorded in each blasting. Two performance indices, i.e., root mean square error and coefficient of multiple correlation (R ²), were used to determine the performance capacity of the proposed models. Comparing the values predicted by the models demonstrated that the proposed equation by NSICS is more reliable than empirical equations in predicting the PPV.