A chaos recurrent ANFIS optimized by PSO to predict ground vibration generated in rock blasting

Abstract

The use of explosives is a common and economical method to fragment and/or displace hard rocks in tunnels and surface and underground mines. Ground vibration, as a side environmental effect induced by blast events, has detrimental impacts on nearby structures like dams and buildings. Therefore, an accurate and reliable estimation of ground vibration is imperative. The goal of this paper is to present a new hybrid model by combining chaos recurrent adaptive neuro-fuzzy inference system (CRANFIS) and particle swarm optimization (PSO) to predict ground vibration. To the best of our knowledge, this is the first research that predicts the ground vibration through a model integrating CRANFIS and PSO. To evaluate the efficiency of the proposed model, the results of CRANFIS-PSO were compared with those of the CRANFIS, RANFIS, ANFIS, artificial neural network (ANN), and several empirical methods. In other words, first, the empirical methods were developed; then, due to their unacceptable performance, the artificial intelligence methods were developed. The results clearly indicated the superiority of CRANFIS-PSO over the above-mentioned methods in terms of predicting ground vibration. The values of coefficient of determination (R2) obtained from CRANFIS-PSO, CRANFIS, RANFIS, ANFIS, and ANN models were 0.997, 0.967, 0.958, 0.822, and 0.775, respectively. Accordingly, the CRANFIS-PSO model could be employed as a reliable and accurate data intelligent model to solve highly-nonlinear problems such as the prediction of blast-induced flyrock and air-overpressure.