Prediction of Blast-Induced Ground Vibration in a Mine Using Relevance Vector Regression Optimized by Metaheuristic Algorithms

Abstract

Prediction of ground vibration induced by blasting operations is a crucial challenge to engineers working in surface mines. This study aims to assess the efficiency of two advanced machine learning models in predicting ground vibrations in a granite quarry located in Malaysia. To this end, two intelligent models were proposed by hybridizing the relevance vector regression (RVR) with the grey wolf optimization (GWO) (which formed the RVR-GWO model) and with the bat-inspired algorithm (BA) (which formed the RVR-BA model). To the best of our knowledge, this is the first attempt to predict ground vibration using the RVR-GWO and RVR-BA models. The afore-mentioned models were developed and tested using 95 datasets. Then, the performance of the developed models was statistically checked through four comparative experiments using, among others, mean square error (MSE) and correlation coefficient (R). The results indicated the superiority of the RVR-GWO model over the RVR-BA model in terms of prediction precision. The RVR-GWO model with R of 0.915 and MSE = 7.920 predicted the ground vibration better than the RVR-BA model with R of 0.867 and MSE = 8.551. Accordingly, it was concluded that applying the GWO algorithm to RVR can result in high accuracy in the prediction of blast-induced ground vibration.