Predicting different components of blast-induced ground vibration using earthworm optimisation-based adaptive neuro-fuzzy inference system

This study focuses on addressing the complexity inherent in various amplitude components of blast-induced ground vibration (BIGV), encompassing vertical, radial, transversal, and the vectoral sum of PPVs of particle velocity. It takes into account their nonlinearity across diverse quarry environments, and aims to present an enhanced nonlinear intelligent system for accurate prediction of these components. Multiple artificial intelligence models were explored and developed for this purpose, including a support vector machine (SVM), an adaptive neural network based on the fuzzy inference system (ANFIS), and a novel hybrid model that combines earthworm optimisation (EO) and ANFIS (EO-ANFIS). The study also leverages the empirical model offered by the United States Bureau of Mines. The outcomes highlighted that the predictions of the three individual components prove to be more accurate compared to the vectoral sum of PPVs of particle velocity. However, the latter remains a valuable metric for evaluating the magnitude of BIGV in open-pit mines. Notably, the hybrid EO-ANFIS model emerges as the most accurate, achieving an impressive ~ 75% accuracy across 10 quarries characterised by distinct geological conditions.