Prediction and Optimization of Blasting-Induced Ground Vibration in Open-Pit Mines Using Intelligent Algorithms

Prediction and parameter optimization are effective methods for mine personnel to control blast-induced ground vibration. However, the challenge of prediction lies in multi-factor multi-effect nature open-pit blasting. This study proposes a hybrid intelligent model predict vibrations using least-squares support vector machine (LSSVM) optimized by particle swarm algorithm (PSO). Meanwhile, multi-objective (MOPSO) was used optimize blast design parameters considering vibration particular areas bulk rate fragmentation. To compare performance PSO-LSSVM, genetic-algorithm-optimized BP neural network (GA-BP), unoptimized LSSVM, were used, applying same database. In addition, root-mean-squared error (RMSE), mean absolute (MAE), correlation coefficient (r) regarded as evaluation indicators. Furthermore, results blasting obtained quoting established proxy MOPSO verified field tests. The indicated that PSO-LSSVM provided highest efficiency predicting with an RMSE 1.954, MAE 1.717, r 0.965. can be controlled two-objective obtain best parameters. Consequently, this provide more specific recommendations hazard control.