Support vector regression optimized by black widow optimization algorithm combining with feature selection by MARS for mining blast vibration prediction

Abstract

Ground vibration induced by mine blasting is the most significant adverse effect on nearby residents and surroundings. Accurate prediction of blasting vibration using limited monitor data is a viable option to control ground vibration. This study proposed a novel integration modeling method based on multivariate adaptive regression splines (MARS), support vector regression (SVR) and black widow optimization algorithm (BWOA) for predicting the peak particle velocity (PPV) and frequency. Feature selection was implemented first using the MARS. Subsequently, the variables selected by the MARS were used as the input to build the SVR model. To increase the performance of the SVR model, we introduced the BWOA to tune the hyperparameters of the SVR model. Moreover, two hybrid SVR models also were developed to compare with the hybrid MARS-BWOA-SVR model. The results indicate that the prediction accuracy of the three hybrid models is superior to the standalone SVR model. Among the three hybrid models, the MARS-BWOA-SVR model yields the highest prediction accuracy. The hybrid MARS-BWOA-SVR model not only outperforms other SVR models but also discerns the relative importance of the input variables. There are four main variables with higher relative importance, namely, distance, maximum charge per delay, integrity coefficient and pre-split penetration ratio. The results demonstrate that the hybrid MARS-BWOA-SVR model is a promising tool for blasting vibration prediction.