Predicting ground vibration during rock blasting using relevance vector machine improved with dual kernels and metaheuristic algorithms

Abstract

The ground vibration caused by rock blasting is an extremely hazardous outcome of the blasting operation. Blasting activity has detrimental effects on both the ecology and the human population living in proximity to the area. Evaluating the magnitude of blasting vibrations requires careful evaluation of the peak particle velocity (PPV) as a fundamental and essential parameter for quantifying vibration velocity. Therefore, this study employs models using the relevance vector machine (RVM) approach for predicting the PPV resulting from quarry blasting. This investigation utilized the conventional and optimized RVM models for the first time in ground vibration prediction. This work compares thirty-three RVM models to choose the most efficient performance model. The following conclusions have been mapped from the outcomes of the several analyses. The performance evaluation of each RVM model demonstrates each model achieved a performance of more than 0.85 during the testing phase, there was a strong correlation observed between the actual ground vibrations and the predicted ones. The analysis of performance metrics (RMSE = 21.2999 mm/s, 16.2272 mm/s, R = 0.9175, PI = 1.59, IOA = 0.8239, IOS = 0.2541), score analysis (= 93), REC curve (= 6.85E-03, close to the actual, i.e., 0), curve fitting (= 1.05 close to best fit, i.e., 1), AD test (= 11.607 close to the actual, i.e., 9.790), Wilcoxon test (= 95%), Uncertainty analysis (WCB = 0.0134), and computational cost (= 0.0180) demonstrate that PSO_DRVM model MD29 outperformed better than other RVM models in the testing phase. This study will help mining and civil engineers and blasting experts to select the best kernel function and its hyperparameters in estimating ground vibration during rock blasting project. In the context of the mining and civil industry, the application of this study offers significant potential for enhancing safety protocols and optimizing operational efficiency.

Keywords: Blasting; Genetic algorithm; Mining; PPV; Particle swarm optimization; Relevance vector machine.

Fig. 1

The favourable and unfavourable outcomes of rock blasting (Source:).

Fig. 2

Propagation of ground vibration wave during rock blasting (Source:).

Fig. 3

Illustration of flow chart of the main research methodology.

Fig. 4

Graphic representation depicting the distribution of variables based on frequency histogram plot in blue navy colour (left) and ridgeline plots in orange colour (right).

Fig. 5

Graphic representation of scatter matrix plot of all the variables to elaborate the relationship between the variables.

Fig. 6

Depiction of violin plots of all variables.

Fig. 7

Illustration of spearman correlation plot.

Fig. 8

Illustration of normal probability (PP) plot of all variables.

Fig. 9

Depiction of 2D mean line graph plot of each input variable (y-axis) with the target variable (x-axis) to illustrate the interaction between each variable.

Fig. 10

Depiction of cosine amplitude sensitivity analysis (SA) for input variables.

Fig. 11

Illustration of the relationship between actual and predicted PPV using RVM models (a) MD1, (b) MD10, (c) MD16, (d) MD21, (e) MD26, and (f) MD29.

Fig. 12

Total score of better performing models.

Fig. 13

Depiction of AOC results for (a) training and (b) testing, (c) validation phase.

Fig. 14

Illustration of curve fitting of the six RVM models, MD1, MD10, MD16, MD21, MD26, and MD29.

Fig. 15

Illustration of Taylor plots for (a) training, (b) testing, and (c) validation phase.

Fig. 16

Depiction of AD test results for models MD1, MD10, MD16, MD21, MD26, and MD29.

Fig. 17

Illustration of radar plots of RMSE & MAE (a1, b1, c1), R & IOA (a2, b2, c2), and PI (a3, b3, c3) in the prediction of ground vibration during (a) training, (b) testing, (c) validation.