Journal of the Southern African Institute of Mining and Metallurgy
On-line version ISSN 2411-9717
Print version ISSN 0038-223X
DINDARLOO, S.R.. Peak particle velocity prediction using support vector machines: A surface blasting case study. J. S. Afr. Inst. Min. Metall. [online]. 2015, vol.115, n.7, pp.637-643. ISSN 2411-9717. http://dx.doi.org/10.17159/2411-9717/2015/V115N7A10.
Although blasting is one of the most widely used methods for rock fragmentation, it has a major disadvantage in that it causes adjacent ground vibrations. Excessive ground vibrations can cause a wide range of problems, from nearby residents complaining to ecological damage. Prediction of blast-induced ground vibration is essential for evaluating and controlling the many adverse consequences of surface blasting. Since there are several effective variables with highly nonlinear interactions, no comprehensive model of blast-induced vibrations is available. In this study, the support vector machine (SMV) algorithm was employed for prediction of the peak particle velocity (PPV) induced by blasting at a surface mine. Twelve input variables in three categories of rock mass, blast pattern, and explosives were used for prediction of the PPV at different distances from the blast face. The results of 100 experiments were used for model-building, and 20 for testing. A high coefficient of determination with low mean absolute percentage error (MAPE) was achieved, which demonstrates the suitability of the algorithm in this case. The very high accuracy of prediction and fast computation are the two major advantages of the method. Although the case study was for a large surface mining operation, the methodology is applicable to all other surface blasting projects that involve a similar procedure.
Keywords : blast-induced ground vibration; peak particle velocity; support vector machine; surface mining.