677
mization model will be the amount of charge in each drill hole. Optimization model will be
solved using a metaheuristic algorithm and the result will determine the required changes in
charging of each drill hole in order to maximize energy distribution uniformity.
4 CONCLUSIONS
Despite using relatively accurate technologies, drilling of the blast holes on their designated
coordination is still an issue in open-pit mining. The problem arises from the fact that blasters are not usually aware of the magnitude and direction of this error due to the operational
restrictions in surveying of all drillholes. The paper explains a new automated methodology
in order to measure the deviation of the as-built drillholes from their desired locations and
adjust the charges of individual drillholes to compensate materialized errors.
The offered approach consists of taking a series of high resolution images from the blasting site and using photogrammetry to generate big picture (orthomosaic) and surface elevation model of the site. Then, an image processing/machine learning approach is used to
automatically measure drilling errors. Finally, an optimization model is solved to calculate
how to compensate the drilling inaccuracy by adjustment of the charges in each drillhole in
order to reach the best possible EED.
ACKNOWLEDGEMENTS
Authors acknowledge VPO Ingenieria SpA (Chile), GeoBlast S.A. (Chile), and Barrick
Nevada for their facilitation of data acquisition.
REFERENCES
JKTech (2012) 2DRing, Underground Blast Design, User Manual.
Kim, P. i.-y. n. (2017) MATLAB deep learning: with machine learning, neural networks and artificial intelligence [eBook]. Place of publication not identified. New York, NY: Apress, Distributed to the book
trade worldwide by Springer Science+Business Media New York.
Michaux, S. & Djordjevic, N. (2005) Influence of explosive energy on the strength of the rock fragments
and SAG mill throughput. Minerals Engineering, 18(4), 439–448.
Sanchidrián, J.A., Segarra, P. & López, L.M. (2007) Energy components in rock blasting. International
Journal of Rock Mechanics and Mining Sciences, 44(1), 130–147.
Solomon, C. & Breckon, T. (2011) Fundamentals of Digital Image Processing: A Practical Approach with
Examples in Matlab. New York, UNITED KINGDOM: John Wiley & Sons, Incorporated.
Valencia López, J.P., Contreras Moreno, E.H. p. g. & Universidad de Santiago de Chile. Departamento
de Ingeniería en, M. (2015). Evaluación de alternativas de perforación y tronadura para el mejoramiento de la fragmentación en Mina Los Filos, Estado de Guerrero, México. Santiago.
mization model will be the amount of charge in each drill hole. Optimization model will be
solved using a metaheuristic algorithm and the result will determine the required changes in
charging of each drill hole in order to maximize energy distribution uniformity.
4 CONCLUSIONS
Despite using relatively accurate technologies, drilling of the blast holes on their designated
coordination is still an issue in open-pit mining. The problem arises from the fact that blasters are not usually aware of the magnitude and direction of this error due to the operational
restrictions in surveying of all drillholes. The paper explains a new automated methodology
in order to measure the deviation of the as-built drillholes from their desired locations and
adjust the charges of individual drillholes to compensate materialized errors.
The offered approach consists of taking a series of high resolution images from the blasting site and using photogrammetry to generate big picture (orthomosaic) and surface elevation model of the site. Then, an image processing/machine learning approach is used to
automatically measure drilling errors. Finally, an optimization model is solved to calculate
how to compensate the drilling inaccuracy by adjustment of the charges in each drillhole in
order to reach the best possible EED.
ACKNOWLEDGEMENTS
Authors acknowledge VPO Ingenieria SpA (Chile), GeoBlast S.A. (Chile), and Barrick
Nevada for their facilitation of data acquisition.
REFERENCES
JKTech (2012) 2DRing, Underground Blast Design, User Manual.
Kim, P. i.-y. n. (2017) MATLAB deep learning: with machine learning, neural networks and artificial intelligence [eBook]. Place of publication not identified. New York, NY: Apress, Distributed to the book
trade worldwide by Springer Science+Business Media New York.
Michaux, S. & Djordjevic, N. (2005) Influence of explosive energy on the strength of the rock fragments
and SAG mill throughput. Minerals Engineering, 18(4), 439–448.
Sanchidrián, J.A., Segarra, P. & López, L.M. (2007) Energy components in rock blasting. International
Journal of Rock Mechanics and Mining Sciences, 44(1), 130–147.
Solomon, C. & Breckon, T. (2011) Fundamentals of Digital Image Processing: A Practical Approach with
Examples in Matlab. New York, UNITED KINGDOM: John Wiley & Sons, Incorporated.
Valencia López, J.P., Contreras Moreno, E.H. p. g. & Universidad de Santiago de Chile. Departamento
de Ingeniería en, M. (2015). Evaluación de alternativas de perforación y tronadura para el mejoramiento de la fragmentación en Mina Los Filos, Estado de Guerrero, México. Santiago.