Madeleine Martinsen
ABB Industrial Automation, Industrial PhD student at MDH, Västerås Sweden
Erik Dahlquist
MDH, Mälardalens University, Västerås Sweden
Anders Lönnermark
RISE, Research Institutes of Sweden, Borås Sweden
Örjan Säker
Epiroc, Rocktec Automation Rock Drills AB, Örebro Sweden
Download article
https://doi.org/10.3384/ecp20176272Published in: Proceedings of The 61st SIMS Conference on Simulation and Modelling SIMS 2020, September 22-24, Virtual Conference, Finland
Linköping Electronic Conference Proceedings 176:38, p. 272-279
Published: 2021-03-03
ISBN: 978-91-7929-731-2
ISSN: 1650-3686 (print), 1650-3740 (online)
A drone (UAV, unmanned aerial vehicle) is no longer a toy, it is gaining bigger and bigger terrain in the industry as an everyday working tool. Equipped with sensors, thermal cameras, components and system software it most likely will be part of the solutions that continues streamlining the mining operations in the future. Data gathering of signals from sensors mounted on drones and other mining equipment such as mining vehicles creates conditions for monitoring, analysis and warning of possible risks and suggests how these can be avoided in due time. The experimental drone study conducted at an open pit mine Aitik, Boliden in Sweden will be presented in this paper. Aitik is today the world’s most efficient copper (Cu) open pit mine. The authors propose decision trees to support and enable the transformation into a completely autonomous mining operation. In combination with deep learning (DL), pattern recognition and artificial intelligence (AI) applications, creates the puzzle pieces to support mining operations to further increase their productivity and safety.
maintenance, inspections, drones, mining operations, decision tree, artificial neuron
