A high level of automation is necessary for mines as they go deeper. We have developed a method for automatic mine scheduling1 that contributes towards the vision of a fully automated mine operation. In an autonomous mine, machines are used more efficiently and workers can be moved from potentially dangerous underground environments.
Many of us have grown accustomed to a way of living that depends heavily on various minerals. Minerals are found in everything from smartphones to fertilizers and are key ingredients in many things that we use in our increasingly digital life. In nature, these minerals are found in ore often located in deposits several kilometers under the surface. To collect these precious minerals, miners are forced to go deeper and deeper to satisfy the market demand. The risks and the costs of underground mine operation increases with depth of production2. To address this, autonomous mining is a trending concept among miners, conveying the vision of a mine operation with a high level of automation. With a highly automated mine operation, humans can be moved above ground, mitigating the ever-present safety risks of being underground. In addition, increased automation leads to a more cost-efficient extraction process. The driving forces behind this initiative is thus clear; however, there are some parts missing on the road to autonomous mining.
While many modern mines are now using automated equipment and semi-autonomous machines, scheduling when a machine should do what and where is still done by humans. Mine scheduling is still a manual activity based on gut-feeling, unfortunately both error-prone and time-consuming for the scheduler3. In our research, we present a mine scheduling algorithm that is based on a method that draws inspiration from artificial intelligence, operations research, and computer science. The method is called Constraint Programming4 and it has been shown to be efficient for similar problems in other industries. For instance, it is used to automate the gate allocation at the Hong Kong Airport, to create loading plans for one of the world’s largest container shipment hubs in Singapore, and it is used to create the daily timetable for the public railway system in the Netherlands.
Using Constraint Programming, we can automate the schedule construction, that is, answering to the when, what and where ofhundreds of activities in a couple of seconds, without introducing resource conflicts. A task that manually takes several hours. Moreover, the constructed schedules obey all safety and process constraints enforced by the mine operations. In our recent work, we have also introduced an optimization technique that can further improve the automatically created schedules by up to 12%. In an industry where throughput is everything, and every percentage count, this presents a major opportunity to sustain mine operations as costs increase.
With a well-functioning scheduling algorithm, miners are one step closer to operationalize a highly automated mine operation. With a high level of automation, we can move workers away from dull, dirty, and dangerous environments.By incrementally pursuing the autonomous mine, we keep contributing towards a future where we can keep the digital lifestyle that many of us have grown accustomed to.
- M. Åstrand, M. Johansson, and A. Zanarini. “Fleet Scheduling in Underground Mines Using Constraint Programming.” International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research. Springer, Cham, 2018.
- J. Parreira, Z. Mullard, J. Meech, and M. G. Vásquez, “How automation and key performance indicators contribute to sustainable development in the mining industry,” presented at the Second International Conference on Multinational Enterprises and Sustainable Development, Nancy-Metz, France, 2009.
- Z. Song, M. Rinne, and A. van Wageningen, “A review of real-time optimization in underground mining production.” Journal of the Southern African Institute of Mining and Metallurgy, vol. 113, no.12, pp 889-897, 2013.
- P. Baptiste, C. Le Pape, and W. Nuijten, Constraint-based scheduling: applying constraint programming to scheduling problems, New York, NY: Springer Science & Business Media, 2012.