With the advent of inexpensive sensors and digital storage, increasing amounts of data about a mining complex can be collected. This can include camera imaging, mill sensors, blasthole analysis, GPS devices etc. This paper shows how the reduction in uncertainty resulting from this data can be incorporated into stochastic short-term decision-making. This is done through the use of adaptive decision-making policies, which encode recipes for responding to new information as it comes along. Focusing on short-term planning, the paper describes how adaptive policies for allocating the extracted material can be computed in conjunction with optimizing the schedule. The resulting plan can be applied across different short-term time scales, marking an important step towards simultaneously optimizing different time scales. An implementation of the proposed method for a copper-gold deposit shows that it can improve over simple heuristic approaches.
Paru en novembre 2016 , 18 pages