Enhanced productivity through data mining

Hem stresses predictive maintenance as an example. When implemented, it enables miners to predict and manage operational risk in a cost-effective way. This requires a digital setup with the capability to collect and analyse data. The difficulty is then to interpret these findings into an actionable form – enabling the organisation to create and prioritise maintenance tasks in order to minimise risk and increase uptime.

“An example of one of these productivity potentials lies in the interplay between the quality variation of the ore and the wear state of the equipment. By understanding how these parameters tie in to process performance, energy consumption and wear rates, it is possible to optimise all or some of these variables. Once data is available, it opens up for different types of maintenance schemes and operational strategies. Combining these with selective mining, stockpile management and sorting of ore we will realise significant increases in productivity," says Hem.

Digitalisation improves automation Sensors in equipment detect rates of wear and tear, and data from these sensors translate into information that enables predictive maintenance or repairs. By allowing operators to schedule maintenance, modifications are undertaken while production is low rather than having to shut down unexpectedly in peak periods – helping miners save time and uphold effective management resources and money.

Automation has already made the process more efficient. By utilising the options within digitalisation, it is now possible to enhance productivity and take automation to the next level: “Automation itself has improved many work processes in the mining industry. By collecting and analysing data, we can optimise the automation processes. However, it is when we combine data with a spark of human experience and creativity, that automation can realise its fullest potential. That is the big picture we are working towards,” says Hem.