Unearthed Sydney 201620 Aug - 22 Aug
From Idea to Prototype on Resource Challenges in just a Weekend
This competition has finished.
Machine learning to predict and prevent surge events in the SAG mill
Our algorithm was developed using machine learning principles with engineering understanding of the circuit to determine variables of interest which would have influence over the internal behavior of the SAG mill. We then offset the time datum of these key variables such that the information correlated over the same point. This allows us to identify leading indicators for surge events in the SAG mill. With these circuit properties identified changes can be made in real time to prevent surge event occurring and prevent downtime.