The technology, developed by Newcrest in association with Microsoft and its partner Insight Enterprises, has been rolled out at Newcrest’s Cadia Valley gold mine in NSW.

Microsoft says the challenge facing Newcrest at Cadia was managing the levels in the underground crushed ore bins. If the bins overfill, they have to be manually emptied introducing lengthy and expensive production delays - and conversely, if the level drops too low it is unable to effectively feed the collection conveyor.

Newcrest had spotters, physically watching the bins to ensure they didn’t overfill as the hard sensor used previously was unreliable.

According to Gary Slater, Digital and Data Science Architect at Newcrest, “The hard sensors in our crushed ore bins were failing at a rate of two or three times every month per crusher, and it often took hours to get the process up and running again”.

“Over a period of six months, our Cadia Valley mine experienced 4,780 minutes of downtime due to sensor failure in one of the crushed ore bins, which equates to a significant dollar value in lost opportunity.”

Using Microsoft Azure, Newcrest and its partners created an Intelligent Edge solution that optimises the underground crushing circuit. The model pulls data from other upstream sensors: tonnes tipped, apron feeder speeds, weightometers, and so on.

The model then analyses the data to predict the level of crushed ore in the bin and uses that information to control the flow of ore to the crusher, keeping the ore moving at an optimal level of productivity and preventing the bins from depleting or over filling.

“Having continuous, accurate information about the amount of ore in the crushed ore bin is a critical component of our operation,” said Slater.

“If the level of ore in the bin drops too low, then too little ore is being fed onto the conveyor. If the bin gets too full, then we need to stop the crusher and empty the bin in what amounts to a manual process. By always knowing how much ore is in the bin, we can regulate the level to keep production high and avoid shutdowns.”

Microsoft says the Intelligent Edge approach has allowed Newcrest to automate bin monitoring and the solution is achieving 85% accuracy, and as a result, Newcrest workers face fewer risks, and the AI-fueled predictive maintenance allows early intervention to keep production on track.

According to Gavin Wood, CIO at Newcrest Mining, the solution is delivering.

“Higher productivity, less downtime, more throughput. With Azure’s AI machine learning and IoT capabilities we see a future where our mines are automated – making our mines safer and more productive,” Wood said.