In the second half of last year, the mining company approached Newtrax to discuss the data it had gathered over six and a half years, what it could do with it and how it could add value for Agnico.

Terry Reid, corporate business process owner - maintenance at Agnico Eagle, said they were able to collect over 10 billion data points using Newtrax sensors.

"This provided Newtrax with data in order to achieve quick wins," he added.

The data was used to apply machine-learning algorithms to predict mobile equipment maintenance issues before they happen.

"Through the Newtrax system we are able to predict issues at least two weeks in advance, even before vehicle alarms, allowing us to intervene before incurring serious problems which can break our engines," said Daniel Pinard, team lead, special projects with Agnico Eagle.

"Through the use of machine-learning algorithms with Newtrax, we were recently able to analyse an engine that had a potential problem and we saved it from failing. This helped the Goldex mine avoid serious damage on that engine which saved them C$85,000 [US$64,000]."

"Newtrax AI is unique in three ways," explained Michel Dubois, VP QA & artificial intelligence at Newtrax.

"First, Newtrax has years of unique data that is extremely well-suited for machine learning, which creates a source of training data for machine learning that is unique in the world, and this data grows every time a mining company decides to join in.

"Second, we have a unique AI team who knows how to generate actionable results using existing AI algorithms.

"And third, we have a unique approach where our AI specialists go underground and focus on quick wins, and they leverage those existing algorithms to solve high-value problems."

According to Newtrax, this is the first applied case study for machine learning in the underground hard-rock mining industry with a defined ROI.

Newtrax works with artificial intelligence and machine learning researchers such as IVADO to apply existing algorithms to the data collected at mine sites.