A vehicle breakdown is not just a hassle—it usually ends up costing both time and money. A vehicle breakdown at a mine site is the same, but on a much larger scale—and can have an impact on productivity and efficiency.
Some breakdowns are well understood and can be prevented through proper maintenance. But some are seemingly random and can’t be planned for—until now. Thanks to an innovative use of machine learning, Teck is using big data to predict the unpredictable and to fix problems before they happen.
Since 2011, we’ve used sensors and data to monitor the health of haul trucks at our steelmaking coal operations, and to manage repairs and preventative maintenance. Now, with the help of artificial intelligence, we’re going a step further.
Through our partnership with Google Cloud and Pythian, we’re unlocking new insights from the millions of data points generated by our mobile fleets. Issues that were previously unpredictable, such as potential electric failures, are now being identified before they happen by machine learning algorithms. We’re also modelling and predicting the remaining lifespan of our trucks, determining wear and tear, identifying abnormal failures, and enhancing alarm and notification systems.
Machine learning for maintenance is helping to minimize unplanned maintenance, reduce overall maintenance costs and extend equipment life. It’s estimated that, at one site alone, there’s potential for over $1 million in annual savings from implementing this program.
Machine learning for maintenance. It’s an idea at work.
