Artificial Intelligence Predicts When Haul Trucks Need Maintenance

Through work with Google Cloud and Canada-based tech solutions company Pythian, Teck, Canada’s largest diversified resource company with operations and projects in Canada, the United States, Chile and Peru, has introduced a machine learning system trained to identify maintenance issues in their haul truck fleet that would be difficult or impossible for a human to identify.

The machine learning system collects and monitors millions of data points to predict maintenance problems before they happen. For example, issues such as potential electric failures, are now being identified before they happen by machine learning algorithms.

According to Teck, machine learning for maintenance is helping to minimize unplanned maintenance, reduce overall maintenance costs and extend equipment life. The company has estimated that at one site alone there is potential for over $1 million in annual savings from implementing this program.

Since 2011, Teck has used sensors and data to monitor the health and manage repairs on Caterpillar and Komatsu haul trucks at their steelmaking coal operations. Operations including its Fording River Operations, Line Creek Operations, Greenhills Operations and Elkview Operations in B.C.’s Elk Valley region are utilizing the machine learning system for haul truck maintenance.

Learn more about Teck’s approach to innovation and technology: