Australian miner BHP Group has said that an artificial intelligence-based solution helped unlock almost 1 million mt of additional annual iron ore output at its Western Australia operations, according to comments made by the company’s Digital Officer Mikko Tepponen at the Global Resources Innovation Expo in Perth.
Tepponen stated that BHP had lost about 1,000 hours of crusher downtime over three years due to oversized rocks and foreign objects entering its processing system, along with additional disruptions at its West Australian ports.
According to Tepponen, BHP responded with a computer vision solution using cameras and machine learning models to detect anomalies in real time. The system, integrated into the company’s process control system, helps teams remove oversized rocks or foreign objects before they create safety risks, damage equipment or cause unplanned stoppages.
The BHP official said the solution is delivering a little under 1 million mt of yearly uplift potential, equivalent to almost $50 million in value, while reducing crusher downtime by 20 percent and related disruptions by up to 60 percent. Tepponen said that, since the technology was implemented in 2025, BHP has had no issues caused by oversized or foreign objects.
Tepponen added that the solution’s effectiveness was based not only on the technology itself, but also on how it was deployed. He said it was co-designed with frontline staff, integrated into existing systems and designed to scale from the outset.
He noted that the same shift from trials to system-level capability is taking place in AI, as seen previously in autonomous haulage across the mining industry. However, he said a gap remains between what is being built and what is actually scaling, adding that this gap will close only when AI solutions are designed for scale and linked to practical operational challenges.