Energy accounts for 20-40% of OPEX in mineral processing. Leveraging AI-powered optimization technology to get the highest possible yields is the lowest carbon way to accelerate the shift towards electrification and the energy transition.
Around 15% of precious metals mined find their way to the tailings pond. Don’t let the complexity of your float system increase that number.
Imubit AI models learn the nonlinear relationships between process variables like reagent concentration, bubble formation, and rotor speed, then tune the available handles to maximize recovery of every float tank under every process condition.
Grinding circuits are the most energy-intensive step in mineral processing with inefficiencies stemming from variable feed properties and lack of real time particle size measurement in the mill.
Imubit models make the most of your energy input, pushing to the max power draw limit, maximizing throughput and minimizing reagent usage in flotation through consistent and optimal control of particle size distribution.
Missed metal composition targets can result in costly reprocessing or downgrades. In steel production, raw material variability and delayed lab-measured properties add complexity.
Imubit AI models learn the complex, nonlinear composition relationships and put them into closed loop to reduce rework and energy costs and provide more consistent mechanical properties.
“I’ve seen operators challenging the platform. We always think we can be better than the computer. It’s really been fun to challenge it, and not only to get beat by it, because you’re going to, but also just to learn from it.”
Learn how Oxbow’s yield improvement initiative accelerated their sustainability journey.
Discover how industry leaders like Marathon Petroleum democratize AI in their organizations.
Prove the value of AI optimization at your plant—at no cost. Uncover AI’s potential, based on your unit and your site-specific economics, in this free assessment.