Decrease Flocculant Usage by 16%
Major Iron Ore Mine in Australia
A case study about reducing Thickener’s process variability with machine learning modelling
Unstabilibity in Achieving Target Setpoints
Continuously changing feed material from the upstream plant was leading to instability to achieve desired underflow % of solids, requiring additional cost with flocculant.
Unplanned Thickener stoppage events due to high rake torque lead to high maintenance costs and a decrease in water reuse.
How We Helped
Thickener Scientific-AI Optimization
Introduction of Machine Learning-based models to predict and recommend adjusting flow rates and flocculant dosages.
Implementation of Virtual Sensors for bed pressure, rake torque, and clear water height monitoring.
Simulator tool for “what if” scenario modeling.
16% Reduction in Flocculant and 18% in Rake Torque
Thickener underflow density was stabilized against the upper limit provided by the client with
a decrease in flocculant dosage by 16%.
Reduction of water and energy consumption with a higher return for capital investment.
Decreased rake torque by 18%, reducing operational costs with thickener maintenance and components.
Discover how Thickener Optimization can be applied to your operation
Mine to Market: Value Chain Optimization
The Stockpile & Inventory Optimization Application is one of a suite of real-time decision-making applications that use Scientific AI to optimize each process; from mine to market.
Our Material Handling model connects these applications to drive even greater efficiency.
Our process optimization apps can be deployed on a specific process bottleneck or expanded across the entire value chain.
They are powered by our Scientific AI Decision Intelligence Platform, brains.app.