MillMax¶
Geometallurgical Modelling for Optimized Mill Performance.
MillMax optimizes plant performance by translating changing feed conditions into clear operating targets, so control rooms stay stable while economics improve.
What it does¶
- Anticipates how changing feed will impact throughput, recovery, and costs.
- Keeps the circuit closer to its best operating window without destabilizing control.
- Improves economic performance while existing APC and MPC maintain stability.
What's broken today¶
Plants react to feed changes after performance drifts, not before.
Many critical variables (true grind state, effective hardness, mineral response) are difficult or impossible to measure directly.
Optimization decisions rely heavily on operator intuition and experience, making results inconsistent across shifts.
How MillMax works¶
Inputs. Required data sources:
- Plant historian data (throughput, power, recovery, reagent usage, key control tags)
- Feed characterization from upstream (DynaMax or OreMax outputs, or equivalent)
- Circuit configuration and operating limits (constraints, setpoint ranges)
Optional data sources (nice to have):
- Laboratory results (assays, grind size, mineralogy, recovery tests)
- Equipment availability and maintenance signals
- Cost sensitivities (energy, reagents, penalties)
Outputs. What users receive:
- Feed-aware operating targets (throughput, grind, reagent strategy, recovery trade-offs)
- Soft sensor estimates for variables that are difficult to measure directly
- Clear recommendations explaining what to change, why, and what to expect
MillMax updates continuously or at a configurable cadence, as feed conditions and plant response change.
Deployment workflow¶
- Ingest live plant data and feed characteristics from upstream systems.
- Estimate unmeasured process states using soft sensors and validated models.
- Predict plant response to changing feed and operating conditions.
- Evaluate economic trade-offs (throughput vs recovery vs reagent and energy cost).
- Recommend optimal operating targets within safe and defined constraints.
- Present explainable guidance to operators or send setpoints to the DCS or SCADA.
- Learn from outcomes as the plant responds, refining recommendations over time.
Top KPIs impacted¶
| KPI | Outcome |
|---|---|
| Recovery improvement | Typically 0.5 to 5 percent depending on circuit and variability |
| Throughput stability | Reduced oscillations and fewer corrective interventions |
| Reagent efficiency | Up to 30 percent savings demonstrated in pilots |
| Energy efficiency | Improved kWh/t through better operating-point selection |
Case story¶
A gold operation experienced frequent recovery swings due to feed variability. MillMax used feed-aware soft sensors and economic optimization to recommend adjusted operating targets, resulting in a 1.6 percent recovery uplift while maintaining stable control (pilot outcome).
Primary users¶
Metallurgists, Control Room Operators, Processing Manager, Plant Manager, Technical Services Manager.