Ore Concentration Recovery and Pre-Concentration Optimization

AI-supported optimization of mineral concentration workflows, including flotation retrofit performance improvement and sensor-based pre-concentration of low-grade stockpiles to increase recovery, reduce downstream load, and lower energy, water, and operating costs.

The Problem

“Ore Concentration Recovery and Pre-Concentration Optimization”

Organizations face these key challenges:

1

Highly variable ore characteristics cause unstable flotation and inconsistent recovery

2

Manual froth control and setpoint tuning are slow and operator-dependent

3

Retrofit benefits are difficult to sustain without continuous optimization

4

Low-grade stockpiles are uneconomic when all material is processed downstream

Impact When Solved

Increase copper recovery in rougher flotation circuits while maintaining plant throughputStabilize froth behavior and reduce operator-driven variabilityReduce downstream plant load by rejecting barren material before full processingLower energy, water, reagent, and maintenance costs per tonne processed

The Shift

Before AI~85% Manual

Human Does

  • •Review plant trends, froth conditions, and assay results to adjust flotation settings
  • •Tune air, reagent, pulp level, and throughput setpoints based on operator judgment
  • •Apply static XRT sorting thresholds and offline calibration rules to separate ore from waste
  • •Decide how much low-grade stockpile material to process downstream based on periodic performance results

Automation

    With AI~75% Automated

    Human Does

    • •Approve recovery versus throughput trade-offs and operating targets for flotation and pre-concentration
    • •Review AI recommendations or control actions during abnormal ore variability, equipment issues, or safety constraints
    • •Authorize threshold changes, campaign strategy shifts, and processing of marginal stockpile segments

    AI Handles

    • •Continuously monitor historian, analyzer, froth image, and sorter data to detect instability and recovery loss risks
    • •Predict recovery, concentrate grade, reject quality, and downstream load under current and alternative operating conditions
    • •Recommend or automatically adjust flotation setpoints and XRT cut points to optimize recovery, mass rejection, and cost
    • •Track stockpile segment performance, sorter yield, and froth behavior to triage anomalies and trigger maintenance or operator actions

    Operating Intelligence

    How it works

    AI runs the operating engine in real time.

    Humans govern policy and overrides.

    Measured outcomes feed the optimization loop.

    Confidence92%
    ArchetypeOptimize & Orchestrate
    Shape6-step circular
    Human gates1
    Autonomy
    67%AI controls 4 of 6 steps

    Who is in control at each step

    Each column marks the operating owner for that step. AI-led actions sit above the divider, human decisions and feedback loops sit below it.

    Loop shapecircular

    Step 1

    Sense

    Step 2

    Optimize

    Step 3

    Coordinate

    Step 4

    Govern

    Step 5

    Execute

    Step 6

    Measure

    AI lead

    Autonomous execution

    1AI
    2AI
    3AI
    5AI
    gate

    Human lead

    Approval, override, feedback

    4Human
    6↺ Loop
    AI-led step
    Human-controlled step
    Feedback loop
    TL;DR

    AI senses, optimizes, and coordinates in real time. Humans set policy and override when needed. Measurements close the loop.

    The Loop

    6 steps

    1 operating angles mapped

    Operational Depth

    Real-World Use Cases

    Performance-based flotation cell retrofit for copper recovery improvement at Antapaccay

    Metso upgraded part of Antapaccay’s copper flotation line so the bubbles carrying copper minerals were more stable and easier to collect, helping the mine recover more copper with less waste.

    Closed-loop process optimization focused on stabilizing froth behavior and improving separation performance.mature industrial process optimization deployment using retrofit hardware and performance-based operating guarantees, not a speculative pilot.
    10.0

    XRT pre-concentration of low-grade tungsten stockpiles at Mt Carbine

    The mine uses X-ray machines to look inside crushed rock and keep the pieces with tungsten while throwing away most waste rock before expensive wet processing.

    Sensor-based classification and real-time physical decisioning for ore/waste separation.deployed production workflow with site-specific test validation and reported operating metrics.
    10.0

    Free access to this report