Mining Demand Forecasting and Flotation Decision Support

AI-powered decision support that combines OT/IT data sharing, near-real-time analytics, and flotation setpoint optimization to improve mining demand forecasting, market responsiveness, and metal recovery under changing operating conditions.

The Problem

“Mining demand forecasting and flotation decision support using OT/IT data fusion and AI optimization”

Organizations face these key challenges:

1

OT historian, lab, maintenance, ERP, and commercial data are fragmented across systems

2

Plant decisions are based on delayed reports rather than current operating conditions

3

Flotation performance changes with ore variability, reagent response, and equipment condition

4

Manual setpoint tuning is inconsistent across shifts and operators

Impact When Solved

Improve near-term production and demand forecast accuracy using fused OT/IT dataIncrease Cu/Au recovery by recommending flotation setpoints under changing ore conditionsReduce metal loss to tails through earlier detection of suboptimal operating regimesShorten decision latency from daily or shift-based review to near-real-time recommendations

The Shift

Before AI~85% Manual

Human Does

  • •Collect historian, lab, ERP, and sales data from separate reports and spreadsheets
  • •Review flotation performance, ore changes, and tails results during shift or daily meetings
  • •Manually tune rougher pull rate and related flotation settings based on operator and metallurgist judgment
  • •Create short-horizon production and demand forecasts using periodic planning inputs

Automation

    With AI~75% Automated

    Human Does

    • •Approve or reject recommended flotation setpoint changes within operating limits
    • •Choose production and demand response actions based on forecast scenarios and plant constraints
    • •Handle exceptions when recommendations conflict with safety, maintenance, or shift priorities

    AI Handles

    • •Fuse OT, lab, ERP, sales, and market signals into a near-real-time operating view
    • •Monitor flotation, throughput, and forecast indicators for abnormal patterns and emerging losses
    • •Predict short-horizon production, concentrate outcomes, and demand scenarios under current conditions
    • •Recommend flotation setpoint adjustments to balance recovery, grade, and tails loss

    Operating Intelligence

    How it works

    AI runs the first three steps autonomously.

    Humans own every decision.

    The system gets smarter each cycle.

    Confidence95%
    ArchetypeRecommend & Decide
    Shape6-step converge
    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 shapeconverge

    Step 1

    Assemble Context

    Step 2

    Analyze

    Step 3

    Recommend

    Step 4

    Human Decision

    Step 5

    Execute

    Step 6

    Feedback

    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 handles assembly, analysis, and execution. The human gate sits at the decision point. Every cycle refines future recommendations.

    The Loop

    6 steps

    1 operating angles mapped

    Operational Depth

    Real-World Use Cases

    AI decision support for Cu/Au flotation circuit setpoint optimisation

    The system watches plant data in real time and tells operators how to adjust flotation settings so less valuable metal is lost to waste.

    Predictive optimisation and recommendation support for industrial process controlproduction-deployed decision support system with measured plant impact and cross-circuit rollout of identified strategies.
    10.0

    Enterprise OT/IT data sharing with AI-powered analytics

    The system sends plant-floor data to business dashboards so executives and analysts can see what is happening almost immediately and use AI to spot patterns and improve decisions.

    Data fusion, enterprise visualization, and predictive analytics enablementcommercially available and positioned for digital transformation programs.
    10.0

    AVEVA™ Documentation

    The provided page is a documentation search/navigation shell, not a description of an AI workflow.

    unknownno evidence of an ai use case in the provided source content.
    5.0

    Free access to this report