Blast Design Optimization and Safety Copilot
Optimizes underground drill-and-blast patterns using design and muckpile image analysis to improve fragmentation, reduce oversize and fines, and provides blast safety prediction with clearance-zone alerting for safer execution.
The Problem
“Blast Design Optimization and Safety Copilot for Underground Mining”
Organizations face these key challenges:
Persistent fragmentation variability in deep-level longhole stoping
Oversized rocks causing grizzly blockages and production interruptions
Excessive fines reducing downstream efficiency
Blast design tuning depends heavily on individual engineer experience
Impact When Solved
The Shift
Human Does
- •Review blast designs and past blast results to adjust burden, spacing, charging, and timing
- •Inspect muckpiles visually and judge oversize and fines issues after each blast
- •Coordinate pre-blast safety checks, radio confirmations, and exclusion-zone clearance
- •Decide blast readiness and authorize firing based on SOPs and crew input
Automation
Human Does
- •Approve or reject recommended blast pattern changes for each ring or stope
- •Investigate exceptions, conflicting signals, or unusual geology before finalizing plans
- •Confirm final blast readiness, handle escalations, and authorize firing
AI Handles
- •Analyze blast designs, operating history, geology, and muckpile images to estimate fragmentation outcomes
- •Recommend burden, spacing, charge, and timing adjustments to reduce oversize and fines
- •Monitor pre-blast conditions and score blast safety risk against readiness thresholds
- •Issue clearance-zone alerts and explain go or no-go status in simple operational language
Operating Intelligence
How it works
AI runs the first three steps autonomously.
Humans own every decision.
The system gets smarter each cycle.
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.
Step 1
Assemble Context
Step 2
Analyze
Step 3
Recommend
Step 4
Human Decision
Step 5
Execute
Step 6
Feedback
AI lead
Autonomous execution
Human lead
Approval, override, feedback
AI handles assembly, analysis, and execution. The human gate sits at the decision point. Every cycle refines future recommendations.
The Loop
6 steps
Assemble Context
Combine the relevant records, signals, and constraints.
Analyze
Evaluate options, risk, and likely outcomes.
Recommend
Present a ranked recommendation with supporting rationale.
Human Decision
A human accepts, edits, or rejects the recommendation.
Authority gates · 1
The system must not authorize firing; final blast readiness and firing approval remain with the responsible supervisor or other designated human authority. [S1][S2]
Why this step is human
The decision carries real-world consequences that require professional judgment and accountability.
Execute
Carry out the approved action in the operating workflow.
Feedback
Outcome data improves future recommendations.
1 operating angles mapped
Operational Depth
Real-World Use Cases
Underground drill-and-blast pattern optimisation with Aegis and muckpile image analysis
The mine used software to study photos of blasted rock and simulate blast-hole layouts so it could change the drilling pattern and produce rock pieces that are not too big and not too fine.
Blast safety prediction and clearance-zone alerting
The system predicts whether a blast may violate safety limits and warns operators visually on maps or drone images before the blast happens.