Key Takeaways

  • Post-blast evaluation splits into two AI-driven tasks: tracking where the ore actually moved (Hexagon Blast Movement Intelligence) and measuring fragmentation size (Split-Desktop, WipFrag).
  • Hexagon BMI generates a “Muckpile Block Model” — a post-blast update to your grade-control block model — without requiring personnel to walk the muckpile to place or retrieve monitors.
  • Fragmentation-analysis tools use image-processing/computer-vision techniques on muckpile photos to estimate particle size distribution instead of manual sieving.
  • This is a genuinely mature AI application — both categories have years of field deployment behind them, not just pilot studies.

TL;DR

Evaluate blast performance with two complementary AI tools: Hexagon Blast Movement Intelligence for tracking ore movement into a muckpile block model, and image-analysis fragmentation tools like Split-Desktop or WipFrag for particle size distribution.

How Do I Evaluate Blasting With AI?

Two separate questions get asked after every blast: “where did the ore actually end up?” and “how fragmented is the muckpile?” Both used to require manual, labor-intensive methods — physically placed movement markers retrieved by hand, and hand-sieved or visually-estimated fragmentation grading.

Hexagon’s Blast Movement Intelligence solves the first problem with an AI-driven blast movement engine (developed with Augment Technologies) paired with Blast Movement Monitors. Instead of requiring someone to walk the muckpile — a genuine safety risk — to place and retrieve physical monitors, BMI’s AI models predict and validate ore movement to generate what Hexagon calls a “Muckpile Block Model”: essentially your pre-blast grade-control block model updated to reflect where material actually ended up post-blast. It integrates directly with Hexagon’s MinePlan Block Model Manager, so the muckpile model flows straight into ore/waste delineation decisions rather than sitting in a separate report.

The second problem — fragmentation — is handled by image-analysis software like Split-Desktop and WipFrag. Both work by photographing the blasted muckpile and running edge-detection/segmentation algorithms to isolate individual fragment boundaries, from which they compute a particle size distribution. WipFrag in particular supports zoom-merge analysis, combining images taken at different scales to overcome the resolution limits of any single photo. The output — a fragmentation curve — feeds directly into decisions about whether your blast design needs adjusting for downstream crushing and grinding efficiency (see our companion post on AI-Optimized Blast Design and Execution).

Practically: expect to pair a dedicated camera/monitor setup with either tool rather than treating this as pure software — both categories depend on decent image capture in the field, and results are only as good as your photo quality and calibration reference.

Try It With Geocluster

Deciding between blast-movement and fragmentation-analysis platforms — and understanding how their outputs should feed back into your blast design — is exactly the kind of multi-tool research question worth doing systematically. The Geocluster Research Harness helps you evaluate AI tooling choices like this across your blasting workflow.