Fragmentation QA QC

Fragmentation QA QC

Introduction

Strayos’ Fragmentation AI is a powerful tool that leverages deep learning to analyze muckpile images, providing accurate rock size distributions and blast performance insights for mining operations. This Quality Assurance/Quality Control (QA/QC) workflow guide ensures that customers collect high-quality data, process it effectively, and interpret results reliably.

Pre‑Flight Best Practices

Task

Recommendation

Why

Timing

Capture 10–15 min after blast when dust settles. Avoid long shadows

 Clear edges, fewer artifacts.

Altitude

20–40 m AGL (GSD ≤ 2 cm).

Detects ≥ 10 mm fragments.

Overlap

80 % front / 70 % side.

Fewer voids in point cloud.

 

Environmental Considerations

  1. Lighting Fly during optimal lighting conditions (e.g., mid-morning or early afternoon) to minimize shadows that can obscure rock edges.
  2. Weather  Avoid flying in rain, high winds, or fog, which can affect image quality or drone stability.
  3. Calibration : Verify drone sensors (e.g., GPS, camera) are calibrated and the battery is sufficient for the flight.


QA/QC Check

  1. Confirm flight plan covers the entire muckpile.
  2. Review sample images post-flight to ensure clarity and no obstructions.

 

Field Image QA

1.   Review sample photos for blur & shadow.

2.   Ensure full pile coverage—no gaps on flight app grid.

3.   Re‑fly missed bands immediately.

Upload & Processing Steps

1.   Create a Fragmentation project → Upload images
2.   Set coordinate system & identify scale objects.

3.   Enable Fragmentation AI and choose Custom size bins if needed.

4.   Click Process

The AI performs photogrammetry, segmentation, and PSD calculation automatically.

QC Checklist After Processing

Check

Pass Criteria

Fix if Fail

Point‑cloud completeness

No gaps or floating points.

Add images; re‑process High‑Quality.

Segmentation accuracy

≥ 90 % correct outlines in spot check.

Use Edit Rock Nodes; split/merge.

PSD curve shape

Smooth S‑curve; logical D50/P80.

Verify scale & GSD; adjust bins.

Histogram outliers

< 5 % in extreme bins (unless expected).

Inspect for blur/shadow in images.

 

Editing & Customization

  1. Custom bins: Settings → Size Ranges.
  2. Node editing: Split oversized polygons or merge over‑segmentation artefacts.
  3. Click Re‑run to refresh stats.

 

Reporting & Interpretation

1.   Open Analytics → Fragmentation Report

2.   Review P80, P50, Uniformity Index, Fines %.

3.   Export PDF / CSV and share.

4.   Compare to blast design targets; log variances.

 

Common Pitfalls & Quick Fixes

Symptom

Root Cause

Remedy

Excess fines

Too high altitude / noise.

Fly 15–20 m; fly slower

P80 spike

Add scale object if possible

Use calibrated bars next run.

Smeared rocks

Motion blur.

Shutter ≥ 1/1000 s; slower UAV speed.

Processing fail

< 60 images / low overlap.

Add images; re‑plan grid.

 

Common Issues

  1. Poor Image Quality : Blurry or shadowed images lead to inaccurate rock detection.

  1. Incomplete Coverage : Missing sections of the muckpile result in incomplete analysis.

  1. AI Misidentification : Shadows, debris, or complex rock shapes cause errors in boundary detection.

Solutions

  1. Image Quality : Refly the muckpile under better lighting or adjust camera settings for higher resolution.
  2. Coverage : Review flight logs to confirm full coverage and plan additional flights if needed.
  3. AI Errors : Use manual editing tools to correct boundaries or contact Strayos support for advanced troubleshooting.

 


    • Related Articles

    • Fragmentation Prediction

      Overview Strayos provides you the most accurate fragmentation predictions possible by automatically calibrating them using previous blasts. The prediction models continually learn and improve as you use the Fragmentation Prediction and Fragmentation ...

    • Fragmentation Analysis - User Guide

      Overview Strayos uses deep learning algorithms to automatically detect rock boundaries and calculate fragmentation particle size distributions. Activating the analysis This analysis is triggered at the project upload stage by activating the ...

    • How the fragmentation AI works

      Obtaining rock contours Pipeline 1) Pre-processing Input is an orthographic RGB image with resolution . Since the input orthographic image could cover an area and such image could have size , to avoid the Out-Of-Memory problems algorithm splits the ...

    • How to Change Fragmentation Measurement Settings

      Strayos offers several ways to customize Rock Colors and Rock Diameter Calculations in the fragmentation module. Users can choose between these settings in their site settings, pictured below. Once the settings are enabled, it will be used for new ...

    • Which fragmentation size algorithm/equation is best for the prediction?

      Both the Kuzram and Xp Frag Cunningham models are commonly used for the fragmentation prediction. Both the methods used common parameters for the fragmentation prediction, such as bench height, burden, spacing, RWS, etc. While a few parameters are ...