📋 Case Study

Coal Mine Haul Road Surface Degradation Analysis

Unplanned truck tire failures due to undetected potholes and rutting; manual road surveys occurred only quarterly

🏗️ Project Overview

North Antelope Rochelle Mine, Wyoming

🎯 Challenge

Unplanned truck tire failures due to undetected potholes and rutting; manual road surveys occurred only quarterly

🔧 Design Approach

Weekly DJI M300 RTK flights with multispectral + high-res RGB; AI model trained on 12,000 labelled images to classify rut depth, crack severity, and aggregate loss

📐 Design Diagram

Coal Mine Haul Road Surface Degradation AnalysisDroneAI ModelGrading TriggerRut > 15 cm(18.3 cm measured)PotholesRut DepthCrack DensityAggregate LossM300 RTKMultispectral + RGBWeekly Flights12k ImagesLabelled Training SetCrack Index: 2.7 m/m²

AI-generated project design illustration

📐 Key Calculations

Rut Depth Critical Threshold

Rut > 15 cm triggers grading
Result: 18.3 cm
Directly correlates with 4× higher tire failure rate

Crack Density Index

Total crack length / area (m/m²)
Result: 2.7 m/m²
Predicts 30-day surface failure probability at 87%

📊 Results

Tire replacement costs down 22%; haul truck availability increased 4.3%; predictive maintenance scheduling reduced reactive grading by 61%

💡 Lessons Learned

  • Multispectral NIR bands improved moisture mapping under dust film
  • RTK horizontal accuracy <2 cm was essential for rut cross-section profiling

Key Takeaways

  • 1Multispectral NIR bands improved moisture mapping under dust film
  • 2RTK horizontal accuracy <2 cm was essential for rut cross-section profiling