AI4I 2020 Dataset · 10,000 IoT machine cycles · Real-time edge failure intelligence
Live telemetry across 200 machine cycles · Failure events marked with red triangles
Engineered features: Temperature Difference · Power Estimate (RPM×Torque) · Tool Wear Rate
Logistic Regression · Random Forest · XGBoost — 8,000 train / 2,000 test · Stratified split
| Model | Accuracy | Precision | Recall | F1 Score | CV F1 (5-fold) | Verdict |
|---|---|---|---|---|---|---|
| Logistic Regression | 85.95% | 17.82% | 86.76% | 29.57% | 27.61% | Best Recall |
| Random Forest ⭐ | 98.60% | 90.00% | 66.18% | 76.27% | 78.01% | Best Overall |
| XGBoost | 98.35% | 77.78% | 72.06% | 74.81% | 77.91% | Balanced |
Feature importance via Random Forest · Mean comparison: Failure vs No-Failure cycles
Adjust sensor sliders to simulate machine conditions · Rule-based RF threshold model
Actionable IoT edge maintenance strategies · Manufacturing & Automotive · AI4I 2020 analysis