What Ayesha demonstrated

Built an end-to-end rolling-bearing fault detector from vibration snapshots: visualized the signal, selected physics-based features, trained a compact depth-capped decision tree on training bearings only, and evaluated it on held-out bearings with catch-rate and false-alarm metrics. Defended an alarm threshold using explicit cost trade-offs and identified the outer-race fault from the dominant BPFO frequency in a maintenance memo.

• Leakage-Free Model Training
• Physics-Informed Feature Selection
• Held-Out Evaluation
• Cost-Based Operational Decision-Making