pinnemaneni charishma sai completed Predictive Maintenance: Industrial ML for Fault Detection

Built an end-to-end rolling-bearing fault detector from vibration data: visualized the faulty waveform, extracted physics-aligned features, localized the fault to the outer race via BPFO dominance, and trained a compact depth-1 decision tree on training bearings only. Evaluated on held-out bearings with reported catch-rate and false-alarm rate, then justified a 0.39 alarm threshold using concrete maintenance costs and a plain-language explanation for operations staff.

• Leakage-Free Feature Engineering
• Honest Held-Out Evaluation
• Physics-Based Fault Localization
• Cost-Based Threshold Selection