Subhadeep Sen completed Predictive Maintenance: Industrial ML for Fault Detection

Built an end-to-end rolling-bearing fault detector from vibration data: engineered RMS, kurtosis, crest factor, and defect-frequency envelope features; trained a depth-capped decision tree on training bearings only; and validated it on a held-out set with catch-rate and false-alarm metrics. The student also localized the fault to the outer race via BPFO and defended a 0.42 alarm threshold using concrete cost tradeoffs.

• Leakage-Free Feature Engineering
• Honest Model Evaluation
• Physics-Based Fault Localization
• Cost-Based Decision Making