Pavithra S completed Predictive Maintenance: Industrial ML for Fault Detection

Built an end-to-end rolling-bearing fault detector: engineered time- and frequency-domain features, localized the fault to the outer race from the dominant BPFO envelope peak, trained a depth-capped decision tree on training bearings only, and evaluated it on a held-out set with reported catch-rate and false-alarm rate. Also wrote a maintenance memo that justified the alarm threshold using the project’s own cost trade-off numbers.

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