Bajjuri Tejaswini completed Predictive Maintenance: Industrial ML for Fault Detection

Built an end-to-end rolling-bearing fault detector from vibration data: identified periodic fault impacts, used kurtosis as the strongest impulsive-fault feature, trained a compact depth-capped decision tree on training bearings only, and evaluated it on a held-out set with catch-rate and false-alarm rate. The memo defended a threshold choice using the student’s own numbers and linked the dominant defect frequency to an outer-race fault.

• Leakage-Free Model Framing
• Interpreting Vibration Signatures
• Compact Tree-Based Classification
• Cost-Aware Threshold Selection