Jithin J R completed Predictive Maintenance: Industrial ML for Fault Detection

Built an end-to-end rolling-bearing fault detector from vibration snapshots: visualized the faulty waveform, engineered time-domain and envelope-spectrum features, trained a shallow decision tree on training bearings only, and evaluated it on a held-out set with reported catch-rate and false-alarm rate. The work also localized the fault to the outer race via BPFO and justified a 0.5 alarm threshold with a maintenance-focused cost trade-off.

• Leakage-Free Feature Selection
• Fault Localization from Envelope Spectrum
• Honest Held-Out Evaluation