Amrutha Varshni G R completed Predictive Maintenance: Industrial ML for Fault Detection

Built a working rolling-bearing fault detector end to end: engineered RMS, kurtosis, crest factor, and envelope-spectrum defect-band energy; localized the fault to the outer race via BPFO; trained a compact depth-1 decision tree on training bearings only; and evaluated it on held-out bearings with reported catch-rate and false-alarm rate. The final memo justified a 0.41 alarm threshold using the student’s own cost numbers and translated the trade-off into maintenance-friendly language.

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