Tisha completed Predictive Maintenance: Industrial ML for Fault Detection

Built a working rolling-bearing fault detector end to end: visualized a faulty vibration snapshot, extracted RMS/kurtosis/crest-factor and defect-band envelope energy, trained a compact depth-capped decision tree on training bearings only, and evaluated it on held-out bearings with catch-rate and false-alarm rate. The memo defended a 0.37 alarm threshold using the student's own cost numbers and correctly identified an outer-race fault from the BPFO peak.

• Leakage-Free Feature Engineering
• Honest Held-Out Evaluation
• Physics-Based Fault Localization
• Cost-Based Threshold Selection