Darshil Patel completed Predictive Maintenance: Industrial ML for Fault Detection

Built an end-to-end rolling-bearing fault detector using vibration snapshots, physics-based time and frequency features, and a compact decision tree sized for embedded use. The work includes a held-out evaluation and a maintenance memo that justifies the alarm threshold with explicit cost trade-offs, catch-rate, and false-alarm figures, while identifying the outer-race fault from the dominant defect frequency.

• Leakage-Aware Model Building
• Physics-Informed Feature Selection
• Compact Interpretable Classification
• Cost-Based Operational Decision-Making