Skip to content

Pranitha GUNIGANTI completed Predictive Maintenance: Industrial ML for Fault Detection

  • Verified
  • Issued 23 July 2026

What Pranitha demonstrated

Built a working rolling-bearing fault detector end to end: engineered time-domain and envelope-spectrum features, identified the dominant BPFO outer-race signature, trained a compact depth-capped decision tree on training bearings only, and evaluated it on held-out bearings with a full confusion matrix. The decision memo defended a cost-based alarm threshold using the candidate’s own catch-rate, false-alarm rate, and maintenance-cost numbers.

  • Leakage-Free Feature Engineering
  • Honest Held-Out Evaluation
  • Cost-Based Operational Decision-Making
  • Interpreting Defect Frequencies

The challenge Pranitha passed

Predictive Maintenance: Industrial ML for Fault Detection

Become a German condition-monitoring engineer. A motor that sounds fine will seize in three weeks — hear the crack inside the bearing from a sensor on the outside. You build a real fault detector by hand in Python: engineer the vibration features, train a tiny classifier, locate the fault from its frequency signature, test it on bearings it never saw, and set an alarm threshold on cost. Physics-based synthetic data; not affiliated with or endorsed by Schaeffler.

  • 2-3 hours · one shift
  • Intermediate
  • Your role: Condition-Monitoring Engineer
  • Rated 4.4 by 62 students
  • 300+ students started it
Builds toward
  • Condition Monitoring
  • Predictive Maintenance
  • Machine Learning
  • Signal Processing

What you will do

  1. 01Cold Open & Onboarding
  2. 02Act 1 · Hear the Failure
  3. 03Act 2 · Turn a Wiggle Into a Number
  4. 04Act 3 · Find the Fingerprint
  5. 05Act 4 · Teach the Sensor to Decide

Verified by ProoV · 629585b86976f5ed…