Intermediate · 30 min · 4 steps
Spotting a faulty machine by comparing it with its own normal
Sameer Kulkarni, Industrial IoT Analytics Lead at Apex Precision Manufacturing
It is Thursday, 7:45 AM. Sameer Kulkarni is the industrial IoT analytics lead at Apex Precision Manufacturing. He is called to an urgent maintenance meeting at the Pune plant. Apex runs six factories in Maharashtra and Gujarat that make precise car gearbox gears. Every machine has sensors that measure vibration, temperature and electric current.
The question
How do we find each sensor's own normal level and normal spread, so that we can spot readings that are far from normal?
- Statistical anomaly detection
- AVG & STDDEV
- Z-score modeling
- CTEs
The rest of this case study is locked
The data, every step with its code and result, and the final answer open with a pass. A few case studies stay free so you can see how they work.