Skip to content
Artificial IntelligencePilotPredictive maintenance

Predictive maintenance — Power plant

Vibration, current and thermal models that predict failures days ahead. Delivered for a power plant client in Rajkot.

Location
Rajkot
Year
2020
Duration
33 weeks
Team
10 engineers
Interactive 3D · drag to rotate
31%
fewer breakdowns
6.6
days warning
−17%
maintenance cost

The challenge

Data existed but lived in spreadsheets and legacy systems, so decisions were made on instinct rather than evidence.

What we built

We owned the whole stack — hardware, firmware, models and dashboards — using scikit-learn, XGBoost, InfluxDB so there was one accountable team.

Delivery timeline

  1. Phase 1

    Discovery sprint and site survey

  2. Phase 2

    Prototype built and tested in the Motera lab

  3. Phase 3

    Pilot on site with before/after measurement

  4. Phase 4

    Scale-out, training and handover

Highlights

  • Operator training delivered in Gujarati, Hindi and English
  • Integrated with existing PLC, ERP or GIS systems — no rip-and-replace
  • Runs on-premises; no data leaves the site unless agreed
  • Documentation, drawings and source handed over at close

Have a problem that needs a machine built for it?

Tell us the constraint — line speed, accuracy, environment, deadline. An engineer will read it and reply with a straight answer, including when the answer is that you don't need us.

We reply to every enquiry within one business day.