Energy optimisation — Glass
Reinforcement-learning control of chillers, compressors and furnaces. Delivered for a glass client in Mumbai.
- Location
- Mumbai
- Year
- 2025
- Duration
- 21 weeks
- Team
- 9 engineers
- 11%
- energy saved
- 17.9 mo
- payback
- 554
- t CO₂/yr avoided
The challenge
Conditions on site — heat, dust, vibration and patchy connectivity — had defeated two earlier attempts at this in glass.
What we built
We ran a two-week discovery sprint, then built and fielded the system end to end on Ray RLlib, Python and BACnet, with operator training and an SLA.
Delivery timeline
Phase 1
Discovery sprint and site survey
Phase 2
Prototype built and tested in the Motera lab
Phase 3
Pilot on site with before/after measurement
Phase 4
Scale-out, training and handover
Highlights
- Remote monitoring and over-the-air updates included
- Runs on-premises; no data leaves the site unless agreed
- Safety case reviewed with the client's EHS team
- Operator training delivered in Gujarati, Hindi and English
Related AI projects
AIDeliveredData centre · Nagpur · 2023
Energy optimisation — Data centre
Reinforcement-learning control of chillers, compressors and furnaces. Delivered for a data centre client in Nagpur.
- 11%
- energy saved
- 10.8 mo
- payback
- 3,311
- t CO₂/yr avoided
AIDeliveredPharmaceutical · Kutch · 2026
Energy optimisation — Pharmaceutical
Reinforcement-learning control of chillers, compressors and furnaces. Delivered for a pharmaceutical client in Kutch.
- 12%
- energy saved
- 16.4 mo
- payback
- 556
- t CO₂/yr avoided
AIR&DHospital · Nagpur · 2025
Energy optimisation — Hospital
Reinforcement-learning control of chillers, compressors and furnaces. Delivered for a hospital client in Nagpur.
- 18%
- energy saved
- 15.9 mo
- payback
- 2,526
- t CO₂/yr avoided
AIPilotMall · Mehsana · 2021
Energy optimisation — Mall
Reinforcement-learning control of chillers, compressors and furnaces. Delivered for a mall client in Mehsana.
- 25%
- energy saved
- 17.2 mo
- payback
- 1,054
- t CO₂/yr avoided
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.