PolandManufacturing2021 – ongoingKGHM Polska Miedź
AI prediction and control of flash-furnace heat losses
KGHM reported nearly 100% effectiveness predicting heat losses at its Głogów copper furnace
Problem
Operators at the Głogów copper smelter needed to stabilize heat removal in the flash furnace's reaction shaft. Fluctuations complicated control of the smelting process.
Approach
Data Drivers developed the solution after KGHM's 2021 CuValley Hack competition. KGHM subsequently completed deployment of algorithms that used historical operating data to predict near-term heat losses. The system could automatically adjust furnace parameters to stabilize them.
Results
Takeaway
The prediction was connected to operating controls. KGHM did not define the error tolerance behind its nearly 100% effectiveness claim.
Categories
- Size
- Large enterprise
- Industry
- Manufacturing
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and MLOptimization
- Adoption
- Partner co-development
- Evidence
- Company's own claim
Sources
Source summaries
KGHM reported completed deployment of AI supporting flash-furnace operators at Głogów. It claimed nearly 100% effectiveness in predicting heat losses and described automatic adjustment of operating parameters.
Full details are in the original sources.
