RussiaManufacturing2019 – ongoingNovolipetsk Steel
Machine-learning guidance for hot strip mill slab discharge
NLMK reported a 5% shorter slab discharge interval with machine-learning guidance
Problem
Operators manually timed slab discharge from reheating furnaces, balancing collision risks against temperature requirements and mill throughput.
Approach
NLMK Lipetsk introduced a model that analyzed slab properties and mill conditions. It calculated travel time to the rolling mill and prompted the operator to release the next slab. The project began in late 2019.
Results
Takeaway
The system gave operators timing prompts. The reported 5% improvement concerned discharge intervals, without a quantified percentage increase in mill output.
Categories
- Size
- Large enterprise
- Industry
- Manufacturing
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and MLOptimization
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
NLMK described an operating machine-learning service that prompted slab discharge at its Lipetsk hot strip mill. It reported a 5% shorter discharge interval and continued model training.
Full details are in the original sources.
