SwedenManufacturing2023 – ongoingEpiroc
Predictive machine learning for steel heat treatment
Epiroc reported 30% fewer customer rejections and product returns with predictive AI
Problem
Epiroc's factories struggled to share heat-treatment data and maintain consistent steel quality. Quality problems sometimes led to equipment returns.
Approach
Epiroc worked with Microsoft and partners to build an AI factory on Azure. Machine-learning models predicted steel properties and helped establish heat-treatment parameters across its manufacturing operations.
Results
Takeaway
Epiroc linked predictive control of steel quality to fewer rejected products and returns, including fewer collection trips.
Categories
- Size
- Large enterprise
- Industry
- Manufacturing
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Partner co-development
- Evidence
- Company's own claim
Sources
Source summaries
Microsoft described Epiroc's use of predictive models to improve steel heat treatment. Epiroc executive Peter Malmberg reported a 30% reduction in customer rejections and product returns.
Full details are in the original sources.
