Normalized claim
Time: 60 hours
Rapid deployment (AI factory in 60 hours, full model deployment in 6 weeks).
Last evidence check: Jun 1, 2026
Epiroc standardizes global manufacturing quality with AI-driven factory solution
Use case typeManufacturing quality monitoringUpdated Jun 13, 2026
Epiroc, a global Swedish manufacturer of mining and construction equipment, faced challenges ensuring consistency in steel quality across its worldwide facilities. Relying on disparate local systems, Epiroc struggled to leverage massive amounts of operational data, impacting both product quality and process efficiency. By deploying a modern 'AI factory' on Microsoft Azure, the company centralized data collection and utilized Azure Machine Learning, Data Factory, Databricks, and ESML (Enterprise Scale Machine Learning) to build automated predictive models for its heat treatment process. The ESML accelerator and local partner Molnbolaget enabled the rapid deployment (within 60 hours) of an architecture spanning multiple services with secure networking. Epiroc now benefits from improved quality control, reduced waste, best-practice sharing across sites, and support for sustainability initiatives—all powered by Microsoft’s cloud and AI capabilities.
- Organization
- Epiroc
- Industry
- Manufacturing
- Location
- Sweden
- Published
- May 2025
Reported outcomes
60 hours
timeTime & speed
Strategic outcomes
New product / capabilityBuilt an AI factory solutionCustomer experience & trustImproved quality and consistency of steel productsSustainability & ESGReduced waste and improved resource managementInnovation & cultureShared AI best practices across plants
Why do we believe this?Outcome claims, sources, and evidence checks
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Epiroc
- Provider
- Microsoft
- Maturity
- Production
- Linked source
- microsoft.com
Relying on disparate local systems, Epiroc struggled to leverage massive amounts of operational data, impacting both product quality and process efficiency
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 3
- 1quality control
- 2manufacturing analytics
- 3predictive maintenance
- Inconsistent steel quality and precise process control across distributed manufacturing sites.
- Inability to efficiently share operational data and best practices between global facilities.
- Manual, labor-intensive process monitoring limited optimization.
- Need for scalable, centralized analytics to support innovation and sustainability.
- Centralized operational and sensor data in Azure Data Lake using Data Factory and Databricks.
- Built an AI factory solution with Azure ML for automated predictive modeling of heat treatment processes.
- Leveraged ESML from Microsoft Sweden and local partner Molnbolaget for best practices and rapid setup.
- Integrated Power BI for advanced analytics and reporting.
- Rapid deployment (AI factory in 60 hours, full model deployment in 6 weeks).
- Improved quality and consistency of steel products worldwide.
- Reduced waste and better resource management for sustainability.
- Streamlined insights and sharing of AI-driven best practices across global plants.
Architecture
Epiroc implemented a modern data architecture on Microsoft Azure, centralizing global data with Azure Data Factory, then feeding it through Databricks and the ESML accelerator for AI model building in Azure ML. Secure private networking ensures company-wide scalability, with Power BI providing reporting and analytics.
Sources & evidence2
Evidence: High85/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
- Multiple corroborating sources available
- Recent evidence check available
- Last evidence check: Jun 1, 2026.
Live sourceStill referenced
The case's original source is still reachable.
- Cited source last checked Jun 1, 2026 — ok (0/2 broken).
Measures whether this deployment's public evidence persists — not whether the system is still in production.
Type: Customer StoryPublished: May 21, 2025Publisher: microsoft.comEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Was this useful?
Community
Comments
No published comments yet.