Mars boosts manufacturing with real-time insights and digital twins
Mars, together with Accenture, implemented digital twin technology powered by Microsoft Azure and AI in their manufacturing operations. The solution uses real-time sensor data and predictive analytics to optimize factory production lines, enabling operators to monitor and adjust processes on the fly. After a successful pilot that reduced over-filling in US factories, the approach was scaled to European and Chinese locations and expanded to other Mars divisions, such as pet care. The collaboration includes edge computing capabilities for real-time decision-making, as well as a cloud platform for global deployment and orchestration of manufacturing data, robotics, and AI solutions. The implementation helped Mars significantly enhance its operational agility, reduce costs, and support sustainability goals like water stewardship, waste reduction, and minimizing greenhouse gas emissions. Accenture and Microsoft’s ongoing collaboration continues to extend the solution to more Mars production sites. Mars’s approach focuses on simulation and validation in digital space before implementing physical changes, minimizing downtime and maximizing resource efficiency. This initiative serves as a model for the “Factory of the Future”, aiming for scalable, efficient, resilient, and sustainable food production across the globe.
- Organization
- Mars
- Industry
- Consumer & Food
- Location
- United States
Reported outcomes
Strategic outcomes
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Mars
- Provider
- Microsoft
- Maturity
- Scaled Production
- Linked source
- accenture.com
After a successful pilot that reduced over-filling in US factories, the approach was scaled to European and Chinese locations and expanded to other Mars divisions, such as pet care
Primary read
Use case focus
Showing 3 of 4
- 1Digital Twin Optimization of Food Production Lines
- 2Real-Time Process Insights for Manufacturing Efficiency
- 3Predictive Analytics for Factory Line Adjustments
- Frequent over-filling of food packages leading to product waste and increased costs.
- Limited real-time visibility into factory line performance.
- Manual interventions in manufacturing processes leading to inefficiency.
- Need to scale operational improvements across multiple global sites.
- Sustainability pressures: need to improve water management, reduce waste, and lower greenhouse emissions.
- Implemented Azure Digital Twins with real-time sensor and edge computing integration.
- Used predictive analytics models on Microsoft Azure cloud to optimize production lines.
- Deployed edge computing to provide operators with instant insights and enable process adjustments.
- Expanded architecture to include global cloud platform for orchestration and scaling.
- Combined robotics, AI, and data analytics for comprehensive manufacturing optimization.
- Significant cost savings from reduced over-filling and waste.
- Improved sustainability metrics: water use, waste generated, greenhouse gas emissions.
- Enhanced production quality and reliability across multiple sites.
- Improved agility and readiness for future workforce and digital transformation.
Architecture
Sensor data from manufacturing equipment is streamed to edge devices for real-time analytics, enabling immediate process adjustments. The data is further aggregated in the Azure cloud, where Azure Digital Twins provide a virtual model of production lines. Predictive analytics and AI models simulate, validate, and optimize production. Operators interact with both edge and cloud interfaces, and results are scaled globally via a unified cloud platform.
Implementation partners1
Sources & evidence2
- Customer explicitly identified
- Deployment status explicitly supported
- Technical implementation details available
- Multiple corroborating sources available
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Was this useful?
Community
Comments
No published comments yet.