Unilever has partnered with Accenture to scale the use of AI-enabled digital twins across its global manufacturing sites. The consumer goods company plans to build more than 40 new digital twins over the next 18 months to improve production quality and operational efficiency.

Unilever is integrating digital twin models with AI agents to identify maintenance needs and simulate production scenarios. The system is designed to eventually take on certain process adjustments automatically under human oversight.

The company reported that existing digital twins have already yielded measurable results. At a personal care facility in North Carolina, the technology predicted 95% of process flow restrictions, leading to a 20% reduction in waste. In Poland, a digital twin used for mayonnaise production reduced minor stoppages by 20% and cut waste by nearly 30%.

In India, the company deployed an “energy twin” at a detergent plant to optimise fan speeds and temperature settings, resulting in lower thermal energy consumption. Another twin at a soap manufacturing site helped reduce quality defects by 30% over a four-year period through real-time control recommendations.

“Scaling AI across our operations isn’t just a technological shift, it’s a commitment to superior products, sustainability and empowering our teams across our factories,” said Adam Raeburn-James, Global VP for Digital Business Operations at Unilever.