Siemens and P&G Scale AI Vision System Across Global Plants

Siemens and Procter & Gamble are rolling out an AI-powered quality inspection system across P&G's manufacturing facilities worldwide, demonstrating how deep learning can solve longstanding challenges in high-speed consumer goods production.

The Visual Inspection Cockpit (VIC) performs real-time inspection of every product moving through production lines, maintaining full accuracy while examining thousands of items per minute. Depending on the product line, the system has reduced scrap rates by 10 to 20 percent compared to traditional inspection methods.

Why it matters

High-speed consumer manufacturing has historically struggled with quality control because products made from delicate, textured materials naturally shift and wrinkle during production. Traditional vision systems require extensive reconfiguration when materials or packaging designs change. This AI approach adapts to variations without constant reprogramming, making quality control scalable across diverse product lines and global facilities—a capability that directly impacts both waste reduction and production economics.

Handling complexity at production speed

The system addresses inspection challenges that rule-based vision systems cannot reliably solve: overlapping components, low-contrast defects, highly decorated packaging, and the need for real-time integration with programmable logic controllers to reject individual defective products at high speeds.

VIC combines P&G's proprietary deep learning models with Siemens' Industrial Edge computing platform, industrial PCs powered by Nvidia GPUs, and specialized AI hardware. The architecture processes camera images locally near production equipment and can automatically trigger alerts or remove defective products from the line.

"Our Industrial AI and Industrial Edge capabilities deliver what high-speed production demands: full inspection accuracy for thousands of products per minute, scalable from a single line to a global footprint," said Rainer Brehm, COO for automation and CTO at Siemens Digital Industries.

Faster deployment, less specialized expertise

The solution includes the Visual Inspection Engineering Tool, which enables plant engineers to configure, train, and update inspection models directly without requiring dedicated data science teams. This design choice makes the technology more accessible for facilities that lack AI specialists.

Because VIC is delivered as a reusable Industrial Edge application, new deployments can be commissioned five to ten times faster than traditional bespoke vision systems. P&G can replicate the solution across plants, products, and inspection scenarios with minimal overhead.

"We engineered this solution to solve a myriad of industry challenges traditional vision systems couldn't touch," said Paul Thomas, director of machine vision and applied AI at Procter & Gamble.

The inspection data feeds into P&G's broader digital manufacturing ecosystem, providing visibility into process stability and supporting continuous improvement initiatives. VIC is part of Siemens' machine vision and industrial AI portfolio, which includes the Industrial AI Suite delivered as standardized applications on the Industrial Edge platform.

These details were first reported by Design News.