Siemens and Procter & Gamble Scale AI Visual Inspection Worldwide

Industrial technology provider Siemens and global consumer goods manufacturer Procter & Gamble (P&G) are expanding the worldwide rollout of their jointly developed artificial intelligence quality inspection system. Known as the Visual Inspection Cockpit (VIC), the edge-based platform inspects consumer products in real time during production at full line speeds, improving quality consistency while reducing scrap rates by 10 to 20 percent depending on the product line.

Context of the Cooperation
In high-speed consumer goods manufacturing, packaging and products frequently incorporate delicate, textured, and flexible materials that shift, stretch, or wrinkle at high line speeds. Conventional rule-based vision systems struggle to accommodate these subtle physical fluctuations, overlapping components, or low-contrast defects, often requiring extensive reconfiguration and downtime whenever packaging designs, materials, or line parameters change.

To address these inspection bottlenecks and maintain defect-free production across high-speed lines, cooperation was established between Siemens and P&G. The collaboration combines P&G’s proprietary deep learning models and consumer goods manufacturing domain knowledge with Siemens’ edge computing hardware, software scaling frameworks, and industrial AI portfolio. Rainer Brehm, COO for Automation and CTO at Siemens Digital Industries, noted that the system delivers full inspection accuracy for thousands of products per minute across scalable architectures, solving industrial inspection challenges that traditional vision systems could not address.

Technical Solution and Responsibilities
The technological framework pairs localized artificial intelligence inference with edge computing architectures directly adjacent to manufacturing machinery. Responsibilities are allocated across the companies to ensure scalable software lifecycle management and deterministic line control:

Procter & Gamble develops and maintains the deep learning models tailored to high-speed consumer products, material behaviors, and packaging variations.

Siemens provides the industrial computing hardware, including industrial PCs powered by NVIDIA GPUs, the Siemens Industrial Edge platform, software scaling infrastructure, and long-term technical operations across sites.

At a system level, the Visual Inspection Cockpit analyzes live camera feeds directly at line speed. Delivered as an Industrial Edge application, inference processing occurs on-site close to the production equipment, enabling real-time PLC integration and automated responses—such as raising operator alerts or triggering pneumatic reject mechanisms to remove defective units without halting the line. The platform also incorporates the Visual Inspection Engineering Tool, enabling plant personnel to configure and update inspection models locally without dedicated data science teams. Quality data is continuously aggregated to identify process drift and guide long-term continuous improvement programs.

Deployment or Implementation
The implementation strategy focuses on rolling out the Visual Inspection Cockpit across P&G’s global manufacturing footprint. Because VIC is architected as a standardized, modular application within the Siemens Industrial AI Suite, new line installations can be commissioned five to ten times faster than bespoke optical vision solutions.

The ongoing worldwide rollout provides P&G with comprehensive defect detection on high-speed lines while mitigating raw material waste through early anomaly identification. By deploying AI inference on Siemens Industrial Edge platforms, the manufacturing network gains a unified, scalable inspection framework that adapts dynamically to new product designs and material variations.

Edited by Romila DSilva, Induportals Editor, with AI assistance.