Siemens and Procter & Gamble are expanding an AI-based quality inspection system across P&G's manufacturing operations worldwide. The system inspects products in real time at full line speed, and depending on the product, scrap rates have dropped by 10 to 20 percent. New deployments are being commissioned five to ten times faster than traditional bespoke vision systems.
What the system does
The Visual Inspection Cockpit analyzes live camera images in real time and inspects every product passing through the production line. Unlike conventional rule-based vision systems, the AI-based approach is designed to handle a wide range of product variations without frequent reprogramming—an important advantage in high-speed consumer goods manufacturing, where delicate, textured materials naturally shift, stretch, or wrinkle at production speed.
The solution includes a Visual Inspection Engineering Tool that lets plant engineers configure, train, and update inspection models directly, without dedicated data science resources. Inspection results are processed close to the production equipment on Siemens' Industrial Edge platform and integrated directly into manufacturing operations. The system can automatically trigger alerts or remove defective products from the line, and quality data can be collected and analyzed over time to support continuous improvement.
Why the edge matters
The inspection data is processed near the production equipment rather than sent to a remote cloud service. That local processing model is what makes real-time reject decisions and PLC integration practical at high production rates, and it is part of why new deployments can be replicated across plants, products, and inspection scenarios with minimal overhead once the underlying infrastructure, DevOps processes, and integration patterns are in place.
Siemens supplies the industrial computing infrastructure, software scaling capabilities, and long-term operation of the system across production sites. The solution combines P&G's deep learning models with Siemens' Industrial Edge computing platform, industrial PCs powered by Nvidia GPUs, and AI hardware and software. It is delivered as a reusable Industrial Edge application, part of Siemens' broader machine vision and industrial AI portfolio.
The broader signal
The partnership is a concrete example of industrial AI moving from proof-of-concept to repeatable production scale. The measurable outcomes—lower scrap, faster commissioning, and a deployment model that can be replicated across sites—matter more than the demo-friendly aspects of the technology. The open questions are how well the approach generalizes beyond the product types and production environments already covered, how much plant-floor engineering effort is still required to keep models current, and whether the edge-plus-AI pattern becomes a standard building block for quality inspection or remains a customized integration in most places.