P&G Rolls Out AI Quality Inspection System Globally
Procter & Gamble (P&G) is expanding its artificial intelligence (AI) quality inspection system globally, after successful tests on individual lines. The system, built with Siemens, uses deep learning models to inspect products in real-time at full line speed and has reduced scrap by 10-20%, depending on the product.
New installations can be commissioned five to 10 times faster than traditional machine vision systems, allowing P&G to replicate the tool across factories instead of engineering a new system for each plant. This approach is part of P&G's Supply Chain 3.0 program, which aims to cut costs by up to $1.5 billion.
The AI inspection system targets problems that conventional machine vision has struggled with, such as variations in material, package design, and line settings. The platform, called the Visual Inspection Cockpit, runs on Siemens' Industrial Edge hardware, allowing plant engineers to configure, train, and update inspection models themselves without a data science team.