Edge learning technology improves product quality


Manufacturers of personal care products take great pains to ensure their products are free from defects. Many leading brands outsource their manufacturing and packaging to third-party packaging partners that must adhere to the strict quality standards set by their customers. MEPCA found out how one such packaging partner is using an edge learning-based system from Cognex to maintain the highest quality for its customers.

Federal Package, based in Minnesota in the United States, specialises in the development and packaging of a wide range of well-known health, beauty, and personal care products. The company prides itself on delivering a quality product that supports its customer’s brand image.

A recent project that involved producing deodorant for a personal care company helped spur an investment in automated inspection. One inspection point was checking the plastic packaging that housed deodorant for drips that not only indicated overfilling but also resulted in a poor product presentation. The second quality checkpoint was verifying the correct label was used and that it was applied in the correct position and orientation on the packaging. To improve productivity and increase quality, automated inspection of each package was an ideal solution.

Edge learning-based system 

Federal Package has invested in machine vision in various areas of its business. The customer service provided by Cognex and a positive software experience led Federal Package to select Cognex with this deodorant inspection application.

Noah Leuer, a manufacturing engineer at Federal Package, got to know one of Cognex’s newest vision systems with embedded edge learning technology. Edge learning is a subset of artificial intelligence in which processing takes place on-device using a pre-trained set of algorithms. The technology is simple to set up, requiring less time and fewer images for training compared to other AI-based solutions, like deep learning.

Noah Leuer felt this new vision system could do the job, and the price point made it easy to justify as an automation technology investment. The drip inspection system evaluated each deodorant package body for excess deodorant that resulted from overfilling.

According to Noah: “We have between 30 and 40 different deodorant designs with different fragrances, colours, and names. The system’s edge learning capability was intelligent enough to filter out the colours and names and focus on the actual defects of the product.”

The drip inspection line runs close to eighty units per minute, and the label inspection line runs around sixty units per minute. In both cases, the automation enables more throughput, as well as guaranteeing all units are inspected, which manual inspection could not achieve.

In addition to the attractive price point of the new Cognex edge learning-based vision system, Federal Package was impressed with how easy the system was to set up and train. Once initially installed on the line, the vision systems were deployed on the production line within an hour and can be retrained for product changeovers in 5-10 minutes.

Delivering on brand image promise

Quality is the top priority for Federal Package. According to Noah: “As a packaging partner to personal care manufacturers, it’s a requirement of the partnership to deliver high-quality consumer products that delight customers and preserve brand value.” The new edge learning-based automated inspection systems that have been put in place have enhanced the company’s quality assurance process, making its best even better.

Federal Package has also invested in a Cognex AI-based vision system which it plans to use to verify date and lot codes that must be printed on its products to enable tracking through the supply chain for inventory management and lot control as required by its customers and the FDA.



About Author

Comments are closed.