Consumers expect their personal care products to be high quality. Manufacturers of these types of products take great pains to ensure their products are free from defects, including overfills, underfills, and poor labeling. Their brand reputation depends on it. Many leading personal care product manufacturers outsource their manufacturing and packaging to third-party packaging partners. These contract manufacturers must adhere to the strict quality standards set by their customers. Federal Package, based in Chanhassen, Minnesota in the United States, is the preferred contract manufacturer for many well-known brands. They specialize in the development and packaging of a wide range of health, beauty, and personal care products including deodorants, sunscreens, lip balms, serums, and a variety of lotions and creams. They pride themselves on delivering a quality product that supports their customer’s brand image.
Labor Shortages Add Risk to Delivering Exceptional Quality Products
A recent project at Federal Package that involved producing deodorant for a personal care company helped spur the investment in automated inspection. There were two inspection points within the manufacturing process that were good candidates for automation. One 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 label inspection. This involved verifying the correct label was used and that it was applied in the correct position and orientation on the packaging. The production line that they planned to use for this project required operators to manually inspect products after they were filled. To improve productivity and increase quality, automated inspection of each package was an ideal solution.
Ease of Use and Great Customer Service Factor into Machine Vision Partner Decision
Federal Package has invested in machine vision in various areas of its business and has experience with Cognex and other leading machine vision technology suppliers. Their relationship with Cognex was cemented when they wanted to redeploy a legacy product on a new project, which started by registering the product through the MyCognex support site and downloading the software update to take advantage of some feature enhancements. They found the software easier to use than those of other machine vision technology suppliers. In registering the sensor on the support site, Nick Raddatz, the Cognex Account Engineer followed up to see if they needed additional help. The customer service provided by Raddatz, and the positive software experience led Federal Package to select Cognex the next time they needed a vision system, which presented itself with this new deodorant inspection application.
Edge Learning-Based System Inspects 100% of the Products With Over 99% Accuracy
During his conversations with Federal Package, Raddatz introduced one of Cognex’s newest 2D vision systems that featured edge learning technology embedded in the device. Edge learning is a subset of artificial intelligence (AI) in which processing takes place on-device, or “at the edge” of where the data originates, using a pre-trained set of algorithms. The technology is simple to setup, requiring less time and fewer images for training compared to other AI-based solutions, like deep learning. Noah Leuer, a manufacturing engineer at Federal Package, felt this new vision system could do the job and the price point made it easy to justify as an automation technology investment. According to Leuer, “The edge learning-based vision system we selected offered the most options for the money.”
Federal Package bought both a color and a monochrome system. They use the monochrome version for drip inspection and the color version for label inspection, as it could more effectively differentiate between the label boundary and the body of the deodorant container. Leuer was pleased with the adaptability of the embedded AI-based technology within the vision systems.
The drip inspection system evaluated both the front and back of each deodorant package body for excess deodorant that resulted from overfilling. If there was any sign of deodorant on the outside of a package, that unit would be rejected. There were two classifications per side: OK (clean packaging) and NG (packaging with drips).
According to Leuer, “We have between 30 and 40 different deodorant designs which include different fragrances, colors, and names, which means there are many different colors and names associated with the containers that the camera sees. After trialing the system, we learned that the system’s edge learning capability was intelligent enough to filter out the colors 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 were inspected, which manual inspection could not achieve. Their accuracy rate for catching defects is over 99% which means minimal human intervention to remedy the few defective units that get through the inspection.
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. This ease of use enabled Leuer to hand off the setup of the vision systems to the maintenance department, which saved him valuable time to address other automation projects. Another benefit of the new vision systems was the time saved during product changeovers. According to Leuer, “The edge learning classify tool enabled us to quickly train the system with images of both good and bad examples, which simplified changeovers to different types of deodorant products.”
Multiple varieties of container types with different colors and labels meant frequent changeovers. However, the automated inspection system handled the changeovers very easily. Training the system for new product runs only took 5 or 10 minutes, which helped maximize operational efficiency. In addition, Federal Package found that they did not need to retrain the system as often as they expected, which saved them time and increased the efficiency of the line.
Edge Learning Helps Deliver on Brand Image Promise
Quality is the top priority for Federal Package. They know that their customers trust them with their brand image, and they do not take that responsibility lightly. They take every measure possible to ensure that they deliver superior services and products to their customers. According to Leuer, “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 they put in place have enhanced their quality assurance process. As Jerry Bilse, Senior Vice President of Operations at Federal Package stated, “The Cognex edge learning-based vision systems make our best even better.”
Federal Package has also invested in a Cognex AI-based vision system which they plan to use to verify date and lot codes that must be printed on their products to enable tracking through the supply chain for inventory management and lot control as required by their customers and the FDA. As their business continues to grow, Federal Package plans to add more Cognex vision systems across various lines to enhance end-of-the-line product quality where it makes sense.