This application focuses on rigid plastic packaging inspection for defects that can compromise the product’s safety, longevity, quality, and brand.
The manufacturing of plastic food containers involves several processes, tailored to meet the specific requirements of the end product. One such common manufacturing process is injection molding, ideal for manufacturing high volumes of uniform items such as tubs, caps, and other rigid containers. It works by injecting molten plastic into a mold at high pressure. Once the plastic cools and solidifies, the mold opens to release the part.
Various defects can occur during injection molding that affect the quality, functionality, and aesthetics of the container. Common defects include:
These defects can reduce structural integrity, making the containers susceptible to breakage or failure during use. Since these containers are used for food packaging, these defects can lead to leaks, contamination, or spoilage of the contents. This can compromise the safety or compliance of the container, posing health risks to consumers and potentially leading to legal and regulatory consequences. It is critical that manufacturers minimize these defects through careful control of the injection molding process.
However, these defects can be difficult to detect– plastic material is challenging to inspect as transparent parts don’t always produce enough contrast and can reflect and refract light in unpredictable ways, creating glare or distortion.
Containers can also vary in size and type, each requiring different inspection criteria. Traditional machine vision requires programming hundreds of hand-crafted rules, causing them to fail to detect new or variable parts or defects that don’t match their programmed parameters.
And in high-volume manufacturing environments, containers must be inspected quickly to keep up with production rates. Traditional machine vision products may fail to keep up with required cycle times.
UnitX’s AI-powered inspection effectively detects food container plastic injection molding defects where other solutions fail.
First, the OptiX imaging system illuminates and images the containers. Then, the CorteX Central AI platform is trained on plastic injection molding defects. Lastly, those AI models are deployed to the CorteX Edge inference system to detect and classify defects in-line.
OptiX provides superior images that minimize reflectivity while maximizing defect visibility. It has 32 independently controllable lighting sources that can be optimized for various transparent plastic surfaces and defects via software. And its lighting dome design supports a very acute incidence angle of projected light, causing even very tiny defects to cast shadows which increase their visibility.
CorteX accurately detects random, complex defects. It automatically normalizes for variability in positions and orientations and recognizes defects down to the pixel-level. It reduces false positives that lead to scrap and wasted product.
CorteX supports fast AI model development, deployment, and iteration. CorteX AI models are sample efficient– they only require a few images to train on new defect types.
UnitX optimizes yield. In CorteX, can tune quality criteria and visualize the impact on yield before rolling those changes to production. All inspection data is referenceable in one central platform for manufacturers to analyze and identify areas for process improvements and pull up historical records to limit the scope of recalls and fight fraudulent claims when needed.
UnitX provides rapid, 100% inline inspection. OptiX has bright LEDs and fast fly capture speeds of 1m/s for high speed imaging. And CorteX Edge supports high inference speeds (up to 100 MP) to quickly output an OK/NG decision, seamlessly communicating that decision via integration to all major PLC, MES, and FTP systems.
Manufacturers who use UnitX to automate syringe component injection molding inspection are able to:
In this example, we inspected plastic food containers after the plastic injection molding process for burns and splays.
Imaging
First, we used OptiX to capture images of the containers, making sure we captured both defective and OK parts. This required both top and backlighting, as well as rotation of the part to image the container from all sides.
Training
Next, we used CorteX Central to train our models. We created labels for two defects: burns and splays. We then labeled those defects in the images we captured from OptiX, using only 7 images of NG parts and 3 images of OK parts.
Because of CorteX’s user friendly interface and the low number of images it requires to train its AI models, it only took us a few minutes to label the defects in the images.
Detection
We then deployed those AI models to CorteX Edge to detect defects on new containers, resulting in the accurate detection and classification of burns and splays.
