Syringes are essential tools in healthcare for the delivery of medications and collection of bodily fluids for testing. This application focuses on the final syringe after the assembly of the needle, hub, barrel, and plunger.
Defects can occur during syringe assembly due to a variety of factors such as material quality, material handling, equipment performance, environmental conditions, and human error. Common defects include:
These defects can compromise syringe functionality and effectiveness and ultimately put patient safety at risk. Quality escapes can lead to costly recalls, legal issues, and damaged reputation with healthcare providers and patients. It is crucial for manufacturers to conduct rigorous inspections to ensure syringes are safe, effective, and ready to use.
However, syringes can be difficult to detect– the syringe components are typically made from clear plastic, which can be challenging to inspect as transparent parts might not produce enough contrast and can reflect and refract light in unpredictable ways, creating glare or distortion. Additionally, syringe components, especially needles, are small– their defects can be hard to see with the human eye and require advanced optical systems.
Syringes can 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, syringes 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 syringe assembly defects where other solutions fail.
First, the OptiX imaging system illuminates and images assembled syringes. Then, the CorteX Central AI platform is trained on syringe 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 syringe 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.
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 needle inspection are able to:
In this example, we inspected the final assembled syringe for damaged and missing components.
Imaging
First, we used OptiX to capture images of the assembled syringe, making sure we captured both defective and OK parts. We imaged the syringe from four different sides.
Training
Next, we used CorteX Central to train our models. We for four defects: scratch, crack, bent needle, and missing needle. We already checked the barrel and plunging post injection molding for scratch and crack defects, but we also want to inspect the final assembled syringe in case it sustained further damage through the assembly process. We also already checked for bent needle defects as well, but want to confirm needles weren’t bent during assembly. Finally, we added a label for a missing needle defect, indicating that the needle failed to attach to the hub during assembly.
We then labeled those defects in the images we captured from OptiX, using only 9 images of NG parts and 4 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 assembled syringes, resulting in the accurate detection and classification of our four defects.
