Vision AI Solution for Packaging Integrity & QA
Vision AI Solution
for Packaging Integrity & QA
The Vision AI Solution for Packaging Integrity & QA is a robust, Vision AI-based, in-line packaging integrity & quality assurance system powered by PerCV.ai, that eliminates the need for human inspection in production lines.
It allows 24/7, unsupervised monitoring of products traveling on manufacturing production lines, detecting:
Surface quality of bags (tears, dents, spills, underweight, dirty)
defects smaller than1 centcoin
Accuracy in defects & printing failures
99
%
on the bag surface
“This Vision AI-based QA system not only allowed us to cut on labor cost for manual inspection by more than 80%, but also reduced product returns & cost of poor quality, minimised compliance risks, and helped us measure & improve the production process overall.”
Plant Manager,
European Cement Company
Vision AI Solution Components
Fully custom Vision AI software, tailored to each plant production specifics. Under the hood, PerCV.ai platform for on-device Vision Intelligence is utilized to build efficient and robust Defect Detection, Packaging Integrity and Quality Assurance solutions, that run in real-time and rely solely on our proprietary ML engine.
Host Device: e.g. Edge Device or Industrial PC
AI Accelerator: ADLINK NVIDIA® Jetson Nano™ Edge Inference Platform provide the sensor with the computational power required to run advanced AI vision workloads
The PerCV.ai Dashboard & AI Analytics is providing real-time, visual check of the functionality of the system.
- Automatic, concurrent image capturing based on camera triggering mechanism
- Capture data / images during system operation and store to the local Industrial PC
- Visually check the Defect (or Production Date) that the AI system detected in real-time
- Data analytics and graph-based statistics (plots)
All metadata can be easily transmitted to your existing software stack (i.e. ERP, WMS etc) via the industry standard MQTT & API protocol
Basler ace camera and lens
Camera module and optics are protected from the industrial environmental conditions (vibrations, dust, moisture) with a compact IP66/IP67 camera enclosure
- Robust construction, compact size
- High IP protection glass
- High chemical resistance
- Vibration-proof mounting
- Excellent heat dissipation
Get in Touch with our Team!
Get in touch in order to explore further how our Vision AI Solution for Packaging Integrity & QA, powered by PerCV.ai, can help automate the integrity inspection and quality assurance procedures at your company. We would love you to give us a very brief description of your implementation scenario, so that we assemble the most qualified team of Vision AI experts for our discussions!
Benefits
QA practices in manufacturing have long relied on visual inspection of products rolling off the production line. However, the error-prone nature of human inspection not only is labor-intense, but also suffers from optical illusions and fatigue.
24/7 Automated Quality Inspection
Labor cost reduction
Product Consistency
Real-time monitoring from anywhere in the plant
VISION AI at the EDGE
Fully custom Vision AI software, tailored to the plant production specifics
Edge device processing – No cloud
Our Vision AI technology surpasses human vision in quality and quantity measurements because of its speed, accuracy, and repeatability. Combined with the necessary optics, Vision AI can also detect defects that are impossible to consistently spot with the naked eye!
Zero-Defect Palletizing
Reduced Cost of Poor Quality (COPQ)
Compliance with regulations (label/date misprint)
Reduced regulatory fines risk
Production Improvement
Identify production weaknesses & inconsistencies
Cement Bag Defect Examples
Defect: Product Spill
Defect: Printing Failure
Defect: Cut or Damaged Edge
Vision AI – one step closer to human-like intelligence
PerCV.ai, Irida Labs’ end-to-end AI software and services platform, enables the real-time identification and QA of multiple products in indoor or outdoor conveyer systems, such as cement bags of all types. It can be easily deployed on pre-existing production lines, allowing quick implementation at scale – moving from prototype to full-scale deployment in weeks, not years. With pre-trained AI/ML models and minimal data campaign requirements, the system can be quickly trained on identifying new products (i.e. bag sizes, product types, new packaging) with remarkable accuracy & consistency.
Previous
Next
Custom Implementation?
Do you need a custom solution, tailored to your specific use case? Talk to our team, we will support you throughout the design and the deployment phases!