Maddox AI automates the visual final inspection of pivot pins with high reliability and precision—even for complex surface geometries, demanding handling requirements, and zone-specific defect catalogs.
Product
Industry
Total savings / year
Our customer performs visual final inspection on safety-critical pivot pins with complex surface geometries. The components feature demanding structures such as knurled areas and multiple functional surfaces, all of which require highly precise image capture.
The previous solution was based on a rule-based machine vision system. In practice, this resulted in a high false reject rate because fluctuations in image quality, lighting, and part positioning had a major impact on inspection results. At the same time, the defect classes were too complex for rigid rule-based logic—especially in cases where identical defects had to be evaluated differently depending on their position on the part.
Integration requirements were also demanding. Multiple robots, large camera distances, and camera positions that had to be both protected and precisely aligned made implementation particularly challenging.
With Maddox AI, the existing rule set was replaced by tailored AI-based inspection models. These models learn complex, context-dependent defect patterns directly from image data. In addition, regions of interest can be defined for each image, making it possible to clearly distinguish between relevant and non-relevant areas and reliably map zone-specific defect catalogs.
The rule-based system was highly sensitive to differences in image quality, lighting, and positioning.
The AI models evaluate parts consistently and reliably, even under varying imaging conditions.
Identical defects could not be reliably evaluated differently based on their location on the part.
Regions of interest enable reliable differentiation between relevant and non-relevant areas.
Knurled areas and functional surfaces were too challenging for rigid inspection rules.
Even demanding surface structures and context-dependent defect patterns are detected reliably.
The rule-based system was highly sensitive to differences in image quality, lighting, and positioning.
Identical defects could not be reliably evaluated differently based on their location on the part.
Knurled areas and functional surfaces were too challenging for rigid inspection rules.
The AI models evaluate parts consistently and reliably, even under varying imaging conditions.
Regions of interest enable reliable differentiation between relevant and non-relevant areas.
Even demanding surface structures and context-dependent defect patterns are detected reliably.
Model accuracy
For complete inspection
Reduction in false rejects
Would you like to learn more about our solution? – Test for free now!
We are ISO 27001 certified.
