Cable testing with machine learning!
Quality assurance and efficient product control are now more important than ever to stay one step ahead of the competition. It is therefore important to avoid errors
In order to prevent such errors during the manufacture of cables, the EyeVision image processing software checks cables or entire cable harnesses.
The following properties are recognized:
- Cracks, scratches and dents
- Wide length
- Control of the copper cores
- Completeness of the components
- Position of the components
This inspection can be extended by the software’s machine learning tool. This means that a wide variety of surfaces such as textiles, fibreboard, metal, plastic, etc. can be tested using the one-class classifier. This can classify the normal appearance of a good part with a few error-free images. In this way, all anomalies such as cracks, grooves, scratches, blowholes, bubbles, inclusions, elevations and dents, etc. on the product are detected.