Data Collection
Our data collection was performed at the production facility. We used the collected data to populate the metadata of the created dataset.
Semantic Zones and Interpretable Features
The sideseam can be characterized by 8 zones. Each zone except from zones 1 and 8 where we see no significant variability across machine settings, behaves differently depending on the machine setting.
Zone Variability by Machine Setting
| Machine Setting | Zone 2 | Zone 3 | Zone 4-Zone 5 | Zone 6 | Zone 7 |
|---|
| A | scattered to continuous engravings | grooves | medium grey | grooves | waving and dark gray line |
| A1 | deformed continuous engravings | shallow grooves | medium grey | shallow groove | waving and dark gray line |
| A2 | deformed continuous engravings | shallow grooves with bumps | medium grey | shallow grooves with bumps | waving and dark gray line |
| B | scattered engravings | shallow grooves | darker grey | shallow grooves | slightly waving and dark gray line |
| C | smooth with no engravings | grooves | medium grey | grooves | straight and dark gray line |
| D | deformed engravings | grooves | medium grey | grooves | straight and dark gray line |
| E | highly deformed engravings | grooves | darker grey | grooves | straight and dark gray line |
| F | scattered engravings | shallow grooves | medium grey | grooves | straight and dark gray line |
- By detecting a feature that we believe leads to a stress test failure of the product.
- By actually performing a stress test and mapping the results to the machine settings.
For the first case, we highlight two features:
For the second case, after examining the stress test results, for the purposes of this report, the image class C is mapped to the FAIL anomaly class (anomalous condition).
Observations
Images from the 12 machine settings appear similar to each other. The similarity between the images is due to two factors:
-
Different machine settings belong to the same machine setting category and within the category they affect similarly the images.
-
The images are blurred due to an incorrect focus of the camera during data collection. A de-blurring algorithm may result in images with much better discrimination.
The image similarity poses a problem for any computer vision model to distinguish between the nominal and anomalous images and therefore perform with the required accuracy.
| Image Classes | Machine Configuration Category Name | Semantics |
|---|
| A, B, C, A1, A2 | δT | Difference in Temperature |
| D, E, F | δP | Difference in Pressure |
| H, I | δL | Difference in Line rate |
| J, K | δO | Difference in seam Overlap |
Plant Variability
On top of the variability across machine settings, the zones also exhibit variability across plants.
The model must be able to perform well across plants and therefore the model must be exposed to images from all plants and domain adaptation may be required.
