An intelligent anomaly, or error, detection system that helps manufacturers detect fabric defects during the textile production process. The model alerts manufactures on defects and helps them adjust the process. Visit * for details.
Veranneman, a Sioen Industries affiliate, used to rely on expensive machines to check mistakes or holes in the woven technical textiles. The Quality Control consisted of both an industrial machine check and secondly by employees.
The current quality machines were not only costly hardware but also had a steep cost of ownership as it required much technical expertise. For instance, it required programming for every additional type of textile.
Initial data capture set–up to gather data to train a model
Labeling and training in our RVAI platform
Testing the AI model on new data from the data capture set-up
The solution Robovision and Viu More created, allows Sioen to optimize their Quality Control using deep learning-based fault detection. Robovision.ai trained the AI model that detects the anomalies in the textile. The staff receives signals by the AI while the machines run. It allows them to tweak the machine on the fly. Now, not only the cost of quality control is lowered, the batch’s value is being improved while it is operating.
- Easy to setup and adapt without
the need for experts
- More accurate, decreasing false positives
- Capable of improving as it runs