Prevas

Alleima in Sandviken is a global manufacturer of high-value products in advanced stainless steels and special alloys. The company supplies industries with very high demands on quality and performance, making quality control a critical part of its operations.

In this project, Prevas and Alleima have explored how machine vision and AI can be used to make quality control of long tubes more efficient. Previously, inspections were carried out manually, with operators visually examining the surface of the tubes.

The new solution captures images of the tube surface as the tube rotates and moves through the production line. Up to 1,000 images can be captured for a single tube. The images are analyzed in real time by an AI network trained to identify specific types of defects.

"This is a good example of how AI and machine vision can create tangible value in production. The technology does not replace the operator's expertise. Instead, it helps direct attention to the areas that require closer inspection. This creates the conditions for more consistent and efficient quality control," says Niklas Brusén, Vision and Systems Engineer at Prevas. 

Verified in a real production environment

The installation at Alleima is a pilot project that has so far focused on verifying the technology's ability to identify defects under real production conditions. At the same time, the results highlight opportunities to develop the solution further.

"What is interesting is not only what the technology can do today, but also the possibilities it opens up for the future. By combining AI, machine vision and industrial automation with knowledge of the customer's production processes, we can solve problems that have previously been difficult to automate," says Milad Abdhagh, Account Manager at Prevas.

The collaboration is an example of how Prevas works with AI and advanced machine vision technology to turn new technology into tangible value for industry.

Read more about the project with Alleima on the Prevas website.