In-line quality assurance in hairpin welding: how machine learning helps achieve new levels of precision.

Inline quality assurance in hairpin welding

Quality assurance in the laser welding of stators with hairpin technology is a major challenge due to the large number of welded joints. Until now, X-ray computed tomography (CT) has been considered the most accurate method, but it is not practical for inline inspection in series production.

A new method based on machine learning now opens up promising possibilities: By combining various sensor signals - including radiation during the welding process as well as pre- and post-process images - a correlation with the CT measurements of the weld cross-sections is achieved. The developed system achieves a coefficient of determination of 0.953.

In addition, the same data was used to classify the weld seams into six categories with an average accuracy of 98.63%. Both approaches are suitable for series production and show great potential for inline quality assurance in hairpin production. Further improvements are expected through the use of new model architectures and high-resolution cameras.

Read the press release

 

You may also be interested in this

Successful debut of the ProCutter 3.0 at EuroBLECH 2026

At EuroBLECH 2026 in Hanover, we unveiled our new ProCutter 3.0 laser cutting head to an international industry audience. The launch attracted…

Learn more

Functional Metasurfaces Go Global: SurFunction and Precitec Partner for Industrial Deployment

SurFunction and Precitec are joining forces to bring functional metasurfaces into industrial manufacturing worldwide.

The strategic partnership…

Learn more

Xperience Days 2026: Three days of technology, inspiring conversations and shared enthusiasm

What an inspiring three days in Gaggenau! Our Xperience Days 2026 brought together customers and partners from around the world, leaving us with fresh…

Learn more

New Representative in Mexico

We are pleased to announce our collaboration with XVR as our new representative in Mexico.

Learn more

Using machine learning with the Precitec Laser Welding Monitor and a photonic 3D fingerprint to guarantee weld quality

AUDI and Precitec among the finalists for the Photonics Frontiers Award 2026

Precitec and AUDI are on the shortlist for the Photonics Frontiers Award 2026. In the “Industrial laser systems” category, both companies have been…

Learn more

wafer topography and bow control

Metrology moves to the frontline of semiconductor innovation

This Photonics article highlights how advanced metrology is moving to the frontline of semiconductor manufacturing, enabling tighter process control…

Learn more

Precitec supports regional projects with a donation

This year, Precitec is once again taking responsibility and providing targeted support for social institutions and regional projects. 💙

One of our…

Learn more

Picture of a Unimog truck called Explorimog during Explorer Days

Explorer Days inspire over 650 pupils - EXPLORIMOG goes on tour in 2026

The Explorer project began over two years ago with a clear vision: to get children and young people interested in nature, people and technology and to…

Learn more

Presentation at the LASER World of Photonics 2025 trade fair in Munich

Successful appearance at the LASER World of PHOTONICS 2025

Our participation in LASER World of PHOTONICS 2025 was a complete success. Our stand met with a great response, interest in our technologies was…

Learn more

We keep Lasers Running - company run 2025

On Wednesday, May 14, 2025, the time had come again. 25 running enthusiasts from Precitec took part in this year's "BW-RUNNING" company run in Bühl.

…

Learn more