Laser World of Photonics Showcase
daily coverage of the optics & photonics industry and the markets that it serves
Photonics World

Trumpf to show how AI can make manufacturing more efficient

08 Jun 2023

Presentation at LASER 2023 will highlight benefits of artificial intelligence in manufacturing.

High-tech company Trumpf has developed an AI application for lasers that it says makes manufacturing even more efficient. Electric car manufacturers, for example, could use it to produce more electric motors in less time. It also results in less rework and scrap.

Christian Schmitz, CEO Laser Technology Trumpf, and AI expert Florian Kiefer made the announcement as part of a pre-LASER 2023 virtual press conference from Trumpf’s headquarters in Ditzingen, Germany, on June 6th.

“In the future, we want to use AI to raise the overall system of lasers, optics, sensor technology and software to a new level of performance. We are therefore pushing ahead with the development of further AI solutions that will make laser processes in industry even more powerful and profitable,” said Schmitz.

He added that the AI process has already proven itself practically in series production for e-mobility and can be used in a variety of laser welding applications; “AI makes production significantly more robust.”

Later this month, at the LASER World of Photonics expo, in Munich, Germany, Trumpf will be demonstrating for the first time how AI supports laser welding: it is presenting its AI solutions EasyModel AI, which creates an algorithm and the AI Filter for VisionLine Detect, which applies the algorithm (to the manufacturing process).

To ensure that the weld seam is always in the right place, the laser's sensor technology has to position the weld geometry precisely on the component – to minimize the risk of rejects.

Dirt or scratches on the component, poor lighting conditions in the work area or highly reflective materials such as copper make positioning difficult. Trumpf says “[our] AI solution supports image processing and thus reduces such interference”.

User trains AI

The user must train the artificial intelligence before it is used. To do this, the machine setter marks the relevant component areas in the corresponding image medium, for which programming knowledge is not required.

Trumpf comments: “Using this system is as simple and intuitive as using the painting and drawing programs that everyone knows from smart phones or computers. The AI model created by the training is then used in the AI filter for the VisionLine Detect image processing system.”

CeNing Optics Co LtdBerkeley Nucleonics CorporationLASEROPTIK GmbHHyperion OpticsIridian Spectral TechnologiesUniverse Kogaku America Inc.Optikos Corporation
© 2024 SPIE Europe
Top of Page