Fault detection in real time
Modular optimized production processes
Researchers at the Fraunhofer Institute for Material and Beam Technology IWS have developed Surfinpro, a solution that uses artificial intelligence and optical measurement technology to detect, classify and visualize defects in real time and report them to the production system. The system will be on display at Laser World of Photonics from June 27 to 30, 2023.
Dr. Christopher Taudt, Group Leader of Surface Metrology at the Fraunhofer Application Center for Optical Metrology and Surface Technologies (AZOM) at the IWS in Zwickau, and his team have developed the system, which detects surface defects, artefacts and texture changes and evaluates them with the help of AI. The process is able to quickly capture surfaces in high resolution in three dimensions and generate further information inline from this measurement data for ongoing production. The measuring system has been successfully in use for over a year and analyzes a roll-to-roll process over a width of 70 centimetres. In order to leverage further optimization potential, Taudt and his team are training Surfinpro during ongoing production. The scientists work with an error catalog. They use the reported defects to feed a neural network and thus make the detection of anomalies more precise.
This article appeared in issue 6/23









