AI / CPS Laser Processing

[SLPC8-01(Invited)] Successful determination of the physical properties of a weld seam - how much information is buried in the sensor signals of a laser welding process?

*Markus Kogel-Hollacher¹, Jens Reiser¹, Joachim Schwarz², Fabian Mack¹, Thomas Nicolay³, Stan Watanabe⁴ (1. Precitec GmbH & Co. KG, 2. Precitec Vision GmbH & Co. KG, 3. Precitec Optronik GmbH, 4. Precitec Japan Ltd)

The focus of this presentation is on using artificial intelligence algorithms to "make the invisible visible". We will discuss how classified, physical properties can be derived from already reliable process information. Rather than defining complex rules for algorithms, the use of Data Science and Machine Learning methods reveals hidden structures in noisy unstructured data and make it possible to find the relationships of the data to the physical measurement.