Pablo Dilger: Assessing Laser Welding

Symbolic picture for the article. The link opens the image in a large view.

For his conference contribution “Determination of the beam position in laser deep penetration welding using coaxially acquired images of the keyhole front and machine learning”, Pablo Dilger trained a convolutional neural network in evaluation of high-speed images of laser welding processes. With his work, he sets the foundation for a quality control system for weld inspection.

Similarly, in his paper “Camera-based closed-loop control for beam positioning during deep penetration welding by means of keyhole front morphology”, he presents real-time image processing for adaptive correction of the beam position in laser welding.

Pablo Dilger works at the Institute of Photonic Technologies, his supervisor is Michael Schmidt.