Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Deep learning-based semantic segmentation for in-process monitoring in laser welding applications

: Knaak, Christian; Kolter, Gerald Manuel; Schulze, Frédéric; Kröger, Moritz; Abels, Peter


Zelinski, M.E. ; Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Applications of Machine Learning : 13-14 August 2019, San Diego, California
Bellingham, WA: SPIE, 2019 (Proceedings of SPIE 11139)
ISBN: 978-1-5106-2971-4
ISBN: 978-1-5106-2972-1
Paper 1113905, 13 pp.
Conference "Applications of Machine Learning" <2019, San Diego/Calif.>
Conference Paper
Fraunhofer ILT ()
laser beam welding; Convolutional Neural Networks; machine learning; auxiliary illumination; coaxial process monitoring

The broad uses of laser welding in various industrial applications such as shipbuilding, automotive production and battery manufacturing, result from its capabilities of high productivity, flexibility and effectiveness 1. However, the complex nature of laser-material interaction requires additional measures in order to reach the high-quality standards of the goods produced. Therefore, continuous process monitoring in laser welding is crucial to achieve reliable mass production and high-quality products at once. Camera-based process monitoring offers great advantages compared to one-dimensional observation techniques. The spatial resolution enables the monitoring of several process characteristics simultaneously, which leads to a more detailed description of the current process state 2. In the last few years, we proposed a coaxially integrated camera system with external illumination. Process images taken by this system typically show the keyhole area, the weld pool, but also areas of solidified weld and areas of the blank sheet3. To automate image evaluation with respect to the recognition of aforementioned areas, we propose a convolutional neural network architecture to perform pixel-wise image classification4. In this paper, we investigate the influence of multiple hyper-parameters required for the network architecture in use, but also the amount of data that is necessary for high segmentation accuracies. In a second step, the outcome of the network is used to detect process deviations in laser welding image data using supervised machine learning. With the help of the Random Forest algorithm, assessment of the extracted process characteristics with respect to prediction accuracy takes place. Based on the information of the segmented image data, further investigations are carried out into the possibility of predicting individual process parameters such as laser power, welding speed and focus size simultaneously.