%0 Journal Article %1 jarwitz2025application %A Jarwitz, Michael %A Michalowski, Andreas %D 2025 %J Journal of Laser Applications %K myown welding laser peer Modeling %N 1 %R https://doi.org/10.2351/7.0001547 %T Application of a physics-informed hybrid model with additional output constraints for the prediction of the threshold of deep-penetration laser welding %U https://pubs.aip.org/lia/jla/article/37/1/012031/3333477/Application-of-a-physics-informed-hybrid-model %V 37 %X The quantitative prediction of process constraints, such as the threshold of deep-penetration laser welding, plays a crucial role for the fast and reliable development of robust process windows for laser manufacturing processes. A physics-informed hybrid model with additional output constraints for the prediction of the threshold of deep-penetration laser welding is presented. A “residual model” approach is used, where a machine learning model, employing Gaussian processes, is used to model and compensate for the deviations between experiments and a physical model, and output warping is used to incorporate additional output constraints into the model. The main benefits that result from applying such a model are found to be (1) an increased prediction accuracy compared to only using the physical model, leading to a reduction of the mean relative error of about 76%; (2) a reduction of the number of required training data compared to only using a blackbox machine learning model; (3) an increased prediction accuracy compared to only using a black-box machine learning model; (4) and an increased compliance with physical boundary conditions by applying the additional output constraints.

@article{jarwitz2025application, abstract = {The quantitative prediction of process constraints, such as the threshold of deep-penetration laser welding, plays a crucial role for the fast and reliable development of robust process windows for laser manufacturing processes. A physics-informed hybrid model with additional output constraints for the prediction of the threshold of deep-penetration laser welding is presented. A “residual model” approach is used, where a machine learning model, employing Gaussian processes, is used to model and compensate for the deviations between experiments and a physical model, and output warping is used to incorporate additional output constraints into the model. The main benefits that result from applying such a model are found to be (1) an increased prediction accuracy compared to only using the physical model, leading to a reduction of the mean relative error of about 76%; (2) a reduction of the number of required training data compared to only using a blackbox machine learning model; (3) an increased prediction accuracy compared to only using a black-box machine learning model; (4) and an increased compliance with physical boundary conditions by applying the additional output constraints.}, added-at = {2025-02-03T17:36:58.000+0100}, author = {Jarwitz, Michael and Michalowski, Andreas}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2faa082ad04b2c7327f3eaab09bea7208/ifsw}, doi = {https://doi.org/10.2351/7.0001547}, interhash = {95a19c8b28834f8d37b2890cbe087920}, intrahash = {faa082ad04b2c7327f3eaab09bea7208}, journal = {Journal of Laser Applications}, keywords = {myown welding laser peer Modeling}, month = feb, number = 1, timestamp = {2025-02-03T17:36:58.000+0100}, title = {Application of a physics-informed hybrid model with additional output constraints for the prediction of the threshold of deep-penetration laser welding}, url = {https://pubs.aip.org/lia/jla/article/37/1/012031/3333477/Application-of-a-physics-informed-hybrid-model}, volume = 37, year = 2025 }