Filtern
Dokumenttyp
Sprache
- Englisch (3)
Schlagworte
- Laser beam welding (3)
- Generative artificial intelligence (2)
- Machine learning (2)
- Keyhole dynamics (1)
- Numerical modeling (1)
- Numerical simulation (1)
- Thermo-capillary convection (1)
- Turbulence (1)
- Weld pool (1)
- Weld pool shape (1)
Organisationseinheit der BAM
The weld pool and keyhole geometries are critical characteristics in evaluating the stability of the high-power laser beam welding (LBW) process and determining the resultant weld quality. However, obtaining these data through experimental or numerical methods remains challenging due to the difficulties in experimental measurements and the high computational demands of numerical modelling. This paper presents a physics-informed generative approach for predicting weld pool and keyhole geometries in the LBW process. With the help of a well experimentally validated numerical model considering the underlying physics in the LBW, the geometries of the weld pool and keyhole under various welding conditions are calculated, serving as the dataset of the generative model. A Conditional Variational Autoencoder (CVAE) model is employed to generate realistic 2D weld pool and keyhole geometries from the welding parameters. We utilize a β-VAE model with the Evidence Lower Bound (ELBO) loss function and include Kullback-Leibler divergence annealing to better optimize model performance and stability during training. The generated results show a good agreement with the ground truth from the numerical simulation. The proposed approach exhibits the potential of physics-informed generative models for a rapid and accurate prediction of the weld pool geometries across a diverse range of process parameters, offering a computationally efficient alternative to full numerical simulations for process optimization and control in laser beam welding processes.
The weld pool and keyhole geometries are critical characteristics in evaluating the stability of the high-power laser beam welding (LBW) process and determining the resultant weld quality. However, obtaining these data through experimental or numerical methods remains challenging due to the difficulties in experimental measurements and the high computational demands of numerical modelling. This paper presents a physics-informed generative approach for predicting weld pool and keyhole geometries in the LBW process. With the help of a well experimentally validated numerical model considering the underlying physics in the LBW, the geometries of the weld pool and keyhole under various welding conditions are calculated, serving as the dataset of the generative model. A conditional variational autoencoder model is employed to generate realistic 2D weld pool and keyhole geometries from the welding parameters. We utilize a β-variational autoencoder model with the evidence lower bound loss function and include Kullback–Leibler divergence annealing to better optimize model performance and stability during training. The generated results show a good agreement with the ground truth from the numerical simulation. The proposed approach exhibits the potential of physics-informed generative models for a rapid and accurate prediction of the weld pool geometries across a diverse range of process parameters, offering a computationally efficient alternative to full numerical simulations for process optimization and control in laser beam welding processes.
A three-dimensional numerical model was developed to accurately predict the steady-state weld pool shape in full penetration laser beam welding. The model accounts for the coupling between the heat transfer and the fluid dynamics by considering the effects of solid/liquid phase transition, thermo-capillary convection, natural convection, and phase-specific and temperature-dependent material properties up to the evaporation temperature. A fixed right circular cone was utilized as a keyhole geometry to consider the heat absorbed from the laser beam. The model was used to analyze the influence of the thermodynamic activity of solutes and turbulence on the weld pool shape. A mesh sensitivity analysis was performed on a hybrid mesh combining hexahedral and tetrahedral elements. For the case of full penetration laser beam welding of 8 mm thick unalloyed steel sheets, the dependence of the weld pool shape on the surface-active element sulfur was found to be negligible. The analysis of the results showed that a laminar formulation is sufficient for accurately predicting the weld pool shape since the turbulence has a minor impact on the flow dynamics in the weld pool. The validity of the numerical results was backed up by experimental measurements and observations, including weld pool length, local temperature history, and a range of metallographic crosssections.
