TY - JOUR A1 - Meng, Xiangmeng A1 - Bachmann, Marcel A1 - Yang, Fan A1 - Rethmeier, Michael T1 - Toward prediction and insight of porosity formation in laser welding: A physics-informed deep learning framework N2 - The laser welding process is an important manufacturing technology for metallic materials. However, its application is often hindered by the occurrence of porosity defects. By far, an accurate prediction of the porosity defects and an insight into its formation mechanism are still challenging due to the highly nonlinear physics involved. In this paper, we propose a physics-informed deep learning (PIDL) framework by utilizing mechanistic modeling and experimental data to predict the porosity level during laser beam welding of aluminum alloys. With a proper selection of the physical variables (features) concerning the solidification, liquid metal flow, keyhole stability, and weld pool geometry, the PIDL model shows great superiority in predicting the porosity ratio, with a reduction of mean square error by 41 %, in comparison with the conventional DL model trained with welding parameters. Furthermore, the selected variables are fused into dimensionless features with explicit physical meanings to improve the interpretability and extendibility of the PIDL model. Based on a well-trained PIDL model, the hierarchical importance of the physical variables/procedures on the porosity formation is for the first time revealed with the help of the Shapley Additive Explanations analysis. The keyhole ratio is identified as the most influential factor in the porosity formation, followed by the downward flow-driven drag force, which offers a valuable guideline for process optimization and porosity minimization. KW - Laser beam welding KW - Physics-informed deep learning KW - Porosity prediction KW - Feature fusion KW - Hierarchical importance PY - 2025 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-624708 DO - https://doi.org/10.1016/j.actamat.2025.120740 VL - 286 SP - 1 EP - 13 PB - Elsevier B.V. AN - OPUS4-62470 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Yang, Chunliang A1 - Yang, Fan A1 - Meng, Xiangmeng A1 - Putra, Stephen Nugraha A1 - Bachmann, Marcel A1 - Rethmeier, Michael T1 - Multi-refining effects of an AC electromagnetic field on the microstructure in AA5754 laser beam welding N2 - Fine-grain structure is beneficial to the mechanical properties of the joint. Different kinds of grain and sub-grain structures refined by magnetic field during laser beam welding of AA5754 aluminum alloy are analyzed in this manuscript, and the influences of different magnetic field parameters (magnetic flux density and frequency) in these refining effects are also studied. Using the scanning electron microscope (SEM), the sub-grain structure near the fusion line was obtained, and it was found that the branching promotion and branches refinement can be achieved by the magnetic field. The branches become finer with the magnetic flux density or frequency increases, and this effect is stronger in the dendritic region than in the equiaxed region. The results of electron backscatter diffraction (EBSD) in the equiaxed region show that a high-frequency magnetic field can greatly reduce the average grain size, while a low-frequency one has little effect. A phenomenological nucleation model based on dendrite fragmentation theory was established, and it was introduced into the phase field model to analyze the equiaxed grains evolution process. In addition, another refinement mechanism was also observed. The periodic solidification pattern caused by the unstable solidification in the molten pool can refine the grains, and the magnetic field promotes this kind of grain refinement by promoting the solidification period. KW - Laser beam welding KW - Magnetic field KW - Aluminum alloy KW - Crystal branch development KW - Periodic solidification pattern KW - Grain refinement PY - 2025 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-637222 DO - https://doi.org/10.1016/j.ijheatmasstransfer.2025.127509 SN - 0017-9310 VL - 252 SP - 1 EP - 16 PB - Elsevier Ltd. AN - OPUS4-63722 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Fritzsche, André A1 - Hilgenberg, Kai A1 - Rethmeier, Michael T1 - Influence of welding parameters on electromagnetic supported degassing of die-casted and wrought aluminum N2 - Laser beam welding of aluminum die casting is challenging. A large quantity of gases (in particular, hydrogen) is absorbed by aluminum during the die-cast manufacturing process and is contained in the base material in solved or bound form. After remelting by the laser, the gases are released and are present in the melt as pores. Many of these metallurgic pores remain in the weld seam as a result of the high solidification velocities. The natural (Archimedean) buoyancy is not sufficient to remove the pores from the weld pool, leading to process instabilities and poor mechanical properties of the weld. Therefore, an electromagnetic (EM) system is used to apply an additional buoyancy component to the pores. The physical mechanism is based on the generation of Lorentz forces, whereby an electromagnetic pressure is introduced into the weld pool. The EM system exploits the difference in electrical conductivity between poorly conducting pores (inclusions) and the comparatively better conducting aluminum melt to increase the resulting buoyancy velocity of the pores. Within the present study, the electromagnetic supported degassing is investigated in dependence on the laser beam power, welding velocity, and electromagnetic flux density. By means of a design of experiments, a systematic variation of these parameters is carried out for partial penetration laser beam welding of 6mm thick sheets of wrought aluminum alloy AlMg3 and die-cast aluminum alloy AlSi12(Fe), where the wrought alloy serves as a reference. The proportion of pores in the weld seams is determined using x-ray images, computed tomography images, and cross-sectional images. The results prove a significant reduction of the porosity up to 70% for both materials as a function of the magnetic flux density. T2 - ICALEO 2019 CY - Orlando, FL, USA DA - 07.10.2019 KW - Laser beam welding KW - Electromagnetic supported degassing KW - Die-casted aluminum PY - 2020 DO - https://doi.org/10.2351/7.0000064 VL - 32 IS - 2 SP - 022031-1 EP - 022031-8 PB - AIP Publishing AN - OPUS4-50728 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Meng, Xiangmeng A1 - Artinov, Antoni A1 - Bachmann, Marcel A1 - Rethmeier, Michael T1 - Theoretical study of influence of electromagnetic stirring on transport phenomena in wire feed laser beam welding N2 - The additional element from the filler wire in the laser beam welding is usually distributed inhomogeneously in the final weld due to the high solidification rate of weld pool. It has been found that the electromagnetic stirring produced by an external oscillating magnetic field can enhance the material mixing in the weld pool to achieve a more uniform element distribution. However, the magnetic field has a highly nonlinear and multicoupled interaction with the weld pool behavior, which makes the quantitative explanation of the physical mechanism difficult. In this study, the effect of electromagnetic stirring on the transport phenomena in the wire feed laser beam welding is investigated by a numerical modeling. A 3D transient multiphysical model considering the magnetohydrodynamics, heat transfer, fluid flow, keyhole dynamics, and element transport is developed. The multiple reflections and the Fresnel absorption of the laser on the keyhole wall are calculated using the ray tracing method. The numerical results show that a Lorentz force produced by the oscillating magnetic field and its induced eddy current gives significant influence on the transport phenomena in the molten pool. The forward and downward flow is enhanced by the electromagnetic stirring, which homogenizes the distribution of the additional elements from a nickel-based filler wire in a steel weld pool. The numerical results show a good agreement with the high-speed images of the molten pool, the fusion line from the optical micrograph, and the element distribution from the energy dispersive x-ray spectroscopy. This work provides a physical base for the electromagnetic-controlled laser beam welding and some guidance for the selection of electromagnetic parameters. KW - Magnetohydrodynamics KW - Molten pool dynamics KW - Element transport KW - Laser beam welding PY - 2020 DO - https://doi.org/10.2351/7.0000069 VL - 32 IS - 2 SP - 022026-1 EP - 022026-9 AN - OPUS4-50874 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Üstündag, Ömer A1 - Bakir, Nasim A1 - Gumenyuk, Andrey A1 - Rethmeier, Michael T1 - Influence of oscillating magnetic field on the keyhole stability in deep penetration laser beam welding N2 - The stability of the keyhole decreases for deep penetrated high-power laser beam welding. The keyhole tends to collapse with increasing laser power and e.g. keyhole induced porosity can occur. This study deals with the observation of the keyhole during high-power laser beam welding in partial penetration mode by means of a high-speed camera. A butt configuration of 25 mm thick structural steel and transparent quartz glass was used for the experiments. An oscillating magnetic field was applied perpendicular to the welding direction on the root side of the steel plate. The keyhole was highlighted with a coaxial diode laser. It was ascertained that the stability of the keyhole and the weld penetration depth were increased by applying an oscillating magnetic field with an oscillating frequency of 1.2 kHz and a magnetic flux density of 50 mT. KW - Magnetic field KW - Laser beam welding KW - Keyhole stability PY - 2021 DO - https://doi.org/10.1016/j.optlastec.2020.106715 SN - 0030-3992 VL - 135 SP - 106715 PB - Elsevier Ltd. AN - OPUS4-52007 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Savitsky, Viktor A1 - Schmies, Lennart A1 - Gumenyuk, Andrey A1 - Rethmeier, Michael T1 - Comparative performance of DIC and optical flow algorithms for displacement and strain analysis in laser beam welding N2 - The measurement of strain and displacement in the context of the welding process represents a significant challenge. Optical methods, such as digital image correlation (DIC) or optical flow algorithms, have demonstrated their efficacy in robust and reliable data acquisition in harsh environments, including those encountered in welding processes. Concurrently, a trade-off between the accuracy of the measurement and the computational resources required for the associated calculations must be evaluated on a case-by-case basis. The application of filters to initial images represents a technique that serves to enhance the quality and accuracy of the strain and displacement prediction. In the present study, the estimated error of two algorithms, namely the Lucas-Kanade (LK) and the inverse compositional Gauss-Newton (IC-GN), is compared on the basis of both synthetic and real welding images. The displacement field is evaluated for different zones in the laser weld seam with varying contrast performance. Based on the aforementioned results, a strain calculation was conducted for both methods, which yielded comparable results for the LK and IC-GN algorithms. KW - Laser speckle KW - DIC KW - Optical flow KW - Error estimation KW - Strain measurement KW - Laser beam welding PY - 2025 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-625919 DO - https://doi.org/10.1016/j.optlaseng.2025.108870 SN - 1873-0302 VL - 187 SP - 1 EP - 15 PB - Elsevier Ltd. AN - OPUS4-62591 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Rethmeier, Michael A1 - Gumenyuk, Andrey A1 - Bachmann, Marcel T1 - High-power laser beam welding for thick section steels – new perspectives using electromagnetic systems N2 - In recent years, it was shown that the introduction of additional oscillating and permanent magnetic fields to laser beam and laser-arc hybrid welding can bring several beneficial effects. Examples are a contactless weld pool support for metals of high thickness suffering from severe drop-out when being welded conventionally or an enhanced stirring to improve the mixing of added filler material in the depth of the weld pool to guarantee homogeneous resulting mechanical properties of the weld. The latest research results show the applicability to various metal types over a wide range of thicknesses and welding conditions. The observations made were demonstrated in numerous experimental studies and a deep understanding of the interaction of the underlying physical mechanisms was extracted from numerical calculations. KW - Laser beam welding KW - Numerical simulations KW - Electromagnetic support PY - 2021 DO - https://doi.org/10.1080/13621718.2021.1999763 VL - 27 IS - 1 SP - 43 EP - 51 PB - Taylor & Francis Group AN - OPUS4-53970 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Huo, Wenjie A1 - Schmies, Lennart A1 - Gumenyuk, Andrey A1 - Rethmeier, Michael A1 - Wolter, Katinka T1 - Prediction of mean strain from laser beam welding images and detection of defects via strain curves based on machine learning N2 - With the advancement of machine learning, many predictions and measurements in visual tasks can be achieved by convolutional neural networks (CNNs). Solidification hot cracking is a significant defect in laser beam welding, commonly encountered in practical applications. Existing theories indicate that the formation of cracks is closely related to strain accumulation near the solidification front. In this paper, we first leverage supervised Regression networks to design CNNs that achieve real-time average strain estimation for each frame in the collected welding videos. Two different architectures are proposed and compared: the first model stacks two frames at a set interval and feeds them into the network, while the second model extracts image features individually and predicts the results by calculating the correlation between them. Each network has its own advantages in Terms of computational efficiency and accuracy. Finally, we further train a multilayer perceptron (MLP) classification model that can detect the occurrence of cracks based on the predicted strain behaviors. KW - Laser beam welding KW - Mean strain prediction KW - Solidification cracking detection Convolutional neural networks KW - Convolutional neural networks PY - 2025 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-644495 DO - https://doi.org/10.1016/j.optlastec.2025.113975 SN - 0030-3992 VL - 192, Part F SP - 1 EP - 8 PB - Elsevier Ltd. AN - OPUS4-64449 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Bachmann, Marcel A1 - Putra, Stephen Nugraha A1 - Yang, Fan A1 - Meng, Xiangmeng A1 - Pusbatzkies, Pablo A1 - Rethmeier, Michael T1 - Elucidation of the laser beam energy attenuation by the vapor plume formation during high-power laser beam welding N2 - In high-power laser beam welding, a common phenomenon is the formation of a keyhole caused by the rapid evaporation of the material. Under atmospheric pressure, this evaporation generates a vapor plume that interacts with the laser beam, leading to energy attenuation and scattering of the laser radiation along its path. These interactions affect the stability of the process and the overall weld quality. This study investigates the influence of the vapor plume on the weld pool and keyhole dynamics during high-power laser beam welding of AlMg3 aluminum alloy through experimental and numerical approaches. The primary goal is to identify key vapor plume characteristics, particularly its length fluctuations, and to improve the accuracy of the numerical models. To achieve this, an algorithm was developed for the automated measurement of the vapor plume length using high-speed imaging and advanced data processing techniques. The measured plume length is then used to estimate additional vapor heating and laser energy attenuation using the Beer–Lambert law. A refined numerical CFD model, incorporating 3D transient heat transfer, fluid flow, and ray tracing, was developed to evaluate the vapor plume’s impact. Results show that already the time-averaged plume length effectively captures its transient influence and aligns well with experimental weld seam geometries. Additionally, energy scattering and absorption caused by the vapor plume led to a wider weld pool at the top surface. The study also shows an increased percentage of keyhole collapses due to the reduced laser power absorption at the keyhole bottom, further highlighting the importance of accurately modeling vapor plume effects. T2 - International Congress of Applications of Lasers & Electro-Optics 2025 CY - Orlando, USA DA - 12.10.2025 KW - Laser beam welding KW - Vapor plume formation KW - Weld pool KW - Keyhole dynamics KW - Numerical modeling PY - 2026 DO - https://doi.org/10.2351/7.0001863 SN - 1938-1387 IS - 38 SP - 012001-1 EP - 012001-9 PB - Laser Institute of America AN - OPUS4-64949 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Meng, Xiangmeng A1 - Bachmann, Marcel A1 - Kising, Pascal A1 - Yang, Fan A1 - Rethmeier, Michael T1 - Prediction of weld pool and keyhole geometries in high-power laser beam welding through a physics-informed generative artificial intelligence approach N2 - 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. KW - Laser beam welding KW - Generative artificial intelligence KW - Machine learning KW - Numerical simulation KW - Weld pool KW - Keyhole dynamics PY - 2026 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-656621 DO - https://doi.org/10.2351/7.0001862 SN - 1042-346X VL - 38 IS - 1 SP - 1 EP - 8 PB - Laser Institute of America AN - OPUS4-65662 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -