TY - CONF A1 - Yang, Fan A1 - Meng, Xiangmeng A1 - Putra, Stephen Nugraha A1 - Bachmann, Marcel A1 - Rethmeier, Michael T1 - Numerical studies of magnetohydrodynamic technology in suppressing process porosity during laser beam welding N2 - The magnetohydrodynamic (MHD) technology is employed to mitigate the porosity problem during partial penetration laser beam welding (LBW) of 10 mm thick aluminum alloy. The effectiveness and universal applicability of the MHD technology in reducing porosity during the LBW process are confirmed by a reduction in the porosity ratio of more than 89%. A transient 3D multi-physical model coupled with the MHD effect has been developed to investigate the suppression mechanism of process porosity. Due to the influence of Lorentz force, there is an obvious change in the weld pool length. This change widens the escaping channel of bubbles escaping from the weld pool. The application of an oscillating magnetic field changes the fluid flow pattern noticeably, whose influence on the formation of porosity defects is highly complicated and nonlinear. T2 - 13th CIRP Conference on Photonic Technologies CY - Nuremberg, Germany DA - 15.09.2024 KW - Laser beam welding KW - Aluminum alloy KW - Process Porosity KW - Porosity suppression KW - Magnetohydrodynamic technology PY - 2024 AN - OPUS4-61604 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Meng, Xiangmeng A1 - Putra, Stephen Nugraha A1 - Bachmann, Marcel A1 - Rethmeier, Michael T1 - Parametric study of the laser energy absorption in high-power laser beam welding N2 - Laser energy absorption on the keyhole wall is decisive for the thermodynamic behavior and the resultant weld properties in the high-power laser beam welding process. However, its highly transient nature on a microsecond scale makes the quantitative analysis challenging. In this paper, the influence of the relevant welding parameters on laser energy absorption is studied statistically by utilizing multiphysical modeling, in which the three-dimensional transient keyhole dynamics and thermo-fluid flow are calculated. A dynamic mesh adaption technique and a localized level-set-based ray-tracing method are employed to improve the model accuracy further. The results show that the focus position has a remarkable effect on the time-averaged laser absorption, and in contrast, the laser energy distribution regime is only slightly influenced by the welding speed in the studied parameter range (1.5–3.0 m/min). The absorption ratio of the laser energy on the keyhole front wall decreases with increasing welding speed and increases with upward-moving focus positions. The comparison between the calculated results and the experimental measurements ensures the validity of the proposed model. T2 - International Congress of Applications of Lasers & Electro-Optics 2024 CY - Los Angeles, CA, USA DA - 03.11.2024 KW - Laser beam welding KW - Laser energy absorption KW - Multiphysics modeling KW - Parametric study KW - Weld pool PY - 2024 SP - 1 EP - 8 AN - OPUS4-61629 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Bachmann, Marcel T1 - Reconstruction of the time-averaged keyhole geometry in laser beam welding with electromagnetic support N2 - In laser beam welding (LBW), the time-averaged keyhole shape provides statistical insights into the process compared to its transient geometry, offering a deeper understanding of the overall keyhole behaviour. However, capturing the time-averaged keyhole shape through experimental methods remains challenging. In this paper, a reconstruction algorithm for the time-averaged keyhole is developed and integrated into a three-dimensional transient multi-physical coupled numerical model. The algorithm can accurately capture the key characteristics of the keyhole, including its diameter and centroid. In addition, it can also successfully reproduce the experimentally observed phenomena of keyhole tailing. The overall shape of the keyhole appears smooth, without exhibiting obvious instability features. Furthermore, the time-averaged keyhole shape is compared under different magnetic flux densities when an external oscillating magnetic field is applied. The results indicate that the application of external magnetic fields does not fundamentally alter the overall keyhole shape. With increasing magnetic flux density, the trailing tail becomes progressively less pronounced and a noticeable increase in the curvature of the rear wall is observed. The standard deviation of the keyhole diameter can serve as an effective index for evaluating the keyhole instability. Keyhole stability in LBW of aluminium alloys is improved under the assistance of electromagnetic fields, and this stabilization is positively correlated with increasing magnetic flux density. T2 - 14th International Seminar Numerical Analysis of Weldability CY - Seggau, Austria DA - 21.09.2025 KW - Laser beam welding KW - Keyhole reconstruction KW - Electromagnetic weld pool support KW - Porosity defects KW - Keyhole stability PY - 2025 AN - OPUS4-64257 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Bachmann, Marcel 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 the 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, FL, USA DA - 12.10.2025 KW - Laser beam welding KW - Vapor plume formation KW - Weld pool KW - Keyhole dynamics KW - Numerical modeling PY - 2025 AN - OPUS4-64816 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Meng, Xiangmeng T1 - Prediction of weld pool and keyhole geometries in high-power laser beam welding through a physics-informed generative 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 (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. T2 - The 45th annual International Congress on Applications of Lasers & Electro-Optics CY - Orlando, FL, USA DA - 12.10.2025 KW - Laser beam welding KW - Generative artificial intelligence KW - Machine Learning KW - Numerical Simulation KW - Weld pool KW - Keyhole dynamics PY - 2025 AN - OPUS4-64812 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Gumenyuk, Andrey T1 - Strain distribution vs strain evolution during solidification cracking CTW test for laser beam welding of 1 mm austenitic stainless steels N2 - Laser welding is a widely established manufacturing process across many industrial sectors. However, solidification cracking and the weldability of materials have remained contentious issues for many years, particularly concerning the causes of hot crack formation. The local distribution of total strain was measured in close proximity to the solidification zone during laser welding of AISI 304 and AISI 310S stainless steels, using the Controlled Tensile Weldability (CTW) test. In this setup, 1 mm thick weld coupons were subjected to a defined external tensile load during welding. Mechanical loading parameters were varied by adjusting the strain rate and ultimate strain level to identify the critical conditions that lead to solidification crack formation along the weld seam centerline. Using Digital Image Correlation (DIC) and the optical flow method [1], we estimated the local strain distribution at the surface near the molten pool and tracked its evolution across several characteristic zones—before, during, and after the application of mechanical loading. The results revealed that solidification crack formation coincides with regions of high plastic deformation within a critical temperature range. Furthermore, we identified a clear relationship between strain rate and both crack initiation probability and maximum local strain. Importantly, neither strain rate nor maximum strain alone is sufficient to predict cracking; instead, their combined effect must be considered to accurately assess hot cracking susceptibility. T2 - AJP 2025 CY - Coimbra, Portugal DA - 16.10.2025 KW - Laser beam welding KW - Solidification cracking KW - Optical measurement PY - 2025 AN - OPUS4-64431 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Gumenyuk, Andrey T1 - Reducing Noise Impact on Strain Accuracy Measurement by Optical Flow and DIC for Laser Welding Applications N2 - In recent years, non-contact methods for in situ local strain measurement during welding processes have gained increasing importance. This trend is driven by advancements in both measurement technology—such as improved camera systems, illumination sources, and X-ray techniques—and in image processing algorithms for strain evaluation. Laser beam welding poses specific challenges for optical strain measurement due to various types of process-related emissions that impair measurement accuracy. In this study, two different algorithms were applied to analyze the local strain field in the solidification zone during laser welding of AISI 310S stainless steel: the inverse compositional Gauss-Newton algorithm for Digital Image Correlation (DIC) and the Lucas-Kanade method for optical flow analysis [1]. Video sequences were recorded under Controlled Tensile Weldability Test (CTW) conditions, in which the specimens were subjected to a defined external tensile load during welding. This setup consistently induced solidification cracking at the material surface, which could be observed in the video recordings. To enhance the robustness and accuracy of the strain evaluation, various noise reduction techniques were implemented. These included identification and mitigation of erroneous frames caused by process emissions and dynamic disturbances. The resulting strain distributions showed high repeatability across multiple experiments and were in good qualitative agreement with predictions from high-fidelity finite element simulations. [2]. T2 - AJP 2025 CY - Coimbra, Portugal DA - 16.10.2025 KW - Laser beam welding KW - Solidification cracking KW - Optical measurement PY - 2025 AN - OPUS4-64428 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - RPRT A1 - Bachmann, Marcel A1 - Rethmeier, Michael A1 - Meng, Xiangmeng T1 - Project title: Multi-physical simulation of the influence of an auxiliary magnetic field on the process porosity formation during high-power laser beam welding N2 - In this project, a multiphysically coupled numerical model will be developed to quantitatively describe porosity reduction in high-power laser beam welding of up to 10 mm thick AlMg3 using an oscillating magnetic field. The aim is to gain fundamental insights into the physical dependencies of the introduced electromagnetic forces on the melt pool behavior and the reduction of porosity. With the help of the numerical model, the transient, multi-coupled, three-dimensional problem of heat transfer, liquid flow, free surface deformation, and magnetic induction is to be solved, taking into account temperature-dependent material properties. The numerical modelling of the heat source will integrate all relevant physical mechanisms, for instance, multiple reflections of the laser radiation by an advanced ray tracing model, as well as local Fresnel absorption at the keyhole wall. This allows an analysis of the keyhole fluctuations, which have a dominant influence on the formation of process spores during deep penetration welding, based on physical principles. In addition, further physical factors such as the ablation pressure of the evaporating metal, the Laplace pressure, and Marangoni shear stresses are also to be integrated into the model. To evaluate the pore formation and reduction by means of the electromagnetic forces introduced in the molten pool, suitable models for describing the movement of the pores in the melt are to be developed. For the process pores, their movement can be implemented by tracking their surface under consideration of their internal pressure and temperature. With the help of the simulation model, all key factors for the formation of process pores during laser beam welding of the used aluminum alloy, as well as their avoidance, can be decoupled and analyzed. Accompanying welding tests are planned at BAM on a 20 kW fiber laser and a 16 kW disk laser. The magnetic flux density will be up to 500 mT at a maximum frequency of 5 kHz. The experimental results, in particular temperature measurements, weld cross sections, computer tomography, and X-ray examinations, will be used to verify the multiphysical model and its calibration. Moreover, the models will be validated and quantified by in situ high-speed imaging of the keyhole dynamics in a metal/quartz glass configuration with keyhole illumination by a diode laser coaxial to the processing laser. On the basis of the numerical and experimental results, the dependencies between applied magnetic field, melt pool behavior, and porosity formation will be revealed in this project. KW - Laser beam welding KW - Electromagnetic weld pool control KW - Numerical simulation KW - Process porosity PY - 2026 DO - https://doi.org/10.34657/27669 SP - 1 EP - 14 AN - OPUS4-65335 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF 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 (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. T2 - International Congress of Applications of Lasers & Electro-Optics 2025 CY - Orlando, USA DA - 12.10.2025 KW - Laser beam welding KW - Generative artificial intelligence KW - Machine learning KW - numerical simulation PY - 2025 SP - 1 EP - 10 AN - OPUS4-65075 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 - Bevilacqua, Tommaso A1 - Gumenyuk, Andrey A1 - Habibi, Niloufar A1 - Hartwig, Philipp A1 - Klawonn, Axel A1 - Lanser, Martin A1 - Rethmeier, Michael A1 - Scheunemann, Lisa A1 - Schröeder, Jöerg T1 - Large-scale thermo-mechanical simulation of laser beam welding using high-performance computing: A qualitative reproduction of experimental results N2 - Laser beam welding (LBW) is a non-contact joining technique that has gained significant importance in modern industrial manufacturing. One potential problem, however, is the formation of solidification cracks, which particularly affects alloys with a pronounced melting range. The aim of the present work is the development of computational methods and software tools to numerically simulate LBW. In order to obtain a sufficiently accurate solution, a large number of finite elements has to be used. Therefore, a highly parallel scalable solver framework, based on the software library PETSc, was used to solve this computationally challenging problem on a high-performance computing architecture. Finally, the experimental results and the numerical simulations are compared. They are found to be in good qualitative agreement, which confirms the validity of the numerical simulations and allows for a better interpretation of the experimentally observed strain distribution. KW - Laser beam welding KW - Termo-mechanical processes KW - Solidification cracking KW - High-performance computing KW - Domain decomposition methods PY - 2025 DO - https://doi.org/10.1016/j.rineng.2025.108827 SN - 2590-1230 SP - 1 EP - 33 PB - Elsevier B.V. AN - OPUS4-65290 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 - Phase-field simulation of the dendrite fragmentation by electromagnetic stirring in AA5754 aluminum alloy laser beam welding N2 - A phase-field model including magnetic field induced dendrite fragmentation was established and applied to the cases with different initial crystal nuclear positions for AA5754 aluminum alloy electromagnetic laser beam welding. Compare the calculated results that include dendrite fragmentation caused by the thermal electromagnetic Lorentz force with the results that consider only the thermal electromagnetic Lorentz force, without fragmentation, at the characteristic time instants. Both in the early and late stages, the small fragmentation at the dendrite tip promotes the number of higher-order branches and their growth, especially in the direction perpendicular to the solidification. The later stage fragmentation has the possibility of breaking one grain into several, which verifies the possibility of grain refinement caused by dendrite fragmentation. The fracture surface caused by fragmentation also makes more solid-liquid interfaces and their growth. In addition, the cases with different initial nuclear positions were compared. The grain growth in the low-temperature zone can be inhibited by the equiaxed grains' fragmentation at the high-temperature area (179.8 μm² and 14.7 % start at the center, 115.4 μm² and 9.4 % start at the high-temperature corner, 134.3 μm² and 10.9 % start at the low-temperature corner), which is another kind of grain refinement by the dendrite fragmentation. This kind of inhibition effect on grain growth in the low-temperature region will be enhanced with the increasing time interval between the two crystal nuclei’ appearance (179.8 μm² and 14.7 % when virtual grains appear at t = 4.3803 s and t = 4.3803 s, 134.3 μm² and 10.9 % at t = 4.0977 s and t = 3.9564 s, and 115.4 μm² and 9.4 % at t = 3.8151 s and t = 3.5325 s). KW - Laser beam welding KW - Electromagnetic KW - Aluminum alloys KW - Phase field method KW - Equiaxed grain KW - Dendrite fragmentation PY - 2026 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-656610 DO - https://doi.org/10.1016/j.cwe.2025.100014 SN - 3117-4159 VL - 35 IS - 1 SP - 1 EP - 12 PB - Elsevier B.V. AN - OPUS4-65661 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 - TY - JOUR A1 - Meng, Xiangmeng A1 - Bachmann, Marcel A1 - Yang, Fan A1 - Rethmeier, Michael T1 - Porosity prediction in laser beam welding with a multimodal physics-informed machine learning framework N2 - Laser beam welding (LBW) of metallic components is a knowledge‑intensive manufacturing process whose quality depends on the complex multi‑physics. However, its engineering application is often hindered by the occurrence of porosity defects. Achieving a thorough understanding and reliable prediction of porosity defects remains difficult because it demands robust representation and reasoning over nonlinear and hard‑to‑observe physical information. In this study, we propose an integrated multimodal physics-informed machine learning (PIML) framework with the help of multi-physical modelling and experimental data to predict the porosity defects in laser beam welding of aluminum alloys. The whole framework contains a multimodal PIML model for predicting the porosity ratio and an ML-based estimator for relevant physical information. By utilizing the scalar welding parameters and high-dimensional physical information (probability of keyhole collapses, cumulative existing time of collapses, and molten pool geometry) as inputs, the multimodal PIML model shows great superiority in predicting the porosity ratio, with a reduction of the mean square error by 45%, compared with the ML model trained only with welding parameters. The ML-based estimator constructed with an encoder‐decoder architecture can accurately reproduce the critical physical information within a timeframe of seconds. By integrating these two ML models, the proposed framework advances engineering informatics by offering a scalable, physics-knowledge‑centric solution for fast and accurate porosity prediction in LBW manufacturing. KW - Laser beam welding KW - Porosity defect KW - Physics-informed machine learning KW - Multimodal model KW - Simulation PY - 2026 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-657589 DO - https://doi.org/10.1016/j.aei.2026.104611 SN - 1474-0346 VL - 74 SP - 1 EP - 12 PB - Elsevier Ltd. AN - OPUS4-65758 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -