TY - JOUR A1 - Diller, Johannes A1 - Siebert, Ludwig A1 - Winkler, Michael A1 - Siebert, Dorina A1 - Blankenhagen, Jakob A1 - Wenzler, David A1 - Radlbeck, Christina A1 - Mensinger, Martin T1 - An integrated approach for detecting and classifying pores and surface topology for fatigue assessment 316L manufactured by powder bed fusion of metals using a laser beam using μ$$ \mu $$CT and machine learning algorithms N2 - AbstractThis research aims to detect and analyze critical internal and surface defects in metal components manufactured by powder bed fusion of metals using a laser beam (PBF‐LB/M). The aim is to assess their impact on the fatigue behavior. Therefore, a combination of methods, including image processing of micro‐computed tomography (CT) scans, fatigue testing, and machine learning, was applied. A workflow was established to contribute to the nondestructive assessment of component quality and mechanical properties. Additionally, this study illustrates the application of machine learning to address a classification problem, specifically the categorization of pores into gas pores and lack of fusion pores. Although it was shown that internal defects exhibited a reduced impact on fatigue behavior compared with surface defects, it was noted that surface defects exert a higher influence on fatigue behavior. A machine learning algorithm was developed to predict the fatigue life using surface defect features as input parameters. KW - Fatigue KW - Machine learning KW - Micro-computed tomography KW - Powder bed fusion of metals using a laser beam KW - Quality assurance PY - 2024 DO - https://doi.org/10.1111/ffe.14375 SN - 8756-758X SP - 1 EP - 16 PB - John Wiley & Sons Ltd. AN - OPUS4-60593 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Oster, Simon A1 - Breese, Philipp Peter A1 - Ulbricht, Alexander A1 - Mohr, Gunther A1 - Altenburg, Simon T1 - A deep learning framework for defect prediction based on thermographic in-situmonitoring in laser powder bed fusion N2 - The prediction of porosity is a crucial task for metal based additive manufacturing techniques such as laser powder bed fusion. Short wave infrared thermography as an in-situ monitoring tool enables the measurement of the surface radiosity during the laser exposure. Based on the thermogram data, the thermal history of the component can be reconstructed which is closely related to the resulting mechanical properties and to the formation of porosity in the part. In this study, we present a novel framework for the local prediction of porosity based on extracted features from thermogram data. The framework consists of a data pre-processing workflow and a supervised deep learning classifier architecture. The data pre-processing workflow generates samples from thermogram feature data by including feature information from multiple subsequent layers. Thereby, the prediction of the occurrence of complex process phenomena such as keyhole pores is enabled. A custom convolutional neural network model is used for classification. Themodel is trained and tested on a dataset from thermographic in-situ monitoring of the manufacturing of an AISI 316L stainless steel test component. The impact of the pre-processing parameters and the local void distribution on the classification performance is studied in detail. The presented model achieves an accuracy of 0.96 and an f1-Score of 0.86 for predicting keyhole porosity in small sub-volumes with a dimension of (700 × 700 × 50) μm3. Furthermore, we show that pre-processing parameters such as the porosity threshold for sample labeling and the number of included subsequent layers are influential for the model performance. Moreover, the model prediction is shown to be sensitive to local porosity changes although it is trained on binary labeled data that disregards the actual sample porosity. KW - Laser Powder Bed Fusion (PBF-LB/M, L-PBF) KW - Selective Laser Melting (SLM) KW - SWIR thermography KW - Online monitoring KW - Flaw detection KW - Machine learning KW - Convolutional neural networks (CNN) PY - 2023 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-575148 DO - https://doi.org/10.1007/s10845-023-02117-0 SN - 0956-5515 SP - 1 EP - 20 PB - Springer AN - OPUS4-57514 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Meng, Xiangmeng T1 - Prediction of porosity formation in high power laser beam welding using physics informed machine learning framework N2 - The applications of the high-power laser beam welding process are often hindered by the occurrence of the porosity defect. However, an accurate prediction and an insight of the porosity formation are still challenging due to the highly nonlinear physics involved in the dynamic weld pool and keyhole behaviours. In this paper, the effects of relevant physical variables related to the porosity defect are evaluated by utilizing mechanistic modelling and experimental data within a physics-informed machine learning (PIML) framework. With a proper selection of the physical variables (features) in the aspects of keyhole stability, liquid metal flow and weld pool geometry, which correspondingly describes the bubble formation, bubble movement and bubble capture by the solidification front, the PIML shows great superiority in predicting the porosity ratio in the laser welding of aluminium in comparison with conventional ML model using welding parameters. The Shapley Additive Explanations analysis is employed to provide a hierarchical importance of the variables on the defect formation. T2 - 77th IIW Annual Assembly and International Conference CY - Rhodes, Greece DA - 07.07.2024 KW - Laser beam welding KW - Machine learning KW - Porosity KW - Modelling PY - 2024 AN - OPUS4-61610 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 -