TY - CONF A1 - Breese, Philipp Peter T1 - Comparison of NIR and SWIR thermography for defect detection in laser powder bed fusion N2 - Since laser powder bed fusion (PBF-LB/M) is prone to the formation of defects during the building process, a fundamental requirement for widespread application is to find ways to assure safety and reliability of the additively manufactured parts. A possible solution for this problem lies in the usage of in-situ thermographic monitoring for defect detection. In this contribution we investigate possibilities and limitations of the VIS/NIR wavelength range for defect detection. A VIS/NIR camera can be based on conventional silicon-based sensors which typically have much higher spatial and temporal resolution in the same price range but are more limited in the detectable temperature range than infrared sensors designed for longer wavelengths. To investigate the influence, we compared the thermographic signatures during the creation of artificially provoked defects by local parameter variations in test specimens made of a nickel alloy (UNS N07208) for two different wavelength ranges (~980 nm and ~1600 nm). T2 - 13th CIRP Conference on Photonic Technologies - LANE 2024 CY - Fürth, Germany DA - 15.09.2024 KW - Additive Manufacturing KW - Laser Powder Bed Fusion KW - Nondestructive Testing KW - Defect Detection KW - Thermography PY - 2024 AN - OPUS4-61285 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Becker, Tina A1 - Breese, Philipp Peter A1 - Metz, Christian A1 - Altenburg, Simon T1 - In-situ monitoring for PBF-LB/M processes: Does multispectral optical tomography add value in recognizing process deviations? N2 - Laser powder bed fusion of metallic components (PBF-LB/M) is gaining acceptance in industry. However, the high costs and lengthy qualification processes required for printed components create the need for more effective in-situ monitoring and testing methods. This article proposes multispectral Optical Tomography (OT) as a new approach for monitoring the PBF-LB/M process. Compared to other methods, OT is a low-cost process monitoring method that uses long-time exposure imaging to observe the build process. However, it lacks time resolution compared to expensive thermographic sensor systems. Monochromatic OT (1C-OT) is already commercially available and observes the building process layer-wise using a single wavelength window in the NIR range. Multispectral OT (nC-OT) utilizes a similar setup but can measure multiple wavelength ranges per location simultaneously. By comparing the classical 1C-OT and nC-OT approaches, this article examines the advantages of nC-OT (two channel OT and RGB-OT) in reducing the false positive rate for process deviations and approximating maximum temperatures for a better comparison between different build processes and materials. This could ultimately reduce costs and time for part qualification. The main goal of this contribution is to assess the advantages of nC-OT compared to 1C-OT for in-situ process monitoring of PBF-LB/M. T2 - Nolamp 2023 CY - Turku, Finland DA - 22.08.2023 KW - Thermography KW - Process Monitoring KW - Additive manufacturing KW - BPF-LB/M KW - In-situ PY - 2023 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-592498 DO - https://doi.org/10.1088/1757-899X/1296/1/012008 VL - 1296 SP - 1 EP - 11 PB - IOP Publishing CY - Bristol, UK AN - OPUS4-59249 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Oster, Simon A1 - Scheuschner, Nils A1 - Chand, Keerthana A1 - Altenburg, Simon A1 - Gerlach, G. T1 - Potentials and challenges of deep-learning-assisted porosity prediction based on thermographic in-situ monitoring in laser powder bed fusion N2 - Laser powder bed fusion is one of the most promising additive manufacturing techniques for printing complex-shaped metal components. However, the formation of subsurface porosity poses a significant risk to the service lifetime of the printed parts. In-situ monitoring offers the possibility to detect porosity already during manufacturing. Thereby, process feedback control or a manual process interruption to cut financial losses is enabled. Short-wave infrared thermography can monitor the thermal history of manufactured parts which is closely connected to the probability of porosity formation. Artificial intelligence methods are increasingly used for porosity prediction from the obtained large amounts of complex monitoring data. In this study, we aim to identify the potential and the challenges of deep-learning-assisted porosity prediction based on thermographic in-situ monitoring. Therefore, the porosity prediction task is studied in detail using an exemplary dataset from the manufacturing of two Haynes282 cuboid components. Our trained 1D convolutional neural network model shows high performance (R² score of 0.90) for the prediction of local porosity in discrete sub-volumes with dimensions of (700 x 700 x 40) μm³. It could be demonstrated that the regressor correctly predicts layer-wise porosity changes but presumably has limited capability to predict differences in local porosity. Furthermore, there is a need to study the significance of the used thermogram feature inputs to streamline the model and to adjust the monitoring hardware. Moreover, we identified multiple sources of data uncertainty resulting from the in-situ monitoring setup, the registration with the ground truth X-ray-computed tomography data and the used pre-processing workflow that might influence the model’s performance detrimentally. T2 - XXXVII. Messtechnisches Symposium 2023 CY - Freiburg, Germany DA - 27.09.2023 KW - Porosity prediction KW - Defect detection KW - Laser powder bed fusion (PBF-LB/M, L-PBF) KW - Selective laser melting KW - Thermography KW - Machine learning PY - 2023 DO - https://doi.org/10.1515/teme-2023-0062 SN - 0171-8096 SN - 2196-7113 VL - 90 SP - 85 EP - 96 PB - De Gruyter CY - Berlin AN - OPUS4-58366 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Oster, Simon T1 - Potentials and challenges of deep-learning-assisted porosity prediction based on thermographic in-situ monitoring in PBF-LB/M N2 - Laser powder bed fusion is one of the most promising additive manufacturing techniques for printing complex-shaped metal components. However, the formation of subsurface porosity poses a significant risk to the service lifetime of the printed parts. In-situ monitoring offers the possibility to detect porosity already during manufacturing. Thereby, process feedback control or a manual process interruption to cut financial losses is enabled. Short-wave infrared thermography can monitor the thermal history of manufactured parts which is closely connected to the probability of porosity formation. Artificial intelligence methods are increasingly used for porosity prediction from the obtained large amounts of complex monitoring data. In this study, we aim to identify the potential and the challenges of deep-learning-assisted porosity prediction based on thermographic in-situ monitoring. Therefore, the porosity prediction task is studied in detail using an exemplary dataset from the manufacturing of two Haynes282 cuboid components. Our trained 1D convolutional neural network model shows high performance (R2 score of 0.90) for the prediction of local porosity in discrete sub-volumes with dimensions of (700 x 700 x 40) μm³. It could be demonstrated that the regressor correctly predicts layer-wise porosity changes but presumably has limited capability to predict differences in local porosity. Furthermore, there is a need to study the significance of the used thermogram feature inputs to streamline the model and to adjust the monitoring hardware. Moreover, we identified multiple sources of data uncertainty resulting from the in-situ monitoring setup, the registration with the ground truth X-ray-computed tomography data and the used pre-processing workflow that might influence the model’s performance detrimentally. T2 - XXXVII. Messtechnisches Symposium 2023 CY - Freiburg im Breisgau, Germany DA - 27.09.2023 KW - Porosity prediction KW - Defect detection KW - Laser Powder Bed Fusion (PBF-LB/M, L-PBF) KW - Selective Laser Melting KW - Thermography KW - Machine Learning PY - 2023 AN - OPUS4-59192 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Oster, Simon T1 - Machine Learning based defect detection in Laser Powder Bed Fusion utilizing thermographic feature data N2 - The formation of irregularities such as keyhole porosity pose a major challenge to the manufacturing of metal parts by laser powder bed fusion (PBF-LB/M). In-situ thermography as a process monitoring technique shows promising potential in this manner since it is able to extract the thermal history of the part which is closely related to the formation of irregularities. In this study, we investigate the utilization of machine learning algorithms to detect keyhole porosity on the base of thermographic features. Here, as a referential technique, x-ray micro computed tomography is utilized to determine the part's porosity. An enhanced preprocessing workflow inspired by the physics of the keyhole irregularity formation is presented in combination with a customized model architecture. Furthermore, experiments were performed to clarify the role of important parameters of the preprocessing workflow for the task of defect detection . Based on the results, future demands on irregularity prediction in PBF-LB/M are derived. T2 - International Conference on NDE 4.0 CY - Berlin, Germany DA - 24.10.2022 KW - Laser Powder Bed Fusion KW - Thermography KW - In-situ Monitoring KW - Convolutional Neural Networks PY - 2022 AN - OPUS4-56332 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Breese, Philipp Peter A1 - Becker, Tina A1 - Oster, Simon A1 - Metz, C. A1 - Altenburg, Simon T1 - In-situ defect detection for laser powder bed fusion with active laser thermography N2 - Defects are still common in metal components built with Additive Manufacturing (AM). Process monitoring methods for laser powder bed fusion (PBF-LB/M) are used in industry, but relationships between monitoring data and defect formation are not fully understood yet. Additionally, defects and deformations may develop with a time delay to the laser energy input. Thus, currently, the component quality is only determinable after the finished process. Here, active laser thermography, a nondestructive testing method, is adapted to PBF-LB/M, using the defocused process laser as heat source. The testing can be performed layer by layer throughout the manufacturing process. We study our proposed testing method along experiments carried out on a custom research PBF-LB/M machine using infrared (IR) cameras. Our work enables a shift from post-process testing of components towards in-situ testing during the AM process. The actual component quality is evaluated in the process chamber and defects can be detected between layers. T2 - 2023 International Solid Freeform Fabrication Symposium CY - Austin, TX, USA DA - 14.08.2023 KW - Additive Manufacturing KW - Laser Powder Bed Fusion KW - Nondestructive Testing KW - Thermography KW - Defect Detection PY - 2023 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-606288 DO - https://doi.org/10.26153/tsw/51096 SP - 1978 EP - 1989 PB - University of Texas at Austin CY - Austin, TX, USA AN - OPUS4-60628 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Oster, Simon T1 - A comparison of machine learning approaches for porosity prediction in PBF-LB/M based on thermography N2 - Metal-based additive manufacturing processes are increasingly used in industry to produce complex-shaped components. In this regard, the laser-based Powder Bed Fusion process (PBF-LB/M) is one of the key technologies due to its capability to produce components in high spatial accuracy. The formation of porosity during manufacturing poses a serious risk to the safety of the printed parts. For quality assessment, in-situ monitoring technologies such as thermography can be used to capture the thermal history during production. It was shown that discontinuities within the thermal history can be correlated with the probability of porosity or defect formation. In this context, Machine Learning (ML) algorithms have achieved promising results for the task of porosity prediction based on thermographic in-situ monitoring data. One important technique is the use of thermogram features for porosity prediction that are extracted from the raw data (e.g., features related to the melt pool geometry or spatter generation). However, the reduction from large thermogram data to discrete features holds the risk of losing potentially important thermal information and, thereby, introducing bias in the model. Therefore, we present a raw data-based deep learning approach that uses thermographic image sequences for the prediction of local porosity. The model takes advantage of the self-attention mechanism that considers not only the thermogram information but also its positional context within the sequence. The model is used to predict porosity in the form of a many-to-one regression. It is trained and tested on a dataset retrieved from the manufacturing of HAYNES282 cuboid specimens. The model results are compared against state-of-the-art thermogram feature-based ML models and artificial neural networks. The raw data model outperforms its feature-based counterparts in terms of prediction scores and, therefore, seems to make better use of the information available in the thermogram data. T2 - 4th Symposium on Materials and Additive Manufacturing CY - Berlin, Germany DA - 12.06.2024 KW - PBF-LB/M KW - In situ monitoring KW - Thermography KW - Additive Manufacturing KW - Machine learning KW - Porosity prediction PY - 2024 AN - OPUS4-62472 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Scheuschner, Nils T1 - SAMMIE - Research PBF-LB/M system for the development of in-situ monitoring methods N2 - By allowing economic on-demand manufacturing of highly customized and complex workpieces, metal based additive manufacturing (AM) has the prospect to revolutionize many industrial areas. Since AM is prone to the formation of defects during the building process, a fundamental requirement for AM is to find ways to assure the safety and reliability of the additively manufactured parts to become applicable in most fields. A possible solution for this problem lies in the deployment of various in-situ monitoring techniques. However, only a few of these techniques are commercially available and are not researched to an extent that allows to guarantee the adherence to strict quality and safety standards. Since commercial AM machines are not designed for research applications, they provide only limited access to the build chamber during the process and little control over the exact timing and parameters of the process. Therefore, for our research at BAM, we built a laser powder bed fusion system (PBF-LB/M), called “Sensor-based Additive Manufacturing MachInE” (SAMMIE). It provides a fully open system architecture with flexible accesses to the build camber and full control of the complete process. In this contribution, we show first results using thermographic cameras and optical tomography. The flexibility of SAMMIE allows us to use the multiple cameras either fixed relatively to the build plate or coaxially to the process laser. T2 - 20th World Conference on Non-Destructive Testing (WCNDT) CY - Incheon, South Korea DA - 27.05.2024 KW - PBF-LB/M KW - In situ monitoring KW - Custom machine KW - Additive Manufacturing KW - Thermography PY - 2024 AN - OPUS4-62471 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Mohr, Gunther A1 - Altenburg, Simon A1 - Hilgenberg, Kai T1 - Effects of inter layer time and build height on resulting properties of 316L stainless steel processed by laser powder bed fusion N2 - Laser powder bed fusion (L-PBF) is the most prominent additive manufacturing (AM) technology for metal part production. Among the high number of factors influencing part quality and mechanical properties, the inter layer time (ILT) between iterative melting of volume elements in subsequent layers is almost completely unappreciated in the relevant literature on L-PBF. This study investigates the effect of ILT with respect to build height and under distinct levels of volumetric energy density (VED) using the example of 316L stainless steel. In-situ thermography is used to gather information on cooling conditions during the process, which is followed by an extensive metallographic analysis. Significant effects of ILT and build height on heat accumulation, sub-grain sizes, melt pool geometries and hardness are presented. Furthermore, the rise of defect densities can be attributed to a mutual interplay of build height and ILT. Hence, ILT has been identified as a crucial factor for L-PBF of real part components especially for those with small cross sections. KW - Laser powder bed fusion (L-PBF) KW - Laser beam melting (LBM) KW - Selective laser melting (SLM) KW - Dwell-time KW - Thermography PY - 2020 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-503300 DO - https://doi.org/10.1016/j.addma.2020.101080 SN - 2214-8604 VL - 32 SP - 101080-1 EP - 101080-13 PB - Elsevier CY - Amsterdam AN - OPUS4-50330 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Mohr, Gunther A1 - Altenburg, Simon A1 - Hilgenberg, Kai T1 - On the limitations of small cubes as test coupons for process parameter optimization in laser powder bed fusion of metals N2 - The capability to produce complexly and individually shaped metallic parts is one of the main advantages of the laser powder bed fusion (PBF LB/M) process. Development of material and machine specific process parameters is commonly based on results acquired from small cubic test coupons of about 10 mm edge length. Such cubes are usually used to conduct an optimization of process parameters to produce dense material. The parameters are then taken as the basis for the manufacturing of real part geometries. However, complex geometries go along with complex thermal histories during the manufacturing process, which can significantly differ from thermal conditions prevalent during the production of simply shaped test coupons. This may lead to unexpected and unpredicted local inhomogeneities of the microstructure and defect distribution in the final part and it is a root cause of reservations against the use of additive manufacturing for the production of safety relevant parts. In this study, the influence of changing thermal conditions on the resulting melt pool depth of 316L stainless steel specimens is demonstrated. A variation of thermo-graphically measured intrinsic preheating temperatures was triggered by an alteration of inter layer times and a variation of cross section areas of specimens for three distinct sets of process parameters. Correlations between the preheating temperature, the melt pool depth, and occurring defects were analyzed. The limited expressiveness of the results of small density cubes is revealed throughout the systematic investigation. Finally, a clear recommendation to consider thermal conditions in future process parameter optimizations is given. T2 - Icaleo 2023 CY - Chicago, IL, USA DA - 16.10.2023 KW - Additive manufacturing KW - Heat accumulation KW - Thermal history KW - In situ monitoring KW - Representative specimens KW - Thermography PY - 2023 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-586558 DO - https://doi.org/10.2351/7.0001080 SN - 1042-346X VL - 35 IS - 4 SP - 1 EP - 10 AN - OPUS4-58655 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -