TY - CONF A1 - Oster, Simon A1 - Becker, Tina A1 - Breese, Philipp Peter A1 - Scheuschner, Nils A1 - Maierhofer, Christiane A1 - Ulbricht, Alexander A1 - Fritsch, Tobias A1 - Mohr, Gunther A1 - Altenburg, Simon T1 - Defect prediction on the Base of Thermographic features in Laser Powder Bed Fusion Utilizing Machine Learning Algorithms N2 - Avoiding the formation of defects such as keyhole pores is a major challenge for the production of metal parts by Laser Powder Bed Fusion (LPBF). The use of in-situ monitoring by thermographic cameras is a promising approach to detect defects, however the data is hard to analyze by conventional algorithms. Therefore, we investigate the use of Machine Learning (ML) in this study, as it is a suitable tool to model complex processes with many influencing factors. A ML model for defect prediction is created based on features extracted from process thermograms. The porosity information calculated from an x-ray Micro Computed Tomography (µCT) scan is used as reference. Physical characteristics of the keyhole pore formation are incorporated into the model to increase the prediction accuracy. Based on the prediction result, the quality of the input data is inferred and future demands on in-situ monitoring of LPBF processes are derived. T2 - Additive Manufacturing Benchmarks 2022 CY - Bethesda, MA, USA DA - 14.08.2022 KW - Laser Powder Bed Fusion KW - Thermography KW - In-situ Monitoring KW - Machine Learning KW - Defect prediction PY - 2022 AN - OPUS4-55591 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Oster, Simon A1 - Becker, Tina A1 - Breese, Philipp Peter A1 - Scheuschner, Nils A1 - Maierhofer, Christiane A1 - Ulbricht, Alexander A1 - Frisch, Tobias A1 - Mohr, Gunther A1 - Altenburg, Simon T1 - Defect prediction in laser powder bed fusion based on thermographic features utilizing convolutional neural networks N2 - The appearance of irregularities such as keyhole porosity is a major challenge for the production of metal parts by laser powder bed fusion (PBF-LB/M). The utilization of thermographic in-situ monitoring is a promising approach to extract the thermal history which is closely related to the formation of irregularities. In this study, we investigate the utilization of convolutional neural networks to predict keyhole porosity based on thermographic features. Here, the porosity information calculated from an x-ray micro computed tomography scan is used as reference. Feature engineering is performed to enable the model to learn the complex physical characteristics of the porosity formation. The model is examined with regard to the choice of hyperparameters, the significance of thermal features and characteristics of the data acquisition. Based on the results, future demands on irregularity prediction in PBF-LB/M are derived. T2 - GIMC SIMAI YOUNG 2022 CY - Pavia, Italy DA - 29.09.2022 KW - Laser Powder Bed Fusion KW - Thermography KW - In-situ Monitoring KW - Convolutional Neural Networks PY - 2022 AN - OPUS4-56331 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Scheuschner, Nils A1 - Altenburg, Simon A1 - Straße, Anne A1 - Gumenyuk, Andrey A1 - Maierhofer, Christiane T1 - In-situ thermographic monitoring of the laser metal deposition process T2 - II International Conference on Simulation for Additive Manufacturing - Sim-AM 2019 N2 - In this paper shortwave infrared (SWIR) thermographic measurements of the manufacturing of thin single-line walls via laser metal deposition (LMD) are presented. As the thermographic camera is mounted fixed to the welding arm, an acceleration sensor was used to assist in reconstructing the spatial position from the predefined welding path. Hereby we could obtain data sets containing the size of the molten pool and the oxide covered areas as functions of the position in the workpiece. Furthermore, the influence of the acquisition wavelength onto the thermograms was investigated in a spectral range from 1250 nm to 1550 nm. All wavelengths turned out to be usable for the in-situ process monitoring of the LMD process. The longer wavelengths are shown to be beneficial for the lower temperature range, while shorter wavelengths show more details within the molten pool. T2 - Sim-AM 2019 - 2. International Conference on Simulation for Additive Manufacturing CY - Pavia, Italy DA - 11.09.2019 KW - Additive manufacturing KW - 3D printing KW - Thermography KW - Direct energy deposition KW - Laser Metal Deposition KW - 3D Druck KW - Laser Pulver Auftragsschweißen KW - Additive Fertigung KW - Thermografie PY - 2019 UR - http://congress.cimne.com/SIM-AM2019/frontal/Doc/proceedings.pdf SN - 978-84-949194-8-0 SP - 246 EP - 255 AN - OPUS4-49086 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Mohr, Gunther A1 - Altenburg, Simon A1 - Ulbricht, Alexander A1 - Hilgenberg, Kai T1 - In-situ defect detection in Laser Powder Bed Fusion (L-PBF) by using thermography and optical tomography N2 - Laser powder bed fusion (L-PBF) is one of the most promising additive manufacturing (AM) technologies for the production of complex metallic real part components. Due to the multitude of factors influencing process conditions and part quality and due to the layer-wise characteristic of the process, monitoring of process signatures seems to be mandatory in case of the production of safety critical components. Here, the iterative process nature enables unique access for in-situ monitoring during part manufacture. In this talk, the successful test of the synchronous use of a high-frequency infrared camera and a camera for long time exposure, working in the visible spectrum (VIS) and equipped with a near infrared filter (NIR), will be introduced as a machine manufacturer independent thermal detection monitoring set-up. Thereby, the synchronous use of an infrared camera and a VIS NIR camera combines the advantages of high framerate and high spatial resolution. The manufacture of a 316L stainless steel specimen, containing purposely seeded defects and volumes with forced changes of energy inputs, was monitored during the build. The measured thermal responses are analysed and compared with a defect mapping obtained by micro X-ray computed tomography (CT). The first results regarding methods for data analysis, derived correlations between measured signals and detected defects as well as sources of possible data misinterpretation are presented in this talk. T2 - 45. MPA Seminar - Fit for Future – Advanced Manufacturing Technologies, Materials and Lifetime CY - Stuttgart, Germany DA - 01.10.2019 KW - Data fusion KW - Laser Powder Bed Fusion (L-PBF) KW - Selective Laser Melting (SLM) KW - Additive Manufacturing (AM) KW - Process monitoring KW - Infrared thermography KW - Optical tomography KW - Computed tomography (CT) KW - Lack-of-fusion PY - 2019 AN - OPUS4-49386 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Altenburg, Simon A1 - Scheuschner, Nils A1 - Straße, Anne A1 - Gumenyuk, Andrey A1 - Maierhofer, Christiane T1 - Towards the determination of real process temperatures in the LMD process by multispectral thermography T2 - Thermosense: Thermal Infrared Applications XLIII N2 - Due to the rapid thermal cycles involved in additive manufacturing of metals, high internal stresses and peculiar microstructures occur, which influence the parts mechanical properties. To systematically examine their formation, in-process measurements of the temperature are needed. Since the part emissivity is strongly inhomogeneous and rapidly changing in the process, the applicability of thermography for the determination of thermodynamic temperatures is limited. Measuring the thermal radiation in different wavelengths simultaneously, temperature and emissivity can be separated. Here, we present results of a preliminary study using multispectral thermography to obtain real temperatures and emissivities in directed energy deposition (DED) processes. T2 - Thermosense: Thermal Infrared Applications XLIII CY - Online meeting DA - 12.04.2021 KW - Additive Manufacturing KW - Process monitoring KW - Multispectral thermography KW - Laser metal deposition KW - TES KW - LMD KW - Temperature emissivity separation PY - 2021 DO - https://doi.org/10.1117/12.2587881 VL - 2021 SP - 77 EP - 83 PB - SPIE AN - OPUS4-52516 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF 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 - Das pulverbettbasierte selektive Laserstrahlschmelzen (engl. laser powder bed fusion, L-PBF) ist die am weitesten verbreitete additive Fertigungstechnologie für die Herstellung metallischer Komponenten. Unter der Vielzahl an Einflussfaktoren auf die Qualität und die mechanischen Eigenschaften von L PBF-Bauteilen hat die Zwischenlagenzeit (engl. inter layer time, ILT) bisher kaum Beachtung in der wissenschaftlichen Literatur gefunden, obwohl sie je nach Bauraumausnutzungsgrad stark variieren kann. In diesem Vortrag werden Ergebnisse einer Studie präsentiert, die den Einfluss der ILT in Kombination mit der Bauteilhöhe und unter Berücksichtigung verschiedener Volumenenergiedichten am Beispiel der austenitischen Stahllegierung AISI 316L untersucht. Die Fertigungsprozesse wurden in situ mittels Thermographiekamera überwacht, sodass Informationen über das Abkühlverhalten der Bauteile während des Prozesses gewonnen werden konnten. Es wurden signifikante Effekte der ILT und der Bauteilhöhe auf Wärmeakkumulation, Mikrostruktur, Schmelzbadgeometrie und Härte festgestellt. Ferner konnte ein Anstieg von Defektdichten bei einem gegenseitigen Wechselspiel aus Bauteilhöhe und ILT aufgezeigt werden. Die Zwischenlagenzeit wurde somit als kritischer Faktor für die L-PBF-Fertigung von Realbauteilen identifiziert. T2 - Workshop In-situ Monitoring and Microstructure Development in Additive Manufactured Alloys CY - Online meeting DA - 19.04.2021 KW - Infrared thermography KW - Laser Powder Bed Fusion (L-PBF) KW - Selective Laser Melting (SLM) KW - Additive Manufacturing (AM) KW - Process monitoring PY - 2021 AN - OPUS4-52699 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Oster, Simon A1 - Maierhofer, Christiane A1 - Mohr, Gunther A1 - Hilgenberg, Kai A1 - Ulbricht, Alexander A1 - Altenburg, Simon T1 - Investigation of the thermal history of L-PBF metal parts by feature extraction from in-situ SWIR thermography N2 - Laser powder bed fusion is used to create near net shape metal parts with a high degree of freedom in geometry design. When it comes to the production of safety critical components, a strict quality assurance is mandatory. An alternative to cost-intensive non-destructive testing of the produced parts is the utilization of in-situ process monitoring techniques. The formation of defects is linked to deviations of the local thermal history of the part from standard conditions. Therefore, one of the most promising monitoring techniques in additive manufacturing is thermography. In this study, features extracted from thermographic data are utilized to investigate the thermal history of cylindrical metal parts. The influence of process parameters, part geometry and scan strategy on the local heat distribution and on the resulting part porosity are presented. The suitability of the extracted features for in-situ process monitoring is discussed. T2 - Thermosense: Thermal Infrared Applications XLIII CY - Online meeting DA - 12.04.2021 KW - SWIR camera KW - Additive manufacturing (AM) KW - Selective laser melting (SLM) KW - Laser beam melting (LBM) KW - In-situ monitoring KW - Infrared thermography PY - 2021 UR - https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11743/117430C/Investigation-of-the-thermal-history-of-L-PBF-metal-parts/10.1117/12.2587913.short?SSO=1&tab=ArticleLink AN - OPUS4-52540 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Altenburg, Simon A1 - Scheuschner, Nils A1 - Gumenyuk, Andrey A1 - Straße, Anne A1 - Maierhofer, Christiane T1 - Unraveling thermal radiation by multispectral thermography: Real temperatures in LMD N2 - Additive manufacturing of metals offers the opportunity to build parts with a high degree of complexity without additional costs, opening a new space for design optimization. However, the processes are highly complex and due to the rapid thermal cycles involved, high internal stresses and peculiar microstructures occur, which influence the parts mechanical properties. To systematically examine the formation of internal stresses and the microstructure, in-process spatially resolved measurements of the part temperature are needed. If the emissivity of the inspected part is known, its thermodynamic temperature can be reconstructed by a suited radiometric model. However, in additive manufacturing of metals, the emissivity of the part surface is strongly inhomogeneous and rapidly changing due to variations of, e.g., the degree of oxidation, the material state and temperature. Thus, here, the applicability of thermography in the determination of thermodynamic temperatures is limited. However, measuring the process thermal radiation at different wavelengths simultaneously enables one to separate temperature and emissivity spatially resolved to obtain further insight into the process. Here, we present results of an initial study using multispectral thermography to obtain real temperatures and emissivities in the powderfree LMD process. T2 - 2nd Workshop on In-situ Monitoring and Microstructure Development in Additive Manufactured Alloys CY - Online meeting DA - 19.04.2021 KW - Additive Manufacturing KW - Process monitoring KW - Multispectral thermography KW - Laser metal deposition KW - TES KW - LMD KW - Temperature emissivity separation PY - 2021 AN - OPUS4-52514 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Scheuschner, Nils A1 - Altenburg, Simon A1 - Pignatelli, Giuseppe A1 - Maierhofer, Christiane A1 - Straße, Anne A1 - Gumenyuk, Andrey A1 - Gornushkin, Igor B. T1 - In-situ temperature measurements of the LMD process by IR-spectroscopy and Thermography N2 - Temperature measurements of the LMD process by IR-spectroscopy and Thermography are presenet and compared. T2 - 2st Workshop on In-situ Monitoring and Microstructure Development in Additive Manufacturing CY - Online meeting DA - 19.04.2021 KW - Additive Manufacturing KW - Thermography PY - 2021 AN - OPUS4-52565 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Poka, Konstantin A1 - Ali, Sozol A1 - Saeed, Waleed A1 - Merz, Benjamin A1 - Epperlein, Martin A1 - Hilgenberg, Kai T1 - Design and implementation of a machine log for PBF-LB/M on basis of IoT communication architectures and an ETL pipeline JF - Progress in Additive Manufacturing N2 - AbstractPowder Bed Fusion with Laser Beam of Metals (PBF-LB/M) has gained more industrial relevance and already demonstrated applications at a small series scale. However, its widespread adoption in various use cases faces challenges due to the absence of interfaces to established Manufacturing Execution Systems (MES) that support customers in the predominantly data-driven quality assurance. Current state-of-the-art PBF-LB/M machines utilize communication architectures, such as OPC Unified Architecture (OPC UA), Message Queuing Telemetry Transport (MQTT) and Representational State Transfer Application Programming Interface (REST API). In the context of the Reference Architecture Model Industry 4.0 (RAMI 4.0) and the Internet of Things (IoT), the assets, particularly the physical PBF-LB/M machines, already have an integration layer implemented to communicate data such as process states or sensor values. Missing is an MES component acting as a communication and information layer. To address this gap, the proposed Extract Transform Load (ETL) pipeline aims to extract relevant data from the fabrication of each build cycle down to the level of scan vectors and additionally to register process signals. The suggested data schema for archiving each build cycle adheres to all terms defined by ISO/TC 261—Additive Manufacturing (AM). In relation to the measurement frequency, all data are reorganized into entities, such as the AM machine, build cycle, part, layer, and scan vector. These scan vectors are stored in a runtime-independent format, including all metadata, to be valid and traceable. The resulting machine log represents a comprehensive documentation of each build cycle, enabling data-driven quality assurance at process level. KW - FAIR data KW - Data-driven quality assurance KW - Laser powder bed fusion PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-601256 DO - https://doi.org/10.1007/s40964-024-00660-7 SN - 2363-9512 SP - 1 EP - 12 PB - Springer Science and Business Media LLC AN - OPUS4-60125 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -