TY - JOUR A1 - Oster, Simon A1 - Scheuschner, Nils A1 - Chand, Keerthana A1 - Altenburg, Simon T1 - Local porosity prediction in metal powder bed fusion using in-situ thermography: A comparative study of machine learning techniques N2 - The formation of flaws such as internal porosity in parts produced by Metal-based Powder Bed Fusion with Laser Beam (PBF-LB/M) significantly hinders its broader industrial application, as porosity can potentially lead to part failure. Addressing this issue, this study explores the efficacy of in-situ thermography, particularly short-wave infrared thermography, for detecting and predicting porosity during manufacturing. This technique is capable of monitoring the part’s thermal history which is closely connected to the flaw formation process. Recent advancements in Machine Learning (ML) have been increasingly leveraged for porosity prediction in PBF-LB/M. However, previous research primarily focused on global rather than localized porosity prediction which simplified the complex prediction task. Thereby, the opportunity to correlate the predicted flaw position with expected part strain to judge the severity of the flaw for part performance is neglected. This study aims to bridge this gap by studying the potential of SWIR thermography for predicting local porosity levels using regression models. The models are trained on data from two identical HAYNES®282® specimens. We compare the effectiveness of feature-based and raw data-based models in predicting different porosity types and examine the importance of input data in porosity prediction. We show that models trained on SWIR thermogram data can identify systematic trends in local flaw formation. This is demonstrated for forced flaw formation using process parameter shifts and, moreover, for randomly formed flaws in the specimen bulk. Furthermore, we identify features of high importance for the prediction of lack-of-fusion and keyhole porosity from SWIR monitoring data. KW - PBF-LB/M KW - In situ monitoring KW - Thermography KW - Additive Manufacturing KW - Process monitoring KW - Porosity prediction KW - Machine Learning KW - Feature extraction PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-621798 DO - https://doi.org/10.1016/j.addma.2024.104502 SN - 2214-7810 VL - 95 SP - 1 EP - 17 PB - Elsevier B.V. AN - OPUS4-62179 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CHAP A1 - Maierhofer, Christiane A1 - Altenburg, Simon A1 - Scheuschner, Nils ED - Meyendorf, N. ED - Ida, N. ED - Singh, R. ED - Vrana, J. T1 - In Situ Real-Time Monitoring Versus Post NDE for Quality Assurance of Additively Manufactured Metal Parts N2 - In this chapter, the current state-of-the-art of in situ monitoring and in situ NDE methods in additive manufacturing is summarized. The focus is set on methods, which are suitable for making statements about the quality and usability of a component currently being manufactured. This includes methods which can be used to determine state properties like temperature or density, other physical properties like electrical or thermal conductivity, the microstructure, the chemical composition, the actual geometry, or which enable the direct detection of defects like cracks, voids, delaminations, or inclusions. Thus, optical, thermographic, acoustic, and electromagnetic methods, as well as methods being suitable for investigating particle and fume emission are presented. The requirements of in situ monitoring methods with a focus on thermographic methods are discussed by considering different additive manufacturing processes like laser powder bed fusion (PBF-LB/M) and direct energy deposition (DED-LB/M). Examples of the successful implementation and applications of such monitoring methods at BAM are given. The in situ monitoring and NDE methods are compared against post-process NDE methods. The advantages and challenges of in situ methods concerning real-time data analysis and the application of AI algorithms are addressed and discussed. KW - Additive manufacturing KW - In situ monitoring KW - In situ NDE KW - Post NDE KW - Thermography KW - Laser powder bed fusion KW - Direct energy deposition PY - 2021 SN - 978-3-030-48200-8 DO - https://doi.org/10.1007/978-3-030-48200-8_51-1 SP - 1 EP - 37 PB - Springer Nature Switzerland AG CY - Cham, Switzerland ET - 1 AN - OPUS4-52824 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 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 - JOUR A1 - Scheuschner, Nils A1 - Altenburg, Simon A1 - Pignatelli, Giuseppe A1 - Maierhofer, Christiane A1 - Straße, Anne A1 - Gornushkin, Igor B. A1 - Gumenyuk, Andrey T1 - Vergleich der Messungen der Schmelzbadtemperatur bei der Additiven Fertigung von Metallen mittels IR-Spektroskopie und Thermografie T1 - Comparison of measurements of the melt pool temperature during the additive production of metals by means of IR spectroscopy and thermography N2 - Im Rahmen des Themenfeldprojektes „Process Monitoring of AM“ (ProMoAM) evaluiert die Bundesanstalt für Materialforschung und -Prüfung (BAM) gegenwärtig die Anwendbarkeit verschiedenster ZfP-Verfahren zur in-situ Prozessüberwachung in der additiven Fertigung (AM) von Metallen in Hinblick auf die Qualitätssicherung. Einige der wichtigsten Messgrößen sind hierbei die Temperatur des Schmelzbades und die Abkühlrate, welche starken Einfluss auf das Gefüge und die Eigenspannung haben. Aufgrund der Zugänglichkeit zum Werkstück während des Bauprozesses bieten sich optische Verfahren zu Temperaturbestimmung an. Hierbei stellen jedoch u. a. die hohe Bandbreite der zu messenden Temperaturen, die Bestimmung der Emissivität und ihre Änderung bei Phasenübergängen der verwendeten Legierung große experimentelle Herausforderungen dar. Eine weitere Herausforderung stellt für die IR-Spektroskopie die Absorption durch das Schutzgas und weitere optische Elemente dar. Um diese auch in einem industriellen Umfeld kompensieren zu können, wurde eine Methode entwickelt, die das gemessene Spektrum bei der Verfestigung des Werkstoffes als Referenz nutzt. In diesem Beitrag wird die Anwendung dieser Methode für die IR-Spektrometrie als auch Thermografische Messungen beim Laser-Pulver-Auftragschweißen von 316L gezeigt, wobei beide Methoden weiterhin in Hinblick auf ihre individuellen Vor- und Nachteile miteinander verglichen werden. N2 - Within the topic area project “Process Monitoring of AM” (ProMoAM) the Federal Institute for Materials Research and Testing is currently evaluating the applicability of various NDT methods for in-situ process Monitoring in the additive manufacturing (AM) of metals with regard to quality assurance. Two of the most important variables to measure are the temperature of the molten pool and the cooling rate, which have a strong influence on the microstructure and the residual stress. Due to the accessibility of the workpiece during the construction process, optical methods for temperature determination are suitable. However, the wide range of temperatures to be measured, the determination of emissivity and its change during phase transitions of the alloy pose great experimental challenges. Another challenge for IR spectroscopy is the absorption by the inert gas and other optical elements. In order to be able to compensate for this in an industrial environment, a method was developed which uses the measured spectrum as a reference when the material is solidified. This paper shows the application of this method for IR spectrometry as well as thermographic measurements during laser powder cladding of 316L. Furthermore both methods are compared with respect to their individual Advantages and disadvantages. KW - Laser-Pulver-Auftragschweißen KW - Thermografie KW - Direct Energy Deposition KW - IR-Spektroskopie KW - Additive Fertigung KW - Laser metal deposition KW - Thermography KW - IR-spectroscopy KW - Additive manufacturing PY - 2021 DO - https://doi.org/10.1515/teme-2021-0056 VL - 88 IS - 10 SP - 626 EP - 632 PB - De Gruyter CY - Oldenburg AN - OPUS4-52987 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Oster, Simon A1 - Scheuschner, Nils A1 - Chand, Keerthana A1 - Breese, Philipp Peter A1 - Becker, Tina A1 - Heinrichsdorff, F. A1 - Altenburg, Simon T1 - From Thermographic In-situ Monitoring to Porosity Detection – A Deep Learning Framework for Quality Control in Laser Powder Bed Fusion N2 - In this study, we present an enhanced deep learning framework for the prediction of porosity based on thermographic in-situ monitoring data of laser powder bed fusion processes. The manufacturing of two cuboid specimens from Haynes 282 (Ni-based alloy) powder was monitored by a short-wave infrared camera. We use thermogram feature data and x-ray computed tomography data to train a convolutional neural network classifier. The classifier is used to perform a multi-class prediction of the spatially resolved porosity level in small sub-volumes of the specimen bulk. T2 - SMSI - Sensor and Measurement Science International 2023 CY - Nürnberg, Germany DA - 08.05.2023 KW - Porosity KW - Laser powder bed fusion KW - In-situ monitoring KW - Thermography KW - Machine Learning PY - 2023 UR - https://www.ama-science.org/proceedings/details/4404 DO - https://doi.org/10.5162/SMSI2023/C5.4 SP - 179 EP - 180 AN - OPUS4-57616 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Straße, Anne A1 - Gumenyuk, Andrey A1 - Scheuschner, Nils A1 - Altenburg, Simon A1 - Pignatelli, Giuseppe A1 - Gornushkin, Igor B. A1 - Baensch, Franziska A1 - Rethmeier, Michael T1 - In-situ Prozessüberwachung beim Laser-Pulver-Auftragschweißen (LPA) mittels Thermografie, optischer Emissionsspektroskopie (OES) und Schallemissionsanalyse (SEA) N2 - Vor allem in den letzten Jahren ist das Interesse der Industrie an der additiven Fertigung deutlich gestiegen. Die Vorteile dieser Verfahren sind zahlreich und ermöglichen eine ressourcenschonende, kundenorientierte Fertigung von Bauteilen, welche zur stetigen Entwicklung neue Anwendungsbereiche und Werkstoffe führen. Aufgrund der steigenden Anwendungsfälle, nimmt auch der Wunsch nach Betriebssicherheit unabhängig von anschließenden kostenintensiven zerstörenden und zerstörungsfreien Prüfverfahren zu. Zu diesem Zweck werden im Rahmen des von der BAM durchgeführten Themenfeldprojektes „Prozessmonitoring in Additive Manufacturing“ verschiedenste Verfahren auf ihre Tauglichkeit für den in-situ Einsatz bei der Prozessüberwachung in der additiven Fertigung untersucht. Hier werden drei dieser in-situ Verfahren, die Thermografie, die optische Emissionsspektroskopie und die Schallmissionsanalyse für den Einsatz beim Laser-Pulver-Auftragschweißen betrachtet. T2 - 41. Assistentenseminar der Füge- und Schweißtechnik CY - Magdeburg, Germany DA - 02.09.2020 KW - Laser-Pulver-Auftragschweißen (LPA) KW - Thermographie KW - Optische Emissionsspektroskopie (OES) KW - Schallemissionsanalyse (SEA) PY - 2021 SN - 978-3-96144-141-9 VL - 370 SP - 132 EP - 140 PB - DVS MEdia CY - Düsseldorf AN - OPUS4-53967 LA - deu 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 - JOUR A1 - Becker, Tina A1 - Altenburg, Simon A1 - Scheuschner, Nils A1 - Breese, Philipp Peter A1 - Metz, C. A1 - Hilgenberg, Kai A1 - Maierhofer, Christiane T1 - In-situ monitoring of the Laser Powder Bed Fusion build process via bi- chromatic optical tomography N2 - As metal additive manufacturing (AM) is entering industrial serial production of safety relevant components, the need for reliable process qualification is growing continuously. Especially in strictly regulated industries, such as aviation, the use of AM is strongly dependent on ensuring consistent quality of components. Because of its numerous influencing factors, up to now, the metal AM process is not fully controllable. Today, expensive part qualification processes for each single component are common in industry. This contribution focusses on bi-chromatic optical tomography as a new approach for AM in-situ quality control. In contrast to classical optical tomography, the emitted process radiation is monitored simultaneously with two temperature calibrated cameras at two separate wavelength bands. This approach allows one to estimate the local maximum temperatures during the manufacturing process, thus increases the comparability of monitoring data of different processes. A new process information level at low investment cost is reachable, compared to, e.g., infrared thermography. T2 - LANE 2022 CY - Fürth, Germany DA - 04.08.2022 KW - Optical tomography KW - Additive Manufacturing KW - L-PBF KW - In-process monitoring PY - 2022 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-560270 DO - https://doi.org/10.1016/j.procir.2022.08.035 SN - 2212-8271 VL - 111 SP - 340 EP - 344 PB - Elsevier B.V. CY - Amsterdam AN - OPUS4-56027 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Altenburg, Simon A1 - Scheuschner, Nils A1 - Maierhofer, Christiane A1 - Mohr, Gunther A1 - Hilgenberg, Kai T1 - Thermography in laser powder bed fusion of metals: time over threshold as feasible feature in thermographic data N2 - Thermography is one on the most promising techniques for in-situ monitoring of metal additive manufacturing processes. Especially in laser powder bed fusion processes, the high process dynamics and the strong focus of the laser beam cause a very complex thermal history within the produced specimens, such as multiple heating cycles within single layer expositions. This complicates data interpretation, e.g., in terms of cooling rates. A quantity that is easily calculated is the time a specific area of the specimen is at a temperature above a chosen threshold value (TOT). Here, we discuss variations occurring in time-over-threshold-maps during manufacturing of an almost defect free cuboid specimen. T2 - 15th Quantitative InfraRed Thermography conference CY - Online meeting DA - 21.09.2020 KW - Additive Manufacturing KW - Process monitoring KW - Thermography KW - L-PBF KW - Time over threshold PY - 2020 DO - https://doi.org/10.21611/qirt.2020.005 SP - 1 EP - 5 PB - QIRT Council CY - Quebec, Canada AN - OPUS4-52014 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - GEN A1 - Ziegler, Mathias A1 - Altenburg, Simon A1 - Krankenhagen, Rainer A1 - Maierhofer, Christiane A1 - Scheuschner, Nils A1 - Marquardt, E A1 - Mühlberger, W. A1 - Nagel, F. A1 - Neumann, E. A1 - Rohwetter, P. A1 - Rutz, F. A1 - Schwake, C. A1 - Schramm, S. A1 - Schwaneberg, F. A1 - Taubert, R. D. T1 - Thermografie und Strahlungsthermometrie - Stand und Trends N2 - In vielen Umgebungen, besonders bei hohen Temperaturen, korrosiven Umgebungen oder auf bewegten oder schlecht zugänglichen Flächen, kann die Temperatur nicht oder nur mit nicht akzeptablem Aufwand mit Berührungsthermometern gemessen werden. Diese Umgebungsbedingungen sind unter anderem in der chemischen Industrie, der Lebensmittel-, Metall-, Glas-, Kunststoff- und Papierherstellung sowie bei der Lacktrocknung anzutreffen. In diesen Bereichen kommen Strahlungsthermometer zum Einsatz. Der VDI-Statusreport zeigt typische Anwendungsfelder von nicht radiometrisch kalibrierten Wärmebildkameras und von radiometrisch kalibrierten Thermografiekameras. Um verlässlich mit spezifizierten Messunsicherheiten berührungslos Temperaturen zu messen, müssen die Strahlungsthermometer und Thermografiekameras nicht nur kalibriert, sondern radiometrisch und strahlungsthermometrisch umfassend charakterisiert werden. Auch die optische Materialeigenschaft, der spektrale Emissionsgrad und die Gesamtstrahlungsbilanz (Strahlung des Messobjekts und der Umgebung) sind bei der industriellen Temperaturmessung von großer Bedeutung. In den letzten Jahrzehnten ist dazu ein umfassendes technisches Regelwerk entstanden, das wir Ihnen mit diesem VDI-Statusreport vorstellen. Manche in den Richtlinien beschriebenen Kennwerte mögen abstrakt wirken. In diesem Statusreport zeigen wir an konkreten Beispielen, was diese Kenngrößen für die berührungslose Temperaturmessung bedeuten. Beispiele von Anwendungen zeigen, wo temperaturmessende Thermografiekameras und ausschließlich bildgebende Wärmebildkameras in der Praxis eingesetzt werden. Mit einer Analyse, welche Themen und Anwendungen derzeit besonders intensiv diskutiert werden, versuchen wir Trends für zukünftige Entwicklungen herauszuarbeiten. KW - Thermografie KW - Temperaturmessung PY - 2021 UR - https://www.vdi.de/ueber-uns/presse/publikationen/details/thermografie-und-strahlungsthermometrie-stand-und-trends SP - 1 EP - 40 PB - VDI Verein Deutscher Ingenieure e.V. CY - Düsseldorf AN - OPUS4-52904 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -