TY - CONF A1 - Bruno, Giovanni T1 - X-ray refraction techniques non-destructively quantify and classify defects in am materials N2 - X-ray refraction is analogous to visible light deflection by matter; it occurs at boundaries between different media. The main difference between visible light and X-rays is that in the latter case deflection angles are very small, from a few seconds to a few minutes of arc (i.e., the refraction index n is near to 1). Importantly, deflection of X-rays is also sensitive to the orientation of the object boundaries. These features make X-ray refraction techniques extremely suitable to a) detect defects such as pores and microcracks and quantify their densities in bulk (not too heavy) materials, and b) evaluate porosity and particle properties such as orientation, size, and spatial distribution (by mapping). While X-ray refraction techniques cannot in general image single defects, they can detect objects with size above a few wavelengths of the radiation. Such techniques, especially at the Synchrotron BESSY II, Berlin, Germany, can be used in-situ, i.e. when the specimen is subjected to temperatures or external loads. The use of X-ray refraction analysis yields quantitative information, which can be directly input in kinetics, mechanical and damage models. We hereby show the application of non-destructive X-ray refraction radiography (SXRR, 2D mapping also called topography) to problems in additive manufacturing: 1) Porosity analysis in PBF-LM-Ti64. Through the use of SXRR, we could not only map the (very sparse) porosity distribution between the layers and quantify it, but also classify, and thereby separate, the filled porosity (unmolten powder) from the keyhole and gas pores (Figure 1). 2) In-situ heat treatment of laser powder bed fusion PBF-LM-AlSi10Mg to monitor microstructure and porosity evolution as a function of temperature (Figure 2). By means of SXRR we indirectly observed the initial eutectic Si network break down into larger particles as a function of increasing temperature. We also could detect the thermally induced porosity (TIP). Such changes in the Si-phase morphology upon heating is currently only possible using scanning electron microscopy, but with a much smaller field-of-view. SXRR also allows observing the growth of some individual pores, usually studied via X-ray computed tomography, but again on much smaller fields-of-view. Our results show the great potential of in-situ SXRR as a tool to gain in-depth knowledge of the defect distribution and the susceptibility of any material to thermally induced damage and/or microstructure evolution over statistically relevant volumes. T2 - AAMS 2023 CY - Madrid, Spain DA - 27.09.2023 KW - X-ray refraction radiography KW - Defects KW - Large scale facilities KW - Computed tomography PY - 2023 AN - OPUS4-58508 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Evans, Alexander T1 - Residual stresses Analysis in Additively Manufactured alloys using neutron diffraction (L-PBF) N2 - An overview of recent progress at BAM of residual stress analysis in additively manufactured, in particular Laser Powder Bed Fusion of metallics materials, using neutron diffraction will be presented. This will cover important topics of the stress-free reference, the diffraction elastic moduli and principal stress determination. T2 - AWT-Fachausschuss 13 "Eigenspannungen" CY - Berlin, Germany DA - 28.03.2023 KW - AGIL KW - Residual stress KW - Additive manufacturing KW - Laser Powder Bed Fusion KW - Diffraction PY - 2023 AN - OPUS4-59177 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Evans, Alexander T1 - Diffraction based residual stress analysis: challenges and opportunities in additive manufacturing N2 - This presentation overviews the challanges and opportunities of diffraction based residual stress analysis for additively manufactured metals. Through examples, the challanges and respective solutions are presented and the opportunities that the presented methods allow are described. T2 - Workshop on Advanced Manufacturing (WAM) 2025 CY - Grenoble, France DA - 03.06.2025 KW - Residual stress KW - Diffraction KW - AGIL KW - Laser powder bed fusion KW - MANUFACT PY - 2025 AN - OPUS4-64137 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Schröder, Jakob T1 - Peculiarities of the determination of residual stress in additively manufactured materials N2 - The determination of residual stress in additively manufactured materials is a challenge, even after decades from the establishment of the basics of residual stress analysis. This is due to the peculiar microstructure of such materials. In fact, researchers have discovered that conventional methods for the determination of RS in materials do not properly work for AM materials. In this tutorial, the basics of RS analysis will be explained, together with the basics of AM manufacturing techniques. The microstructure of the peculiar materials (AM) dealt with here will be elucidated. Successively, the necessary modifications to the conventional approaches to RS analysis will be explained and case studies will be displayed, for the attendant to touch with hands the peculiarities of the approaches. Finally, a few experimental and theoretical tips will be given on dos and don’ts for a correct determination of RS in AM materials. T2 - 11th European Conference on Residual Stresses CY - Prague, Czech Republic DA - 03.06.2024 KW - Additive Manufacturing KW - Laser Powder Bed Fusion KW - Residual Stress KW - Diffraction PY - 2024 AN - OPUS4-60428 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Schröder, Jakob T1 - The heat treatment of L-PBF Inconel 718: A manyfold problem N2 - The interest to additively manufacture Nickel-based superalloys has substantially grown within the past decade both academically and industrially. More specifically, additive manufacturing processes such as laser powder bed fusion (LPBF) offer the ability to produce dense parts within a single manufacturing step. In fact, the exceptional freedom in design associated with the layer-based nature of the processes is of particular interest for the complex shapes typically required in turbine applications. In certain cases, the overall part performance can be achieved by tailoring the microstructure and the crystallographic texture to the specific application. However, these advantages must be paid at a price: the large local temperature gradients associated with the rapid melting and solidification produce parts that inherently contain large residual stress in the as-manufactured state. In addition, the presence of pores in the final part may further affect the in-service part failure. As among Nickel-based alloys Inconel 718 exhibits excellent weldability, this alloy has been widely studied in open research in the domain of LPBF. However, significant microsegregation of the heavier alloying elements such as Niobium and Molybdenum accompanied by dislocation entanglements may preclude the application of conventional heat treatment schedules. Therefore, different post processing heat treatments are required for laser powder bed fused Inconel 718 as compared to conventional variants of the same alloy. In this study, we investigated two different heat treatment routes for LPBF Inconel 718. In a first routine, the samples were stress relieved and subsequently subjected to hot isostatic pressing (HIP) followed by a solution heat treatment and a two-step age (referred to as FHT). In a second routine, the samples were subjected to a single-step direct age post stress relieving heat treatment (referred to DA). We investigated the consequences of such heat treatment schedules on the microstructure, texture, and mechanical behavior. We show that by applying a DA heat treatment the typical columnar microstructure possessing a crystallographic texture is retained, while an equiaxed untextured microstructure prevails in case of an FHT heat treatment. We further evaluate how these heat treatments affect the mechanical behaviour on the macroscopic and microscopic scale. T2 - 4th European Symposium on Superalloys and their Applications EuroSuperalloys 2022 CY - Bamberg, Germany DA - 18.09.2022 KW - Electron Backscatter Diffraction KW - Additive Manufacturing KW - Laser Powder Bed Fusion KW - Mechanical Behavior KW - Heat Treatment KW - X-Ray Diffraction PY - 2022 AN - OPUS4-55811 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Schröder, Jakob T1 - On the influence of heat treatment on microstructure and mechanical behavior of laser powder bed fused Inconel 718 N2 - Since additive manufacturing processes typically introduce heterogeneous microstructures and residual stresses, the applicability of parts produced in an as-built state is limited. Therefore, often different post-processing treatments are necessary to obtain the desired stress state and properties. For additively manufactured Inconel 718, the recently developed standard ASTM F3301 provides guidance for the heat treatment of powder bed fusion specimens. Although this standard is based on standards developed for wrought Inconel 718, it does not include the direct aging variant. In this study, we characterized the microstructure and tensile behavior of Inconel 718 specimens produced by a laser powder bed fusion process. The specimens were heat-treated according to two different routines after stress relieving: a full heat treatment cycle versus a one-step aging process. Differences in the resulting texture and grain morphology were observed. Although these differences prevail, the ex-situ tensile behavior was broadly similar. Minor differences were observed in yield strength and work hardening rate for the direct aged specimen. In order to understand this behavior, investigations with in-situ tensile testing during synchrotron energy-dispersive X-ray diffraction measurements revealed differences in the load partitioning among different crystal directions. This was attributed to microstructural differences between the heat treatment variants. Further analysis emphasized that the various strengthening mechanisms are present to a different extent depending on the heat-treatment cycle applied. In addition, the elastic anisotropy expressed by the differences in the diffraction elastic constants displayed a dependence on the microstructure. Importantly, a precise knowledge of such constants is indispensable to reliably determine residual stresses in parts. T2 - EUROMAT 2021 - European Congress and Exhibition on Advanced Materials and Processes CY - Online meeting DA - 13.09.2021 KW - Electron microscopy KW - X-ray analysis KW - Inconel 718 KW - Additive manufacturing (AM) KW - Mechanical behavior KW - Diffraction elastic constants (DECs) PY - 2021 AN - OPUS4-53301 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Hejazi, Bardia A1 - Fritsch, Tobias A1 - Benz, Christopher A1 - Radtke, Lars A1 - Sander, Manuela A1 - Bruno, Giovanni T1 - In-situ very high cycle fatigue experiments of additively manufactured Ti-6Al-4V using X-ray computed tomography N2 - X-ray computed tomography (XCT) is an invaluable method for evaluating the properties and performance of components both during service and after failure in a non-destructive manner. XCT is particularly useful for the investigation of additively manufactured (AM) components, which often have production defects that are inherent to the manufacturing process, such as lack of fusion defects. Understanding the mechanisms of fatigue crack growth throughout the life cycle of such components is crucial and so to address this need, we designed and performed experiments to investigate the fatigue life and fatigue crack growth behavior of Ti-6Al-4V components under very high cycle fatigue (VHCF) testing. The titanium samples were additively manufactured with intentional internal defects to control crack initiation location. XCT of the component was carried out to identify crack initiation sites and characterize the dynamics of crack growth. The findings from this work will benefit industries that rely on the AM of titanium alloys, aiding in the improvement of component design and manufacturing processes. T2 - Alloys for additive manufacturing 2025 (AAMS 2025) CY - Neuchâtel, Switzerland DA - 02.09.2025 KW - X-ray computed tomography KW - Deep learning KW - Titanium alloy KW - Very high-cycle fatigue PY - 2025 DO - https://doi.org/10.5281/zenodo.15261296 AN - OPUS4-64096 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Breese, Philipp Peter T1 - Thermographic Methods for In-situ Monitoring of Metal-based Additive Manufacturing Processes N2 - Additive manufacturing (AM) with metals creates new, exciting opportunities for industrial applications. Especially industries with high relevance for the future like transport and energy benefit from optimized designs and novel materials. However, a reliable in-situ quality assurance for metal AM is still missing while process optimization is slow. This directly hinders the huge potential of metal AM technologies. A promising method to counteract this issue is the investigation of the emitted thermal radiation. It is optimal for monitoring and understanding the thermal history of the high-temperature AM process. The thermal history holds virtually all information about the properties and the quality of the manufactured components. The thermal information is also highly valuable for tuning and validating numerical simulations to gather further insights into the process. Despite this importance, the usage of thermal radiation in commercial AM machines is only marginal (like simple pyrometry or long-time exposure for optical tomography (OT) at a single wavelength). Based on this deficit and potential, this work gives an overview of the research in division “8.3 Thermographic Methods” at the Bundesanstalt für Materialforschung und -prüfung (BAM) in Berlin, Germany. Different wavelengths of the thermal radiation are investigated: the visible range (VIS), the short-wave infrared (SWIR), and the mid-wave infrared (MWIR) with their respective optimal field of application. Focus lies on laser powder bed fusion of metals (PBF-LB/M), but directed energy deposition with laser beam (DED-LB/M) is investigated as well. The presented research is performed not only on commercial AM machines, but also on an in-house developed PBF-LB/M research system specifically designed for sensor testing. This ensures an exciting mélange of applied research for industrial applications, and fundamental research for process understanding and validation. Therefore, a crucial contribution to industrial and scientific insights of metal AM is given. T2 - Sim-AM 2025 CY - Pavia, Italy DA - 09.09.2025 KW - Laser powder bed fusion KW - Direct energy deposition KW - Quality assurance KW - Infrared thermography PY - 2025 AN - OPUS4-65391 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Suarez Ocano, Patricia T1 - Exploring the impact of heat treatment on room and high temperature strength of 316L stainless steel fabricated by PBF-LB N2 - Laser Powder Bed Fusion (PBF-LB/M) enables the fabrication of 316L stainless steel components with superior strength and intricate geometries. The alloy PBF-LB/M/316L features a fully austenitic microstructure with hierarchical characteristics— such as fine dislocation structures, segregated elements, low-angle grain boundaries, and nano-dispersed silicates—that enhance strength and ductility. Additionally, it includes metallurgical defects and residual stresses. Apart from process control, heat treatments (HTs) are used to tailor the microstructure for specific loading conditions. This study investigate the effects of post-processing HTs on the hierarchical microstructure and tensile properties of PBF-LB/M/316L at room and high temperature. The heat treatments, ranging from 400 °C to 900 °C for 1 to 4 hours, focus on sub-recrystallization temperatures to preserve the microstructural hierarchy. The HTs applied had minimal impact on the grain shape, size, or texture of PBF-LB/M/316L. However, significant modifications occurred in the solidification cellular substructure after HTs at 800 °C and 900 °C, when compared to a heat-treated condition at 450 °C. HTs at 800 °C notably decreased dislocation density and enlarged cellular structures, though they remained partially intact. After 1 hour at 900 °C, the cellular substructure dissipated, correlating with a further reduction in dislocation density. These microstructural changes resulted in a decreased yield strength and increased work hardening capacity at both room and high temperature, highlighting the critical link between HT parameters, microstructural evolution, and mechanical performance. T2 - The 20th International Conference on Strength of Materials (ICSMA 20) CY - Kyoto, Japan DA - 02.06.2025 KW - Additive manufacturing KW - 316L stainless steel KW - Heat treatments KW - Tensile properties KW - Microstructure PY - 2025 AN - OPUS4-63914 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Suárez Ocano, Patricia T1 - Effect of heat treatment on the hierarchical microstructure and properties of 316L stainless steel produced by Laser Powder Bed Fusion (PBF-LB/M). N2 - Laser Powder Bed Fusion (PBF-LB/M) of AISI 316L stainless steel has gained popularity due to its exceptional capacity to produce complex geometries and hierarchical microstructures, which can increase the yield strength while maintaining good ductility. Nevertheless, owing to high thermal gradients encountered during the process, the as printed 316L stainless steel often exhibit microstructural heterogeneities and residual stresses, which can limit its performance in demanding environments. Hence, employing heat treatments which balance the reduction of residual stresses while retaining improved static strength may be beneficial in various scenarios and applications. This study investigates the impact of post-processing heat treatments on the microstructure of 316L stainless steel manufactured via PBF-LB/M, along with its correlation with micro-hardness properties. To this end, 6 different heat treatments, i.e., 450 °C for 4h, 700 °C for 1h, 700 °C for 3h, 800 °C for 1h, 800 °C for 3h, and 900 °C for 1h, were applied to different specimens and Vickers hardness measurements (HV1) were performed in all states. At 800 °C, although the cellular structure appears to be retained, there is an observable increase in cellular size. However, while treatments exceeding 900 °C indicate no significant grain growth compared to other conditions, the cellular structure is entirely dissolved, which leads to a reduced Vickers hardness. The effect of the heat treatments on other microstructural features such as grain size and morphology, melt pool boundaries (MPB), crystallographic texture, chemical segregation, dispersoids and phase stability are also discussed in the present work T2 - 4th Symposium on Materials and Additive Manufacturing CY - Berlin, Germany DA - 12.06.2024 KW - Additive manufacturing KW - Heat treatment KW - Microstructure PY - 2024 AN - OPUS4-60304 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - D'Accardi, E. A1 - Ulbricht, Alexander A1 - Krankenhagen, Rainer A1 - Palumbo, D. A1 - Galietti, U. T1 - Capability of active thermography to detect and localize pores in Metal Additive Manufacturing materials N2 - Active thermography is a fast, contactless and non-destructive technique that can be used to detect internal defects in different types of material. Volumetric irregularities such as the presence of pores in materials produced by the Additive Manufacturing processes can strongly affect the thermophysical and the mechanical properties of the final component. In this work, an experimental investigation aimed at detecting different pores in a sample made of stainless AISI 316L produced by Laser Powder Bed Fusion (L-PBF) was carried out using pulsed thermography in reflection mode. The capability of the technique and the adopted setups in terms of geometrical and thermal resolution, acquisition frequency and energy Density of the heating source were assessed to discern two contiguous pores as well as to detect a single pore. Moreover, a quantitative indication about the minimum resolvable pore size among the available and analysed defects was provided. A powerful tool to assess the Limits and the opportunities of the pulsed technique in terms of detectability and localizability was provided by comparing active thermography results to Computed Tomography as well as a related Finite Element Analysis (FEA) to simulate the pulsed heating transfer with Comsol. T2 - 49th Italian Association for Stress Analysis Conferencee (AIAS 2020) CY - Online meeting DA - 02.09.2020 KW - Additive manufacturing KW - Laser powderbed fusion KW - Pores KW - Thermography KW - Micro-CT PY - 2021 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-519231 DO - https://doi.org/10.1088/1757-899X/1038/1/012018 VL - 1038 SP - 1 EP - 17 PB - Institute of Physics CY - London AN - OPUS4-51923 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Ferrari, Bruno T1 - Microstructural evolution of PBF-LB/M Inconel 718 during solution-aging heat treatments - an in-situ x-ray diffraction study N2 - Inconel 718 (IN718) is a traditional age-hardenable nickel-based alloy that has been increasingly processed by additive manufacturing (AM) in recent years. In the as-solidified condition, IN718 exhibits chemical segregation and the undesired Laves phase, requiring a solution annealing (SA) prior to aging. The material produced by AM does not respond to the established thermal routines in the same way as conventionally produced IN718, and there is still no consensus on which routine yields optimal results. This work aims to provide a fundamental understanding of the heat treatment (HT) response by continuously monitoring the microstructural evolution during SA via time-resolved synchrotron x-ray diffraction, complemented by ex-situ scanning electron microscopy (SEM). The samples were produced by laser powder bed fusion to a geometry of 10x20x90 mm³, from which Ø1x5 mm³ cylindric specimens were extracted. Two different scanning strategies – incremental 67° rotations, Rot, and alternating 0°/67° tracks, Alt – were used, leading to two different as-built conditions. 1-hour SAs were carried out in the beamline ID22 of the ESRF at 50 KeV. Two SA temperatures, SA1 = 1020 °C, and SA2 = 1080 °C were tested for each scanning strategy. Data were processed using the software PDIndexer. In the as-built state, all samples showed typical subgrain columnar cell structures with predominant Nb/Mo segregation and Laves phase at the cell walls, as seen by SEM. The Alt scan induced higher intensity on the Laves peaks than the Rot scan, suggesting a greater content of Laves. Chemical homogenization in the SA was largely achieved during the heating ramp (Fig. 1). SA2 eliminated the Laves peaks just before reaching 1080 °C, and mitigated differences between Rot and Alt samples. On the other hand, SA1 induced the precipitation of the generally detrimental δ phase, also observed by SEM. Furthermore, the Rot scan showed higher δ peak intensities than the Alt scan, indicating a higher content of δ in the latter. No signs of recrystallization were observed in any of the investigated SAs. T2 - FEMS EUROMAT 2023 CY - Frankfurt a. M., Germany DA - 03.09.2023 KW - Additive Manufacturing KW - X-Ray Diffraction KW - Inconel 718 KW - Heat Treatments KW - Microstructure PY - 2023 AN - OPUS4-58392 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Waske, Anja T1 - A unique authenticator for additively manufactured parts derived from their microstructure N2 - The international research community is currently devoting extensive resources to the development of digital material data spaces and the associated digital twins and product passports of materials and components. A common weak link in these projects to date has been the connection between physical components / samples and their digital data and documents. This is where the concept of the unique identification comes in. Components produced using additive manufacturing can be marked for unique identification and secure authentication [1,2]. Serial numbers and machine-readable codes can be used to identify the component, and link digital product-related data (i.e., a digital product passport) to the actual components. The most prevailing solution consists of local process manipulation, such as printing a quick response (QR) code [3] or a set of blind holes on the surface or the internal cavity of hollow components. However, local manipulation of components may alter the properties, and external tagging features can be altered or even removed by post-processing treatments. This work provides a new methodology for identification, authentication, and traceability of additively manufactured (AM) components using microstructural features that are unique to each part. X-ray computed tomography (XCT) was employed to image the microstructural features of a batch of AlSi10Mg parts. Based on size and geometry, the most prominent features were selected to create a unique digital authenticator. We implemented a framework in Python using open-access modules that can successfully create a digital object authenticator using the segmented microstructure information from XCT. We show that this method allows to authenticate individual parts from the build job based on its microstructural fingerprint. This is our contribution to enhancing the security and product protection of additively manufactured components. T2 - FEMS EUROMAT CY - Granada, Spain DA - 15.09.2025 KW - Authentication KW - Fingerprint KW - Non-destructive testing PY - 2025 AN - OPUS4-65202 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Waske, Anja T1 - A unique authenticator for additively manufactured parts derived from their microstructure N2 - Components produced using additive manufacturing can be marked for unique identification and secure authentication [1,2]. Serial numbers and machine-readable codes can be used to identify the component, and link digital product-related data (i.e., a digital product passport) to the actual components. The most prevailing solution consists of local process manipulation, such as printing a quick response (QR) code [3] or a set of blind holes on the surface of the internal cavity of hollow components. However, local manipulation of components may alter the properties, and external tagging features can be altered or even removed by post-processing treatments. This work therefore aims to provide a new methodology for identification, authentication, and traceability of additively manufactured (AM) components using microstructural features that are unique to each part. X-ray computed tomography (XCT) was employed to image the microstructural features of AlSi10Mg parts. Based on size and geometry, the most prominent features were selected to create a unique digital authenticator. We implemented a framework in Python using open-access modules that can successfully create a digital object authenticator using the segmented microstructure information from XCT. The authenticator is stored as a QR code, along with the 3D information of the selected features. T2 - MRS Spring Meeting Seattle CY - Seattle, WA, USA DA - 07.04.2025 KW - Additive Manufacturing KW - Fingerprint KW - Non-destructive testing PY - 2025 AN - OPUS4-65199 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Hejazi, Bardia T1 - X-ray Computed Tomography Image Compression and Denoising with AI N2 - The ever-growing volume of data in imaging sciences stemming from advancements in imaging technology, necessitates efficient and reliable storage solutions for such large datasets. In this study, we investigated the compression of industrial X-ray computed tomography (XCT) data using deep learning and examined how these compression algorithms affect the quality of the recovered data. To determine best strategies, we investigated two different network architectures with different compression rates. The XCT data used was from a sandstone sample with a complex internal pore network. The quality of the recovered images obtained from the two different deep learning architectures with different compression rates were quantified and compared to the original input data. We showed that the most suitable architecture and compression rate can change, depending on what specific characteristics we would need to preserve for later analysis. The findings presented here can aid scientists in determining the best approaches and strategies for their data storage and analysis requirements. T2 - BAM AI & ML Symposium CY - Berlin, Germany DA - 06.11.2025 KW - X-ray computed tomography KW - Compression KW - Deep Learning PY - 2025 AN - OPUS4-65610 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -