TY - CHAP A1 - Zerbst, Uwe A1 - Madia, Mauro ED - Yadroitsev, I. ED - Yadroitsava, I. ED - Du Plessies, A. ED - McDonald, E. T1 - Structural integrity II: fatigue properties N2 - If a component is cyclically loaded, its load carrying capacity is considerably lower than in the monotonic loading case. This general observation applies in particular to L-PBF parts. The causes of this are mainly material defects such as pores and unwelded regions (Chapter 8) and a pronounced surface roughness in the as-built condition (Chapter 9). In addition, effects due to the anisotropy of the microstructure (Chapter 6) and a complex residual stress pattern (Chapter 7) play an important role. A consequence is that common strategies of fatigue assessment cannot be transferred to L-PBF applications without modifications. Due to the inhomogeneity of the material, the determination of representative material properties and the transfer to the component is a problem, and this is also the case with regard to the consideration of defects, surface roughness and residual stresses. The chapter gives a brief introduction to these problem areas. KW - Fatigue crack propagation stagesdefects KW - Fatigue strength KW - Fatigue life KW - Fracture mechanics PY - 2021 SN - 978-0-12-824090-8 DO - https://doi.org/10.1016/B978-0-12-824090-8.00015-9 SP - 377 EP - 394 PB - Elsevier Inc. CY - Amsterdam ET - 1 AN - OPUS4-52854 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 - CHAP A1 - Chand, Keerthana A1 - Fritsch, Tobias A1 - Hejazi, Bardia A1 - Poka, Konstantin A1 - Bruno, Giovanni T1 - Deep Learning Based 3D Volume Correlation for Additive Manufacturing Using High-Resolution Industrial X-Ray Computed Tomography N2 - Quality control in Additive Manufacturing (AM) is vital for industrial applications in areas such as the automotive, medical, and aerospace sectors. Geometric inaccuracies caused by shrinkage and deformations can compromise the life and performance of additively manufactured components. Such deviations can be quantified using Digital Volume Correlation (DVC), which compares the Computer-Aided Design (CAD) model with the X-ray Computed Tomography (XCT) geometry of the components produced. However, accurate registration between the two modalities is challenging due to the absence of a ground truth or reference deformation field. In addition, the extremely large data size of high-resolution XCT volumes makes computation difficult. In this work, we present a deep learning-based approach for estimating voxel-wise deformations between CAD and XCT volumes. Our method uses a dynamic patch-based processing strategy to handle high-resolution volumes. In addition to the Dice score, we introduce a Binary Difference Map (BDM) that quantifies voxel-wise mismatches between binarized CAD and XCT volumes to evaluate the accuracy of the registration. Our approach shows a 9.2% improvement in the Dice score and a 9.9% improvement in the voxel match rate compared to classic DVC methods, while reducing the interaction time from days to minutes. This work sets the foundation for deep learning-based DVC methods to generate compensation meshes that can then be used in closed-loop correlations during the AM production process. Such a system would be of great interest to industry, as it would make the manufacturing process more reliable and efficient, saving time and material. KW - Deep learning PY - 2025 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-646293 DO - https://doi.org/10.3233/FAIA251475 SN - 0922-6389 VL - 413 SP - 5368 EP - 5375 PB - IOS Press AN - OPUS4-64629 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CHAP A1 - Hejazi, Bardia A1 - Chand, Keerthana A1 - Fritsch, Tobias A1 - Bruno, Giovanni T1 - D-CNN and VQ-VAE Autoencoders for Compression and Denoising of Industrial X-Ray Computed Tomography Images N2 - The ever-growing volume of data in imaging sciences stemming from advancements in imaging technologies, necessitates efficient and reliable storage solutions for such large datasets. This study investigates the compression of industrial X-ray computed tomography (XCT) data using deep learning autoencoders and examines how these compression algorithms affect the quality of the recovered data. Two network architectures with different compression rates were used, a deep convolution neural network (D-CNN) and a vector quantized variational autoencoder (VQ-VAE). The XCT data used was from a sandstone sample with a complex internal pore network as a good test case for the importance of feature preservation. The quality of the decoded images obtained from the two different deep learning architectures with different compression rates were quantified and compared to the original input data. In addition, to improve image decoding quality metrics, we introduced a metric sensitive to edge preservation, which is crucial for three-dimensional data analysis. We showed that different architectures and compression rates are required depending on the specific characteristics needed to be preserved for later analysis. The findings presented here can aid scientists in determining the requirements and strategies needed for appropriate data storage and analysis. T2 - 28th European Conference on Artificial Intelligence – Including 14th Conference on Prestigious Applications of Intelligent Systems (PAIS 2025) CY - Bologna, Italy DA - 25.10.2025 KW - Data Compression KW - Deep Learning KW - X-ray Computed Tomography PY - 2025 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-644758 UR - https://ebooks.iospress.nl/doi/10.3233/FAIA251480 DO - https://doi.org/10.3233/FAIA251480 SN - 0922-6389 SP - 1 EP - 8 PB - IOS Press AN - OPUS4-64475 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CHAP A1 - Bruno, Giovanni ED - Makul, Matt T1 - Investigation of a New Ti Alloy for a New Generation of Additively Manufactured Implants with Lattice N2 - A new titanium alloy improving the operation of implants additively manufactured and including laterally closed lattice structures is proposed. The new alloy possesses an increased affinity to the bone. The measured bone–interface implant (BII) of less than 10 mm and bone–implant contact (BIC) of 95% demonstrated an excellent osseointegration. Furthermore, since additive manufacturing naturally leads to a high-roughness surface finish, the wettability of the implant is increased. The combination of these factors is pushing ossification beyond its natural limits. In addition, the quality and speed of the ossification and osseointegration in/around laterally closed lattice implants open the possibility of bone spline key of prostheses. This enables the stabilization of the implant into the bone while keeping the possibility of punctual hooks allowing the implant to be removed more easily if required. KW - X-ray Computed tomography KW - Defects KW - Machine Learning KW - Implants KW - Lattices PY - 2024 DO - https://doi.org/10.9734/bpi/cpstr/v7/7198E VL - 7 SP - 12 EP - 37 AN - OPUS4-59754 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -