TY - CONF A1 - Paul, Nathalie A1 - Kister, Alexander A1 - Schnellhardt, Thorben A1 - Fetz, Maximilian A1 - Hecker, Dirk A1 - Wirtz, Tim ED - Meo, Rosa ED - Silvestri, Fabrizio T1 - Reinforcement Learning for Segmented Manufacturing N2 - The manufacturing of large components is, in comparison to small components, cost intensive. This is due to the sheer size of the components and the limited scalability in number of produced items. To take advantage of the effects of small component production we segment the large components into smaller parts and schedule the production of these parts on regular-sized machine tools. We propose to apply and adapt recent developments in reinforcement learning in combination with heuristics to efficiently solve the resulting segmentation and assignment problem. In particular, we solve the assignment problem up to a factor of 8 faster and only a few percentages less accurate than a classic solver from operations research. T2 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2023 CY - Turin, Italy DA - 18.09.2023 KW - Reinforcement Learning KW - Assignment Problem KW - Large component manufacturing PY - 2025 DO - https://doi.org/10.1007/978-3-031-74640-6_38 VL - 1 IS - 1 SP - 470 EP - 485 PB - Springer Cham AN - OPUS4-63031 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Bintz, Thilo A1 - Kruschwitz, Sabine T1 - Non-destructive Testing for the Determination of Durability-Relevant Material Properties of Clinker-Reduced Building Materials N2 - In the quest to combat climate change, the construction industry, heavily reliant on cement-based materials, faces scrutiny due to significant CO2 emissions, mainly from clinker production. To address this, there’s a need to strategically reduce clinker content in cement. However, these new formulations must meet the same requirements as the original ones, so their durability must be investigated. In this study, we determined material parameters that enable an assessment of moisture and ion transport. These methods offer advantages over conventional approaches, including non-destructiveness, reduced measurement time, simplified setup, enhanced resolution, and improvement of detection limits. Our investigation utilizes NDT techniques, using 1H NMR relaxometry for moisture transport and LIBS for ion transport in various clinker-reduced materials. The NMR tomograph provides spatial insights into internal moisture transport, correlated with weight change assessments for the capillary transport coefficient. Additionally, based on NMR relaxometry data the chloride diffusion coefficient is estimated. Chloride migration tests are performed, and results are evaluated using LIBS and indicator tests for the chloride migration coefficient. Our findings highlight NMR relaxometry and LIBS advantages over conventional methods, showcasing superior spatial resolution, non-destructiveness, and, in some cases, expedited results with independence from the formulation of the cement matrix. Thus, these new methods can be used to test the durability of new, more heterogeneous cementbased building. T2 - Rilem Spring Convention 2024 CY - Milano, Italy DA - 10.04.2024 KW - NMR relaxometry KW - LIBS KW - Clinker reduced cement KW - Durability parameters PY - 2025 SN - 978-3-031-70281-5 DO - https://doi.org/10.1007/978-3-031-70281-5_48 VL - 56 SP - 426 EP - 434 AN - OPUS4-61824 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Ermilova, Elena A1 - Hertwig, Andreas A1 - Döhring, Thorsten A1 - Stanik, Eva A1 - Cotroneo, Vincenzo A1 - Gibertini, Eugenio T1 - Ellipsometrical characterization of poly-dopamine layers considered for technical applications N2 - Although the organic molecule dopamine (3,4-dihydroxyphenethylamine) is commonly known as the “hormone of happiness”, thin films of poly-dopamine also have interesting technical properties. When produced by dip coating, the self-organizing layers grow in a reproducible thickness of single or multiple molecule monolayers of a few nanometer thickness only. In this work, we introduce a method of determining the layer thickness of poly-dopamine on mirrors for astronomical X-ray telescopes. This work is based on spectroscopic ellipsometry measurements and involves the development of an optical model for the poly-dopamine layers including the dielectric function. Thereby the complex refractive index of the produced layers was determined, covering the range from the ultraviolet to the near infrared spectral region. These measurement results and the corresponding technical challenges are presented in this contribution. Furthermore, an outlook to potential technical applications of this interesting material is given and poly-dopamine layers will make scientist and engineers hopefully happy as an innovative and fascinating technical solution for the future. T2 - SPIE PHOTONICS EUROPE CY - Strasbourg. France DA - 08.04.2024 KW - Polydopamine KW - Thin Solid Layers KW - X-ray optics KW - Spectroscopic Ellipsometry PY - 2024 SN - 978-1-5106-7344-1 DO - https://doi.org/10.1117/12.3015281 VL - 13013 SP - 1 EP - 8 PB - SPIE digital library AN - OPUS4-60954 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Weichert, Dorina A1 - Kister, Alexander A1 - Houben, Sebastian A1 - Link, Patrick A1 - Ernis, Gunar ED - Kiyavash, Negar ED - Mooij, Joris M. T1 - Robust Entropy Search for Safe Efficient Bayesian Optimization N2 - The practical use of Bayesian Optimization (BO) in engineering applications imposes special requirements: high sampling efficiency on the one hand and finding a robust solution on the other hand. We address the case of adversarial robustness, where all parameters are controllable during the optimization process, but a subset of them is uncontrollable or even adversely perturbed at the time of application. To this end, we develop an efficient information-based acquisition function that we call Robust Entropy Search (RES). We empirically demonstrate its benefits in experiments on synthetic and real-life data. The results show that RES reliably finds robust optima, outperforming state-of-the-art algorithms. T2 - UAI 2024 CY - Barcelona, Spain DA - 15.07.2024 KW - Bayesian Optimization KW - Gaussian process KW - Active learning PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-613523 UR - https://proceedings.mlr.press/v244/weichert24a.html SN - 2640-3498 VL - 244 SP - 3711 EP - 3729 PB - Proceedings of Machine Learning Research AN - OPUS4-61352 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph A1 - John, Elisabeth A1 - Firdous, Rafia A1 - Hirsch, Tamino A1 - Kaczmarek, Daria A1 - Ziesack, Kevin A1 - Buchwald, Anja A1 - Stephan, Dietmar A1 - Kruschwitz, Sabine ED - Ferrara, Liberato ED - Muciaccia, Giovanni ED - di Summa, Davide T1 - Beyond Theory: Pioneering AI-Driven Materials Design in the Sustainable Building Material Lab N2 - This work focuses on Artificial Intelligence (AI)-driven materials design, addressing the challenge of improving the sustainability of building materials amid complex formulations. These formulations involve various components, such as binders, additives, and recycled aggregates, necessitating a balance between environmental impact and performance. Traditional experimental methods often fall short in managing the complexity of material composition, hindering fast enough development of optimal solutions. Our research explores complex composition materials design through a comprehensive, comparative lab study between Data-Driven Design, using SLAMD - an open-source AI materials design tool, and traditional Design of Experiments (DOE). We aimed to develop a high-performance, alkali-activated material using secondary precursors, aiming for a compressive strength exceeding 100 MPa after 7-days. The findings reveal that AI-driven design outperforms DOE in development speed and material quality, successfully identif. T2 - 4 RILEM Spring Convention and Conference on advanced construction materials and processes for a carbon neutral society 2024 CY - Milano, Italy DA - 07.04.2024 KW - Secondary Raw Materials KW - Data-Driven Design KW - Sequential Learning KW - Design of Experiments KW - Alkali-Activated Binder PY - 2024 SN - 978-3-03170281-5 DO - https://doi.org/10.1007/978-3-031-70281-5_31 SN - 2211-0852 VL - 2 SP - 274 EP - 282 PB - Springer AN - OPUS4-61662 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Zia, Ghezal Ahmad Jan A1 - Völker, Christoph A1 - Moreno Torres, Benjami A1 - Kruschwitz, Sabine T1 - An Adaptive Upscaling Approach for Assessing Materials’ Circularity Potential with Non-destructive Testing (NDT) N2 - Advancing towards a circular economy necessitates the efficient reuse and maintenance of structural materials, which relies on accurate, non-damaging condition assessments. This paper introduces an innovative AI-driven adaptive sampling (AS) technique integrated with Non-Destructive Testing (NDT) to optimize this process. AS focuses on critical data points, reducing the amount of data needed for precise assessments—evidenced by our method requiring on average only 7 samples for Logistic Regression and 8 for Random Forest, contrasted with 29 for traditional sampling. By reducing the necessity for extensive data collection, our method not only streamlines the assessment process but also significantly contributes to the sustainability goals of the circular economy. These goals include resource efficiency, waste reduction, and material reuse. Efficient condition assessments promote infrastructure longevity, reducing the need for new materials and the associated environmental impact. The circular economy aims to create a sustainable system where resources are reused, and waste is minimized. This is achieved by extending the lifecycle of materials, reducing the environmental footprint, and promoting recycling and reuse. Longevity directly contributes to the circular economy by maximizing the utility and lifespan of existing materials and structures. Longer-lasting infrastructure means fewer resources are needed for repairs or replacements, leading to reduced material consumption and waste generation. This aligns with the circular economy's principles of sustainability and resource efficiency. This research not only advances the field of structural health monitoring but also aligns with the broader objective of enhancing sustainable construction practices within the circular economy framework. T2 - Rilem Spring Convention CY - Milano, Italy DA - 09.04.2024 KW - Adaptive Sampling KW - Random Sampling KW - Machine Learning KW - Non-Destructive Testing KW - Condition Assessment KW - Circular Economy PY - 2024 SN - 978-3-031-70277-8 DO - https://doi.org/10.1007/978-3-031-70277-8_38 SN - 2211-0844 VL - 55 SP - 330 EP - 338 PB - Springer Nature Switzerland CY - Switzerland AN - OPUS4-62458 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Munsch, Sarah Mandy A1 - Telong, Melissa A1 - Grobla, Lili A1 - Schumacher, Katrin A1 - Völker, Christoph A1 - Yared, Kaleb A1 - Kruschwitz, Sabine ED - Ferrara, Liberato ED - Muciaccia, Giovanni ED - di Summa, Davide T1 - Study on the Predictability of Carbonation Resistance of Cementitous Materials Based on NMR Features and the Use of SLAMD N2 - This study explores the acceleration of material design in the concrete industry, focusing on improving carbonation resistance, a key factor in the durability of concrete structures. Traditional tests for carbonation resistance are lengthy, but with the construction industry aiming for sustainable production, finding a balance between carbonation resistance and CO2 footprint is crucial. Our research employs two innovative methods: 1. Applying the Sequential Learning App for Materials Discovery (SLAMD), an AI materials design framework, to an extensive dataset of real-world concrete compositions to selectively test materials that meet market demands: maximum durability, optimal eco-durability, and the best cost-durability trade-off. 2. Investigating 1H Nuclear Magnetic Resonance (NMR) relaxometry as a quick alternative for characterizing carbonation behavior, as it saves time compared to traditional tests and assesses the complete material’s pore space. Specific NMR features are then integrated into the material design model, with the model’s performance compared against traditional approaches. The results of our study are compelling, demonstrating that materials can be precisely tailored to meet specific requirements with minimal data points. This marks a significant stride in the concrete industry, indicating thatNMR-based, lowfidelity surrogate characterizations, combined with a focused, data-driven design approach, can substantially accelerate the development of durable, sustainable concrete mixtures. T2 - 4 RILEM Spring Convention and Conference on advanced construction materials and processes for a carbon neutral society 2024 CY - Milano, Italy DA - 07.04.2024 KW - Nuclear magnetic resonance KW - carbonation resistance KW - cement and concrete KW - SLAMD app KW - predictability PY - 2024 DO - https://doi.org/10.1007/978-3-031-70281-5_49 VL - 2 SP - 435 EP - 442 PB - Springer CY - Cham, Switzerland AN - OPUS4-61692 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Kaiser, Sebastian A1 - Erxleben, Kjell A1 - Rhode, Michael A1 - Kannengießer, Thomas T1 - Repair Welding of In-Service Hydrogen Pipelines - Concepts and Challenges N2 - Hydrogen is set as the energy carrier of tomorrow for a more sustainable fossil fuel free future. As this necessitates a reliable transport infrastructure, repurposing of the existing natural gas grid is planned. With regards to the well-known effect of hydrogen embrittlement, the compatibility of utilized materials must be investigated. First comprehensive studies on pipeline material hydrogen compatibility indicate that these materials can be applied to a certain extent. Nonetheless, the material compatibility is currently of high interest and focus of numerous research projects worldwide. However, pipelines require frequent maintenance and repair work. As part of these, in some cases it is necessary to do weldments onto pipelines while they are pressurized. This in-service welding introduces additional challenges for the material compatibility. Due to the resulting high temperatures, the metallurgical changes in the material and of course the presence of high-pressure hydrogen in the pipeline, additional investigations need to be conducted to ensure that no critical material degradation because of increased hydrogen absorption occurs and an overall material compatibility is given. For this reason, the present paper introduces in-service welding on pipelines. An overview of current research projects that deal with the application of in-service welding specifically on hydrogen pipelines and the emerging problems when applying these techniques on hydrogen pipelines is given. Methods of material testing, their limits and possible solutions are presented and discussed. T2 - 2024 15th International Pipeline Conference CY - Calgary, Alberta, Canada DA - 23.09.2024 KW - Hydrogen KW - Pipeline KW - Welding KW - In-Service PY - 2024 SN - 978-0-7918-8856-8 DO - https://doi.org/10.1115/IPC2024-133052 SP - 1 EP - 6 PB - The American Society of Mechanical Engineers (ASME) CY - New York AN - OPUS4-62262 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Jaunich, Matthias A1 - Goral, Milan A1 - Sagradov, Ilja A1 - Wolff, Dietmar A1 - Völzke, Holger T1 - Aging investigations of metal seals used in containers for interim storage of spent fuel N2 - For bolted casks for used fuel and high level waste the sealing system has an important impact of ensuring safe enclosure of the inventory The used metal seals show some changes over time which have been addressed for nearly 15 years in running experiments at BAM The observed changes are temperature de pendent and therefore it is expected that test s at higher temperature allow for an acceleration of the effects and ideally the proposal of an ageing model covering the expected time of use . Nevertheless, questions concerning the influence of the experimental approach on the results and effects taking place at the initial days of ageing remain. To address these a new project was launched to give a better understanding of the seal behavior. T2 - PVP2024, Pressure Vessels & Piping Conference CY - Bellevue, WA, USA DA - 29.07.2024 KW - Metal seal KW - Aging KW - Interim storage PY - 2024 SN - 978-0-7918-8851-3 SP - 1 EP - 4 PB - ASME AN - OPUS4-61357 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Bhadeliya, Ashok A1 - Rehmer, Birgit A1 - Fedelich, Bernard A1 - Jokisch, Torsten A1 - Skrotzki, Birgit A1 - Olbricht, Jürgen T1 - High Temperature Fatigue Crack Growth in Nickel-Based Alloys Refurbished by Additive Manufacturing N2 - Hybrid additive manufacturing plays a crucial role in the restoration of gas turbine blades, where, e.g., the damaged blade tip is reconstructed by the additive manufacturing process on the existing blade made of a parent nickel-based alloy. However, inherent process-related defects in additively manufactured material, along with the interface created between the additively manufactured and the cast base material, impact the fatigue crack growth behavior in bi-material components. This study investigates the fatigue crack growth behavior in bi-material specimens of nickel-based alloys, specifically, additively manufactured STAL15 and cast alloy 247DS. The tests were conducted at 950 °C with stress ratios of 0.1 and −1. Metallographic and fractographic investigations were carried out to understand crack growth mechanisms. The results revealed significant retardation in crack growth at the interface. This study highlights the potential contributions of residual stresses and microstructural differences to the observed crack growth retardation phenomenon, along with the conclusion from an earlier study on the effect of yield strength mismatch on crack growth behavior at a perpendicular interface in bi-material specimens. T2 - Superalloys 2024 Conference CY - Champion, Pennsylvania, USA DA - 08.09.2024 KW - Fatigue crack growth KW - Bi-material structure KW - Additive manufacturing KW - Nickel-based alloys PY - 2024 SN - 978-3-031-63937-1 DO - https://doi.org/10.1007/978-3-031-63937-1_92 SN - 2367-1181 SN - 2367-1696 VL - 15th SP - 994 EP - 1001 PB - Springer CY - Cham AN - OPUS4-60907 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -