TY - GEN A1 - Fahrion, Marc-Steffen A1 - Draeger, Susan A1 - Lakatos, Michael A1 - Schmidt, Timo A1 - Nickl, Christoph A1 - Brombacher, Moritz A1 - Bangalore, Deekshitha A1 - Sundermann, Wolfgang T1 - KLIBAU – Weiterentwicklung und Konkretisierung des Klimaangepassten Bauens : Handlungsempfehlungen für Planer und Architekten Y1 - 2019 UR - https://www.bbsr.bund.de/BBSR/DE/forschung/programme/zb/Auftragsforschung/5EnergieKlimaBauen/2018/klibau/handlungsempfehlungen.pdf?__blob=publicationFile&v=4 ER - TY - GEN A1 - Walther, Dominik A1 - Schmidt, Leander A1 - Räth, Timo A1 - Schricker, Klaus A1 - Bergmann, Jean Pierre A1 - Sattler, Kai-Uwe A1 - Mäder, Patrick T1 - Deep learning-driven active sheet positioning using linear actuators in laser beam butt welding of thin steel sheets T2 - Journal of advanced joining processes N2 - Welding thin steel sheets in industrial applications is difficult because joint gaps occur during the process, which can lead to weld interruptions. Such welds are considered a reject and in order to avoid the weld to interrupt it is crucial to hinder the formation of joint gaps. Especially laser beam welding is affected by the emergence of gaps. Due to the narrow laser spot, product quality is highly dependent on the alignment and positioning of the sheets. This is typically done by clamping devices, which hold the workpieces in place. However, these clamps are suited for a specific workpiece geometry and require manual redesign every time the process changes. Adaptive clamping devices instead are designed to realize a time-dependent workpiece adjustment. Modeling the joint gap behavior to realize a controller for adaptive clamps can be difficult as the influence of heating, melting, and cooling on the joint gap formation is unknown and varies due to temperature dependent physical properties. Instead, the control parameters and actions can be derived using data-driven methods. In this paper, we present a novel data-driven approach how deep learning can be utilized to manipulate the sheet position during the weld with two actuators that apply force. A temporal convolution neural network (TCN) analyzes the change of the joint gap and predicts the required force to adapt the workpiece position. The developed method has been integrated into the welding process and improves the length of the average weld seam by 39.5% compared to welds without an active adjustment and 1.4% to welds that have been adapted with a constant force. KW - Laser beam welding KW - Temporal convolutional neural network KW - Thin steel sheets KW - Inductive probes KW - Gap adjustment KW - Deep learning Y1 - 2025 U6 - https://doi.org/10.1016/j.jajp.2025.100303 SN - 2666-3309 VL - 11 SP - 1 EP - 12 PB - Elsevier BV CY - Amsterdam ER - TY - GEN A1 - Heyman, Tom A1 - Pronizius, Ekaterina A1 - Lewis, Savannah C. A1 - Acar, Oguz A. A1 - Adamkovič, Matúš A1 - Ambrosini, Ettore A1 - Antfolk, Jan A1 - Barzykowski, Krystian A1 - Baskin, Ernest A1 - Batres, Carlota A1 - Boucher, Leanne A1 - Boudesseul, Jordane A1 - Brandstätter, Eduard A1 - Collins, W. Matthew A1 - Filipović Ðurđević, Dušica A1 - Egan, Ciara A1 - Era, Vanessa A1 - Ferreira, Paulo A1 - Fini, Chiara A1 - Garrido-Vásquez, Patricia A1 - Godbersen, Hendrik A1 - Gomez, Pablo A1 - Graton, Aurelien A1 - Gurkan, Necdet A1 - He, Zhiran A1 - Johnson, Dave C. A1 - Kačmár, Pavol A1 - Koch, Chris A1 - Kowal, Marta A1 - Kratochvil, Tomas A1 - Marelli, Marco A1 - Marmolejo-Ramos, Fernando A1 - Martínez, Martín A1 - Mattiassi, Alan A1 - Maxwell, Nicholas P. A1 - Montefinese, Maria A1 - Morvinski, Coby A1 - Neta, Maital A1 - Nielsen, Yngwie A. A1 - Ocklenburg, Sebastian A1 - Onič, Jaš A1 - Papadatou-Pastou, Marietta A1 - Parker, Adam J. A1 - Paruzel-Czachura, Mariola A1 - Pavlov, Yuri G. A1 - Perea, Manuel A1 - Pfuhl, Gerit A1 - Roembke, Tanja C. A1 - Röer, Jan P. A1 - Roettger, Timo B A1 - Ruiz-Fernandez, Susana A1 - Schmidt, Kathleen T1 - Crowdsourcing multiverse analyses to explore the impact of different data-processing and analysis decisions : a tutorial T2 - Psychological methods N2 - When processing and analyzing empirical data, researchers regularly face choices that may appear arbitrary (e.g., how to define and handle outliers). If one chooses to exclusively focus on a particular option and conduct a single analysis, its outcome might be of limited utility. That is, one remains agnostic regarding the generalizability of the results, because plausible alternative paths remain unexplored. A multiverse analysis offers a solution to this issue by exploring the various choices pertaining to data-processing and/or model building, and examining their impact on the conclusion of a study. However, even though multiverse analyses are arguably less susceptible to biases compared to the typical single-pathway approach, it is still possible to selectively add or omit pathways. To address this issue, we outline a novel, more principled approach to conducting multiverse analyses through crowdsourcing. The approach is detailed in a step-by-step tutorial to facilitate its implementation. We also provide a worked-out illustration featuring the Semantic Priming Across Many Languages project, thereby demonstrating its feasibility and its ability to increase objectivity and transparency. (PsycInfo Database Record (c) 2026 APA, all rights reserved). Y1 - 2025 U6 - https://doi.org/10.1037/met0000770 SN - 1939-1463 PB - American Psychological Association (APA) CY - Washington, DC ER -