119092 research outputs found
Sort by
Monetarisierung einer industriellen Datenbasis : der EuProGigant-Ansatz
No full textDatenökosysteme in produzierenden Unternehmen eröffnen neue Möglichkeiten der Wertschöpfung zwischen Dateninhabern, -anbietern und -nutzern im industriellen Kontext. Geschäftsmodelle für föderierte Datenaustauschplattformen tragen dabei zur Schaffung zusätzlicher Einnahmen und Einsparungen durch die Bereitstellung und Nutzung von industriellen Daten bei. Besonders für kleine und mittlere Unternehmen (KMU) ist das Teilen von Daten von entscheidender Bedeutung, da es ihnen ermöglicht, von externen Daten zu profitieren, ohne die vollen Kosten und den Ressourcenaufwand allein tragen zu müssen. Der effiziente Datenaustausch kann somit die Innovationskraft, Wettbewerbsfähigkeit und langfristige Entwicklung von KMU fördern. In diesem Beitrag werden Ergebnisse aus der Entwicklung von Ökosystemen und Geschäftsmodellen im Rahmen des Gaia-X Leuchtturmprojekts EuProGigant für die produzierende Industrie präsentiert. Dabei wird verdeutlicht, wie unterschiedliche Akteure in Fertigungsökosystemen den vertrauensvollen Austausch von Daten fördern und davon profitieren können. Zusätzlich wird aufgezeigt, wie mehrseitige, innovative Geschäftsmodelle entwickelt und umgesetzt werden können, um den spezifischen Interessen der Beteiligten gerecht zu werden. Das Ziel ist, praxisnahe Anwendungsbeispiele darzustellen und die damit verbundenen Potenziale zur Monetarisierung von industriellen Daten zu veranschaulichen
Data-Driven Anomaly Detection of Powder Bed Fusion with Acoustic Emission Data
No full textPowder bed fusion with Laser Beam (PBF-LB) is an additive manufacturing process used extensively in highvalue industries such as aerospace, automotive, and medical engineering, due to its ability to produce complex and lightweight components. Ensuring consistent quality and detecting defects in real time is critical to optimizing production quality and minimizing waste. This work proposes a data-driven approach for anomaly detection in PBF using acoustic emission (AE) and microphone data compared to optical solutions. AE sensors, with their high sampling rate, provide rich information in the high-frequency range, enabling the detection of abrupt changes in the process that may indicate anomalies. By applying convolutional neural networks (CNNs), adapted from image processing, to the spectrogram of the AE data we aim to efficiently detect defects, which shows the potential to save energy, material, time, and
costs in manufacturing. The results with AE data are also evaluated in comparison with microphone and optical signals
Terminologische Integration in akademischen Fachkulturen. Ein korpuspragmatischer Zugang
No full textDer Beitrag beschäftigt sich damit, wie Termini in wissenschaftliche Texte eingeführt werden. Dabei gibt es grundsätzlich zwei Fälle: Erstens kann ein bestehender Terminus in einen Text eingeführt werden; zweitens kann ein Terminus neu eingeführt und im Fachdiskurs vorgeschlagen werden. In diesem Beitrag wird untersuchen wir den ersten, wesentlich häufigeren Fall. Unser Fokus liegt dabei auf den Textroutinen der Implementierung von Termini - bspw. unterschiedlichen Referenzierungspraktiken, Relevanzmarkierungen, Formen der Differenzierung, Strukturierung, Einordnung und Abgrenzung sowie der Kontextualisierung. Wir beleuchten Gemeinsamkeiten und Unterschiede solcher Fälle in der Breite der akademischen Fachkulturen
Einsatz von Fernerkundungsdaten und KI-Methoden zur nachhaltigen Landnutzung
No full textEine nachhaltige Flächeninanspruchnahme und der Erhalt schützenswerter Landschaften stellen zentrale Themen dar. Der vorliegende Beitrag untersucht die Einsatzpotenziale von innovativen Analysemethoden von Fernerkundungsdaten zur Verbesserung des Monitorings von Naturschutzmaßnahmen und Landnutzungsänderungen. Das spezifische Monitoring erfolgte mittels Bilddaten-Analyse aus Satellitendaten sowie durch gezielte Auswertung von Luftbildaufnahmen aus Befliegungen. Hierzu wurden entsprechende Auswertungsarithmetiken entwickelt, die je nach Anwendungsfall Geodaten und Statistiken ausgeben. Visualisiert und zur weiteren Analyse bereitgestellt wurden diese mittels eines webgestützten Geoinformationssystems, welches in einem Workshop mit Experten evaluiert wurde. Es kann festgestellt werden, dass die Verarbeitung von Fernerkundungs- und Geodaten mit den Methoden der künstlichen Intelligenz Fachanwender beim Monitoring von Naturschutzmaßnahmen und Landnutzung effektiv unterstützen können. Dadurch können Entwicklungen in Natur- und Landschaftsschutz besser nachvollzogen und bei Bedarf früher gegengesteuert werden
3D gold nanowire networks with tailorable surface wetting state: from rose‐petal effect to super‐hydrophilicity
No full textThis study demonstrates the different wetting states that can be achieved by varying the diameter and density of nanowires in free‐standing 3D gold nanowire networks. This network structure consists of nanowires oriented at 45° to the horizontal plane and interconnected from four different directions. Sessile drop measurements on these tailored nanostructured films show a transition from hydrophilic to hydrophobic behavior as porosity increases from 20% to 98%. With tailored porosity from 60% to 80%, this nanostructure can exhibit super‐hydrophilicity. In addition, the highly porous (>90%) hydrophobic structures exhibit the rose‐petal effect, where water droplets remain pinned to the surface. These novel results demonstrate the capability to precisely control surface wetting behavior through intricate designs of nanostructures, which are crucial for a wide range of applications, including liquid transport, microfluidic devices, and sensors
Banking market consolidation in Asia: Evidence from acquirers, targets, and rivals
No full textWe analyse the financial sector consolidation in Asia by using a comprehensive sample of bank M&As from 1995 to 2021. Our results show that M&A announcements by Asian domestic acquirers are associated with significant positive stock price returns to both acquirers and their rivals. In contrast, cross‐border acquirers and their rivals experience negative but insignificant returns, while targets and their rivals record gains, regardless whether it is a domestic or cross‐border transaction. Further analyses reveal that domestic acquirers obtaining larger relative increases in their market share benefit the most, indicating that market power considerations are the primary driver behind acquirers' positive returns. For cross‐border acquirers, neither cultural differences nor regulatory arbitrage considerations can explain return patterns surrounding M&A announcements
Aging matrix visualizes complexity of battery aging across hundreds of cycling protocols
No full textTo reliably deploy lithium-ion batteries, a fundamental understanding of cycling aging behavior is critical. Battery aging consists of complex and highly coupled phenomena, making it challenging to develop a holistic interpretation. In this work, we generate a diverse battery cycling dataset with a broad range of degradation trajectories, consisting of 359 high energy density commercial Li(Ni,Co,Al)O₂/graphite + SiOₓ cylindrical 21 700 cells cycled across 207 unique cycling protocols. We consolidate aging via 16 mechanistic state-of-health (SOH) metrics, including cell-level performance metrics, electrode-specific capacities/state-of-charges (SOCs), and aging trajectory metrics. We develop a framework using interpretable machine learning and explainable features to generate an aging matrix that visually deconvolutes the complex battery degradation behavior. This generalizable data-driven mechanistic framework simplifies the complex interplay between cycling conditions, degradation modes, and SOH, acting as a hypothesis-generation tool to aid battery users in identifying key degradation regimes for further study and experimentation
Reliable machine learning models for manufacturing processes
No full textData-driven condition monitoring in manufacturing using machine learning (ML) offers great potential for operating processes reliably and cost-effectively. Particularly in blanking, a manufacturing process characterized by high production rates combined with narrow tolerances, data-driven process monitoring techniques are necessary to ensure a reliable operation. However, an inherent weakness of these data-driven techniques is their sensitivity to changes in the system configuration. Such changes directly affect the data validity and lead to shifts in the underlying data distribution, resulting in a dramatic deterioration of the model’s ability to predict a target variable. Therefore, the goal of this work is to introduce the deep hybrid modelling (DHM), which enables reliable ML-based condition monitoring even when the boundary conditions of the system fluctuate and lead to random process deviations. The potential of the introduced strategy is demonstrated by predicting the abrasive wear state during a blanking operation with the simultaneous occurrence of a data shift due to a random fluctuation of the semi-finished product parameters. In addition, a similarity measure is introduced that allows a user-friendly and computationally efficient quantification of the data shift and the associated magnification of the occurring fluctuations in the process boundary conditions. To ensure a reliable ML-based prediction depending on the magnitude of the data shift, different modelling frameworks are introduced. For this purpose, a resilient modelling strategy based on DHM and a flexible modelling strategy based on domain adaptation technique called adaptive DeepCORAL are proposed
Shape function-based strain determination in DIC for solids and lattice structures
No full textBackground: Additive Manufacturing offers the opportunity to build lattice structures with benefits in manufacturing efficiency and weight. For the determination of the fatigue properties of lattice structures, it lacks a method to determine the deformation under mechanic stress.
Objective: A digital image correlation (DIC) algorithm was implemented. The algorithm determines strains within a subset in an uncommon way by physically interpreting the subset shape function and does not need neighboring subsets, therefore.
Method: With a monochrome background this shape function-based strain determination is able to determine the deformation of a whole lattice unit cell, even if the background is visible in sectors of the subset. The implementation is validated by comparing the results in quasi-static tests on bulk material specimens to the results tactile sensors and a conventional DIC program. Then the deformation of lattice unit cells in fatigue tests is evaluated.
Results: The shape function-based strain determination performs well in quasi-static tests even for large deformations. The deformation of lattice unit cells is determined successfully, whereby conventional DIC algorithms can be challenged if the lattice’s strut diameter becomes close to the image resolution. The determined strains are appropriate for lifetime prediction and fractures can be detected.
Conclusion: The shape function-based strain determination is a suitable tool for determination of large local strains as well as strains in lattice structures, which do partially not cover the background in the whole region of interest due to periodic empty spaces between the lattice struts. For determination of strain fields, conventional DIC algorithms will still be more efficient in this state of development
Crack segmentation for high-speed imaging: detection of fractures in thermally toughened glass
No full textFracture morphology characterization in broken glass panes is crucial for designing laminated safety glass (LSG) in civil engineering. Verifying completely broken LSG systems requires destructive sampling, increasing costs and hindering development. Therefore, to determine the residual load-bearing capacity, the link between the pre-fracture characteristics and the fracture morphology must be known. However, when the crack propagation needs to be directly captured with high-speed imaging, conventional methods are no longer sufficient for detecting cracks. To enable such investigations, we propose a novel machine learning framework for crack segmentation in high-speed imaging that addresses the complexity of glass fracture and minimises the required labour costs. In this study, the crack propagation of a sample was recorded and analysed at 2,000,000 images per second. The results showcase accuracies surpassing 97% while requiring only two labeled images for training, thus streamlining practical implementation. Furthermore, we show the method's robustness to the extent that hyperparameter tuning becomes unnecessary. Instead, we offer guidelines for selecting the most crucial hyperparameters depending on the problem. Our method offers a promising approach for non-linear temporal interpolation of noisy images, with implications for various applications extending beyond glass fracture analysis